Monitoring of advanced cancer patients' health, treatment, and supportive care is essential for improving cancer survival outcomes. Traditionally, oncology has relied on clinical metrics such as survival rates, time to disease progression, and clinician-assessed toxicities. In recent years, patient-reported outcome measures (PROMs) have provided a complementary perspective, offering insights into patients' health-related quality of life (HRQoL). However, collecting PROMs consistently requires frequent clinical assessments, creating important logistical challenges. Wearable devices combined with artificial intelligence (AI) present an innovative solution for continuous, real-time HRQoL monitoring. While deep learning models effectively capture temporal patterns in physiological data, most existing approaches are unimodal, limiting their ability to address patient heterogeneity and complexity. This study introduces a multimodal deep learning approach to estimate HRQoL in advanced cancer patients. Physiological data, such as heart rate and sleep quality collected via wearable devices, are analyzed using a hybrid model combining convolutional neural networks (CNNs) and bidirectional long short-term memory (BiLSTM) networks with an attention mechanism. The BiLSTM extracts temporal dynamics, while the attention mechanism highlights key features, and CNNs detect localized patterns. PROMs, including the Hospital Anxiety and Depression Scale (HADS) and the Integrated Palliative Care Outcome Scale (IPOS), are processed through a parallel neural network before being integrated into the physiological data pipeline. The proposed model was validated with data from 204 patients over 42 days, achieving a mean absolute percentage error (MAPE) of 0.24 in HRQoL prediction. These results demonstrate the potential of combining wearable data and PROMs to improve advanced cancer care.

Recent advancements in artificial intelligence (AI) and the vast data generated by modern clinical systems have driven the development of AI solutions in medical imaging, encompassing image reconstruction, segmentation, diagnosis, and treatment planning. Despite these successes and potential, many stakeholders worry about the risks and ethical implications of imaging AI, viewing it as complex, opaque, and challenging to understand, use, and trust in critical clinical applications. The FUTURE-AI guideline for trustworthy AI in healthcare was established based on six guiding principles: Fairness, Universality, Traceability, Usability, Robustness, and Explainability. Through international consensus, a set of recommendations was defined, covering the entire lifecycle of medical AI tools, from design, development, and validation to regulation, deployment, and monitoring. In this paper, we describe how these specific recommendations can be instantiated in the domain of medical imaging, providing an overview of current best practices along with guidelines and concrete metrics on how those recommendations could be met, offering a valuable resource to the international medical imaging community.

Over the past five years, artificial intelligence (AI) has introduced new models and methods for addressing the challenges associated with the broader adoption of AI models and systems in medicine. This paper reviews recent advances in AI for medical image and video analysis, outlines emerging paradigms, highlights pathways for successful clinical translation, and provides recommendations for future work. Hybrid Convolutional Neural Network (CNN) Transformer architectures now deliver state-of-the-art results in segmentation, classification, reconstruction, synthesis, and registration. Foundation and generative AI models enable the use of transfer learning to smaller datasets with limited ground truth. Federated learning supports privacy-preserving collaboration across institutions. Explainable and trustworthy AI approaches have become essential to foster clinician trust, ensure regulatory compliance, and facilitate ethical deployment. Together, these developments pave the way for integrating AI into radiology, pathology, and wider healthcare workflows.

Patients with Parkinson's disease (PD) often exhibit speech and voice impairments early in the disease course, making these characteristics potential biomarkers for diagnosis. Additionally, PD speech analysis offers a promising avenue for monitoring disease progression in response to therapeutic interventions. In this study, we propose a novel method for distinguishing PD patients from healthy controls (HCs) through the analysis of speech task recordings. Our method integrates recurrence plots (RPs) and their corresponding quantitative descriptors with established speech features, namely Mel-spectrograms and Mel-frequency Cepstral Coefficients (MFCCs). To enrich the representation of speech signals, RPs and Mel-spectrograms are further processed to extract features using a Convolutional Neural Network (CNN). The resulting feature sets are then classified with a Support Vector Machine (SVM). Experimental evaluations on the PC-GITA speech database, as well as an analogous set of PD tasks in Greek, demonstrate the effectiveness of the proposed approach, achieving classification accuracies above 90% on the examined tasks.

Gut microbiome research has made tremendous progress, especially with the integration of machine learning and artificial intelligence that can provide new insights from complex microbiome data and its impact on human health. The use of explainable artificial intelligence is becoming critical in medicine and adopting it in precision medicine-models leveraging gut microbiome data is appealing for providing more transparency and trustworthiness in clinical research. This scoping review evaluates the use of machine learning and explainable artificial intelligence techniques and identifies existing gaps in knowledge in this research area to suggest future research directions. Online databases (PubMed and Scopus) were searched to retrieve papers published between 2018-2024, and from which we selected 76 publications. Different clinical applications of machine learning and artificial intelligence techniques in gut microbiome studies were explored in the reviewed articles. We observed a high prevalence in the use of black box models in the field, with Random Forest being the most used algorithm. The explainability remains somewhat limited in the field, but it appears to be improving. Researchers showed interest in SHAP applications as an explainable technique. Finally, not enough attention was paid to the reproducibility of the research work published. This review highlights opportunities for advancing research on explainable artificial intelligence models in the field of microbiome, supporting future applications of microbiome-based precision medicine.

Colorectal cancer (CRC) is a largely preventable disease influenced by modifiable behavioral risk factors such as diet, smoking, alcohol consumption, physical inactivity, and chronic stress. This study proposes a machine learning-based framework that generates personalized lifestyle recommendations aimed at CRC prevention. The system consists of two components: the Behavioral Recommendation Mapping Engine, which maps behavioral questionnaire responses to expertvalidated recommendations, and the Risk Assessment Module, which classifies participants into specific recommendations using supervised learning models. Eight domain-specific classifiers were developed, each targeting a key behavioral risk factor. Random Forests consistently outperformed Decision Trees, achieving high macro-averaged F1 scores even in imbalanced categories such as smoking$(F 1=0.88)$and stress$(F 1=0.80)$. The system also identifies the most influential behavioral variable per domain to highlight actionable risk factors. This framework will be integrated into the DIOPTRA mobile application to support realtime, personalized prevention.

Fear of falling is a major concern among older adults, often leading to reduced activity and increased fall risk. This study evaluated the impact of the HOLOBALANCE augmented-reality telerehabilitation system on fear of falling, measured using the Falls Efficacy Scale-International (FESI). Forty-nine older adults completed an 8-week intervention combining balance training, motion sensors, and virtual coaching. FES-I scores improved significantly post-intervention ($\mathbf{p}<0.00001$; Cohen's$d=-0.81$). Machine learning models using baseline and sensor-derived features predicted FES-I changes with high accuracy ($R^{2}=0.74$) and classified significant responders ($\Delta$FES-I$\geqslant 5.5$) with AUC$=\mathbf{0. 7 9}$. Findings support HOLOBALANCE's effectiveness and demonstrate the potential of AI-driven personalization in falls prevention programs. Clinical Relevance: Predicting meaningful change in fear of falling enhances clinical decision-making and enables targeted, personalized rehabilitation strategies.

Heart failure (HF) affects over 64 million people globally and poses complex diagnostic and therapeutic challenges. Reliable clinical research in HF hinges on high-quality data. This study presents a novel data quality assessment (DQA) framework tailored to retrospective HF datasets. It adapts the IEEE standard 2801-2022 criteria—originally for general medical data—to HF's clinical and multimodal structure and introduces a fairness-aware dimension to assess demographic representativeness. Applied to a real-world dataset of 6,039 patients and over 110,000 records across 11 clinical domains, the framework evaluates six dimensions: Completeness, Accuracy, Consistency, Compliance, Timeliness, and Fairness. Initial completeness was low$(48.82 \%)$, but improved to 61.04% after cleaning via outlier correction, imputation, and schema normalization. Accuracy and compliance reached 100%, and consistency improved to 99.61%. Fairness, measured via JensenShannon Similarity across age, sex, and BMI, remained at 87.35%, highlighting demographic imbalance remained unresolved by technical cleaning. This is the first standards-aligned, domain-adapted, and fairness-extended DQA pipeline for HF, producing a robust dataset suitable for machine learning and clinical decision support.

The evolution of information and communication technologies has affected all fields of science, including health sciences. However, the rate of technological innovation adoption by the healthcare sector has been historically slow, compared to other industrial sectors. Innovation in computer modeling and simulation approaches has changed the landscape in biomedical applications and biomedicine, paving the way for their potential contribution in reducing, refining, and partially replacing animal and human clinical trials. In Silico Clinical Trials (ISCT) allow the development of virtual populations used in the safety and efficacy testing of new drugs and medical devices. This White Paper presents the current framework for ISCT, the role of in silico medicine research communities, the different perspectives (research, scientific, clinical, regulatory, standardization, data quality, legal and ethical), the barriers, challenges, and opportunities for ISCT adoption. In addition, an overview of successful ISCT projects, market-available platforms, and FDA- approved paradigms, along with their vision, mission and outcomes are presented.

Cardiovascular disease (CVD) remains a leading global health burden, with carotid intima-media thickness (cIMT) recognized as a sensitive, non-invasive biomarker for early atherosclerosis and future cardiovascular risk. Although ultrasound imaging is the standard method for measuring cIMT, its accessibility may be limited in large-scale populations with intensive screening demands or in low-resource settings, posing a significant challenge for stroke survivors who have a high need for CVD assessment. While existing cIMT prediction models based solely on tabular data have been proposed to bypass the need for strong reliance on image-derived features, they typically frame the task as a binary classification problem, indicating only the presence or absence of vascular risk, thereby failing to effectively capture its actual severity. In contrast, this work proposes a prognostic learning model to effectively estimate cIMT, enabling precise quantification of atherosclerosis severity without relying on imaging data. By constructing a patient similarity graph relying on demographic and clinical-derived features to (i) bypass the need for revealing the actual clinical measurements, promoting privacy, and (ii) to explicitly account for patient's interdependencies, this work introduces a graph-guided self-supervised learning (Self-SL) framework to learn informative representations for the cIMT prediction task. These learned representations encode key local and global graph information that can readily assist the downstream task requiring only a minimal amount of labeled data. Applied to the UK Biobank cohort, the model outperforms conventional learning models, achieving up to 93.22% average MSE reduction, underscoring graph similarity strength in capturing latent clinical patterns.

Cardiac rehabilitation (CR) programs are vital for people recovering from cardiac surgeries or events. However, the effectiveness of CR programs varies and some patients may not adhere to them, which might result in less favourable outcomes. Machine Learning (ML) models could help predict the effectiveness and adherence of CR programs. This study proposes two such models: a) the CR program effectiveness prediction model and b) the CR program adherence prediction model. The models were trained on data from retrospective cohort study with 1448 participants collected at the Cardiac Rehabilitation Unit of the Hospital Clinico de Santiago de Compostela in Galicia, Spain (SERGAS). Data cleaning, normalization, imputation, statistical analysis, feature selection and repeated stratified k-fold cross-validation (CV) were applied on the ML pipeline, which tested and evaluated on baseline demographic, clinical, exercise tests and behavioral features. The performance of ML models was assessed by mean Area Under operating characteristic Curve (AUC), specificity, sensitivity, and balanced accuracy with 95% confidence interval (CI). The results show that Random Forest (RF) outperformed other evaluated classifiers for the CR program effectiveness model, with the highest AUC value of 0.789 (0.775, 0.802), while the best classifier for the CR adherence model was the Logistic Regression (LR) classifier, with an AUC value of 0.757 (0.749, 0.764). SHAP plots were also used to investigate the relationships among the variables used in the analysis. Finally, a two-dimensional scoring system was developed to jointly assess predicted adherence and effectiveness, enabling personalized visualization of patient response to CR.

This paper presents significant advancements in GPU-driven optimization for web-based volume rendering, which is specifically applied to peripheral artery disease (PAD) CT imaging. The proposed method enhances rendering efficiency and image quality, addressing the critical need for real-time, high-quality visualization of complex anatomical structures of PAD. Key improvements in the preprocessing pipeline, such as efficient chunking of large datasets, contribute to better GPU performance. The results demonstrate a substantial improvement over existing tools, with 95.37% reduction in render time, and 96.87% decrease in GPU memory usage compared with BlueLight, and significant memory optimization over Glance. These enhancements facilitate the detailed and interactive 3D visualization of vascular structures, which is crucial for accurate diagnosis and surgical planning. This paper highlights the potential of the proposed method to transform medical imaging practices, improving clinical outcomes for patients with PAD.

Atherosclerotic disease on peripheral arteries, commonly known as peripheral artery disease represents accumulation of cholesterol in peripheral arteries. It causes the formation of different types of depositions called plaques which cause thickening of the arterial walls resulting in reduced blood flow to lower extremities, in case of femoral arteries, upper extremities, in case of brachial artery or brain in case of carotid artery. Current research shows that approximately 8.5 million Americans, aged over 40 years, are affected by peripheral artery disease while one fourth of them falls into a severe category. For these reasons, an early detection of the disease is important. In order to detect the disease, arteries need to be imaged properly. In the recent years, an increase of optical coherence imaging has occurred due to the ease of use and the ability to detect tissue morphology which is extremely important for the detection of the disease. From the tissue morphology, it is of most importance to observe the tissue between lumen and intimal layer of the artery, since the majority of the plaques form in that region, but it is also important to observe the region between intima and adventitia (the outer wall of the artery) since the plaque can penetrate the intimal layer as well. In this paper, a deterministic approach for the detection of the adventitia is described based on the previously detected intimal layer of the artery. The proposed method is evaluated on optical coherence tomography images from 8 specimens of porcine femoral arteries. The results show that the detection of adventitia is possible on this image modality with Dice coefficient 0.9805 and Hausdorff distance 0.1 mm.

This study focuses on the development of artificial intelligence models to enhance telerehabilitation practices. We utilized diverse datasets to create clinically relevant models for predicting two critical outcomes: fall risk and treatment effectiveness. By applying various machine learning techniques, including K-Nearest Neighbors, Random Forest, Decision Tree, Support Vector Machine, and XGBoost, our models demonstrated high accuracy, sensitivity, and specificity. Notably, the Random Forest model achieved an accuracy of 0.97 in predicting fall risk and 0.96 in assessing treatment effectiveness. These models equip clinicians with powerful tools for data-driven decision-making, ultimately improving patient outcomes in rehabilitation settings.

Heart failure (HF) is a complex syndrome that is affected by many factors and causes. It is crucial to early recognize the disease subtypes and the unidentified clinical pathways that give rise to it. Machine learning (ML) is the tool that assist to deal with these challenges and improve the prediction of HF. In this work, the HF risk prediction was implemented by employed ML classifiers, such as Random Forest (RF), Extreme Grading Boosting (XGBoost) and Light Gradient-Boosting Machine (LGBM). We utilized the data from the German epidemiological trial on ankle brachial index - getABI cohort, which includes 6,454 patients. The performance of classifiers was estimated by Accuracy (ACC), Sensitivity, Specificity and the area under the receiver operating characteristic curve (AUC) in mean values for each ML classifier. The results were also interpreted using the Explainable artificial intelligence (XAI) approach, the Shapley Additive exPlanations (SHAP) values. Our work reveals that LGBM classifier predict the HF risk within 5 years follow-up in general population with 68 % accuracy. Moreover, the N-terminal pro-B-type natriuretic peptide (NT-proBNP) was identified as the most important feature for HF risk prediction.

Recent research indicates a worrisome surge in the prevalence of Peripheral Artery Disease (PAD). This alarming rise underscores the pressing need for new approaches to PAD treatment. Consequently, this paper introduces the DECODE platform, a cloud-based solution aimed at revolutionizing the treatment of PAD using Drug-Coated Balloons (DCBs). DECODE's main contribution lies in its integration of cutting-edge technologies, including 3D-enabled visualization, augmented and virtual reality, investigation of drug release mechanisms, in-vitro and in-silico simulations, computational modeling, multiscale analysis, and data analysis, into a cohesive system. This integration facilitates collaboration among researchers, clinicians, and medical professionals and provides a holistic approach to PAD treatment, encompassing visualization, simulation, optimization, and outcome analysis. DECODE's impressive performance metrics, assessed by Google's Lighthouse tool, further emphasize its efficiency: a performance score of 91%, accessibility at 90%, adherence to best practices at 83%, SEO-friendliness with a score of 100%, and optimization as a progressive web app. These metrics highlight its strengths as a comprehensive and effective solution for PAD treatment.

Cardiovascular disease is one of the leading causes of death worldwide resulting an estimated of 523 million people with cardiovascular disease in 2020 while 19 million deaths were attributed to it. It is a group of diseases including coronary artery disease, stroke, congestive heart failure, peripheral artery disease and other similar conditions that impact heart and blood vessels. Coronary artery disease represents accumulation of cholesterol in the inner wall of the artery and thus forming of different types of plaques, which cause thickening of the arterial walls which makes it difficult for the blood to flow to the organs and, eventually, the artery can get blocked. For these reasons, it is extremely important to detect the disease as soon as possible. In this paper we provide lumen and adventitia segmentation as an important pre-step for plaque characterization and full 3D reconstruction and of coronary artery vessels. We evaluated our methods on manually annotated OCT images from 10 patients in terms of F1-score and overall quality of the reproduced masks. Experimental results show that modified U-Net provides us with the best results for lumen segmentation with F1-score 0.9819, while modified SegNet and PSPNet networks provide us with the best results for adventitia segmentation with F1-scores 0.9458 and 0.9406, respectively. Results also show that modified networks outperform original architectures.

The application of clustering techniques to glucose time series data has the potential to enhance early detection and effective management of diabetes and other metabolic disorders. This, in turn, can contribute to improved clinical outcomes and patient-reported outcomes. In this study, we aim to address the issue of personalized clustering of glucose time series data, specifically those recorded during the nocturnal sleep period, via Self Organized Maps. The clustering model was constructed using a dataset comprising 22 patients diagnosed with type 1 diabetes who were closely monitored for a maximum duration of 4 weeks as part of the GlucoseML study. Based on the silhouette coefficient score, two distinct clusters have been identified, indicating the presence of two separate glucose distributions observed during nocturnal sleep. Within Cluster 1, it has been observed that 90% of glucose values fall within the desired euglycemic range of 70-180 mg/dL. Consequently, there is a corresponding increase in the likelihood of hypoglycemia, with a rate of 2.4% occurring below the threshold of 70 mg/dL. Within Cluster 2, patients show a mainly hyperglycemic profile, characterized by 64.4% of values exceeding 180 mg/dL, while no instances of hypoglycemia were observed.

Fatal myocardial infarction (MI) is one of the most common types of cardiovascular diseases that often presents in the emergency department. The prediction of death caused by myocardial infarction within 10-years follow-up is addressed in this study, using comorbidities, daily habits, clinical and laboratory data in binary and continuous data respectively. The used data are included in a cohort of the Ludwigshafen Risk and Cardiovascular Health (LURIC) study. The target feature, namely death caused by MI, contained 106 deceased patients and 2,321 alive patients in the final used dataset. The analysis was based on machine learning models (ML), such as support vector machine (SVM), light gradient-boosting machine (LGBM), Random Forest (RF), Decision Tree (DT). Their performance was estimated by Area Under Receiver Operating Characteristic Curve (AUC), Sensitivity, Specificity, Precision and Accuracy. Results show that LGBM was the most suitable of the aforementioned models to predict death caused by myocardial infarction within 10-years follow-up, achieving area under the curve (AUC) value equal to 77.03 %, accuracy 69.42 %, sensitivity 69.75 %, specificity 69.40% and precision 53.76 %. In addition, explainable artificial intelligence (xAI) was utilized and especially SHapley Additive exPlanations (SHAP) was the selected method. SHAP was utilized in order to shed light on the results, applying the LGBM model as the best predictive model. The provided SHAP plots contribute to the interpretation of how each independent feature aid to the final prediction.

The identification of the location of prostate cancer is of paramount importance for improved treatment. This process is strictly bonded with the accurate segmentation of the prostate gland and its zones, on MR images. In the present study, an ensemble of 3 deep learning models along with a Meta-learner module able to refine the outcomes of the models, is proposed (Transi-Net) to segment the prostate's transition zone. A method to quantify the model's uncertainty is introduced to measure the confidence of an architecture with respect to its final decision. The backbone of Transi-Net consist the original U-net, Dense2U-net and Bridged U-net models. The proposed model showcased significant improvement in comparison with its base components as well as an independent model, the USE-Net, while it was proven more confident about its decision. The proposed model resulted in an improvement of 5%, 3%, 3% and 4% for Sensitivity, Balanced Accuracy, Dice Score and Rand Error Index respectively, compared to the second best, USE-Net.

Cardiovascular disease (CVD) poses a significant global health challenge, and accurate inference methods are vital for early detection and intervention. However, the quality of prediction relies heavily on the availability of labeled data, which are often limited in medical applications. To cope with the challenge of limited labeled data, we are the first to propose an active learning (AL) approach that leverages a weighted ensemble of Gaussian processes to effectively infer CVD by strategically selecting the few most informative data points to label. Through experiments conducted on the SMARTool dataset, we demonstrate the effectiveness of the advocated approach, achieving superior performance in CVD inference compared to baseline methods. Our findings highlight the potential impact of the proposed AL framework in CVD diagnosis and treatment clinical cases, particularly in scenarios where labeled data are scarce, due to data confidentiality concerns or high sampling costs.

Breast cancer (BC) is the most common cancer in women in Europe and worldwide, with a high prevalence in middle-aged and older women. The last years, the evolution in the existing treatment approaches have contributed to improved clinical outcomes and survival rates. Nevertheless, BC therapy-related cardiotoxicity, poses a severe impact in the short- and long-term Quality of Life (QoL) and associated survival of the BC patients. This study demonstrates how the CARDIOCARE platform and the developed risk stratification models provides healthcare professionals with a valuable tool for effectively managing BC patients, preventing treatment induced cardiotoxicity and improving their QoL. This is accomplished through the integration of multi-source patient-specific data from patient-oriented mobile applications and wearable sensors, and by the employment of beyond the state-of-the-art data mining and machine learning approaches.

This study presents an automated sleep stage detection methodology using a reduced number of signals, as input from polysomnography (PSG) recordings. The aim is to establish a competitive sleep stage detection performance based on AI models for respiration and heart rate signal analytics, as these signals can be effectively collected by wearable and wireless monitoring solutions in home and clinical environment. A wide range of time, frequency and time-frequency domain features were first extracted in 30-sec long signal segments, along with heart and respiration rate variability analytics. The most optimal subset of features per evaluation run was assessed and selected using mutual information and each segment was then classified as either Wake, N1+N2, N3 or REM class, using a Gradient Boosted Decision Tree classifier. The proposed methodology was evaluated with data from two different databases, containing both healthy subjects and patients with apnea-related disorders, achieving an average classification accuracy of 84.62% and 85.18%, respectively, in the challenging 4-class task of wake-light-deep-REM sleep stage detection, outperforming previous results. Reducing the model’s input to only respiration and heart rate data, the proposed methodology paves the way to the use of wireless and contactless systems, enabling prolonged and unobtrusive monitoring of patients with various sleep disorders with high sleep stage detection accuracy.

The Timed Up and Go (TUG) test is a well-established, standardized test used to assess various aspects of a patient's mobility. Although its reliability is proven, instru-mentation is necessary for acquiring accurate information. This work evaluated the instrumentation of the TUG test using devices based on inertial measurement unit (IMU) and UWB radar sen-sors, and subsequently assessed test-related motion parameters, extracted from their data. To that end, five healthy individuals participated in three sessions of a TUG test, performed in slow, normal and fast speeds, while an IMU-based wearable device, the PDMonitor®, and an ultra-wideband (UWB) radar, the Aria Sensing® LT102, monitored their motion. The sessions were also timed, recorded on video, and annotated as a post-processing step. Results showed that both approaches performed very well in estimating walking duration$({R}^{2}=0.9{6}$for IMU and$R^{2}=0.98$for UWB) and turning duration$(R^{2}=0.74$for IMU and$R^{2}=0.66$for UWB). Moreover, for the IMU sensors, the test duration had excellent correlation with annotations$(R^{2}=0.98)$and results showed that gait kinematic features could be used as predictors$(AUC=0.9955)$of detecting a high TUG score$(T^{\mathbf{TUG}}- > 13.5\mathrm{s})$, identifying increased fall risk. On the other hand, gait speed estimated using UWB data had excellent correlation (R2= 0.95) with speed calculated using annotations. The different characteristics of the two approaches, and their good performance in the TUG test's segmentation and assessment of gait parameters, indicate that they could be fused to augment the resulting information.

We have been faced with an unprecedented challenge in combating the COVID-19/SARS-CoV2 outbreak that is threatening the fabric of our civilization, causing catastrophic human losses and a tremendous economic burden globally. During this difficult time, there has been an urgent need for biomedical engineers, clinicians, and healthcare industry leaders to work together to develop novel diagnostics and treatments to fight the pandemic including the development of portable, rapidly deployable, and affordable diagnostic testing kits, personal protective equipment, mechanical ventilators, vaccines, and data analysis and modeling tools. In this position paper, we address the urgent need to bring these inventions into clinical practices. This paper highlights and summarizes the discussions and new technologies in COVID-19 healthcare, screening, tracing, and treatment-related presentations made at the IEEE EMBS Public Forum on COVID-19. The paper also provides recent studies, statistics and data and new perspectives on ongoing and future challenges pertaining to the COVID-19 pandemic.

The aim of this work is to present two different algorithmic pipelines for human activity recognition (HAR) in real time, exploiting inertial measurement unit (IMU) sensors. Various learning classifiers have been developed and tested across different datasets. The experimental results provide a comparative performance analysis based on accuracy and latency during fine-tuning, training and prediction. The overall accuracy of the proposed pipeline reaches 66 % in the publicly available dataset and 90% in the in-house one.

The paper describes experiences from building and cloudification of the in-silico research platform SilicoFCM, an innovative in-silico clinical trials' solution for the design and functional optimization of whole heart performance and monitoring effectiveness of pharmacological treatment, with the aim to reduce the animal studies and the human clinical trials. The primary aim of cloudification was to prove portability, improve scalability and reduce long-term infrastructure costs. The most computationally expensive part of the platform, the scientific workflow manager, was successfully ported to Amazon Web Services. We benchmarked the performance on three distinct research workflows, each of them having different resource requirements and execution time. The first benchmark was pure performance of running workflow sequentially. The aim of the second test was to stress-test the underlying infrastructure by submitting multiple workflows simultaneously. The benchmark results are promising, painting the infrastructure launching overhead almost negligible in this kind of heavy computational use-case.

It is generally accepted that a healthy diet plays an important role in modern lifestyle and can prevent or reduce the effects of important diseases, such as obesity, diabetes or cardiovascular diseases. Technological advancement and the wide spread of smartphones enable the monitoring and recording of nutritional habits on a daily basis, through mHealth solutions. The most difficult task of mHealth dietary systems for calculating the nutritional composition of food is to estimate its volume. In this study, we present a volume estimation system based on structure from motion smartphone camera, through two-view 3D food reconstruction. The proposed methodology uses stereo vision techniques and requires the input of two food images with a reference card next to the plate, to reconstruct the 3D structure of the food and to estimate its volume. The above approach achieves a mean absolute percentage error from 4.6 - 11.1% per food dish. The systematic collection of a labelled Mediterranean Greek Food images dataset, the MedGRFood, with known food weight allows the evaluation of the proposed methodology.

Cognitive workload is a critical feature in related psychology, ergonomics, and human factors for understanding performance. However, it still is difficult to describe and thus, to measure it. Since there is no single sensor that can give a full understanding of workload, extended research has been conducted in order to present robust biomarkers. During the last years, machine learning techniques have been used to predict cognitive workload based on various features. Gaze extracted features, such as pupil size, blink activity and saccadic measures, have been used as predictors. The aim of this study is to use gaze extracted features as the only predictors of cognitive workload. Two factors were investigated: time pressure and multi tasking. The findings of this study showed that eye and gaze features are useful indicators of cognitive workload levels, reaching up to 88% accuracy.

In the last years, many studies have been investigating emotional arousal and valence. Most of them have focused on the use of physiological signals such as EEG or EMG, cardiovascular measures or skin conductance. However, eye related features have proven to be very helpful and easy to use metrics, especially pupil size and blink activity. The aim of this study is to predict emotional arousal and valence levels which are induced during emotionally charged situations from eye related features. For this reason, we performed an experimental study where the participants watched emotion-eliciting videos and self-assessed their emotions, while their eye movements were being recorded. In this work, several classifiers such as KNN, SVM, Naive Bayes, Trees and Ensemble methods were trained and tested. Finally, emotional arousal and valence levels were predicted with 85 and 91% efficiency, respectively.

Automatic segmentation of the prostate peripheral zone on Magnetic Resonance Images (MRI) is a necessary but challenging step for accurate prostate cancer diagnosis. Deep learning (DL) based methods, such as U-Net, have recently been developed to segment the prostate and its' sub-regions. Nevertheless, the presence of class imbalance in the image labels, where the background pixels dominate over the region to be segmented, may severely hamper the segmentation performance. In the present work, we propose a DL-based preprocessing pipeline for segmenting the peripheral zone of the prostate by cropping unnecessary information without making a priori assumptions regarding the location of the region of interest. The effect of DL-cropping for improving the segmentation performance was compared to the standard center-cropping using three state-of-the-art DL networks, namely U-net, Bridged U-net and Dense U-net. The proposed method achieved an improvement of 24%, 12% and 15% for the U-net, Bridged U-net and Dense U-net, respectively, in terms of Dice score.

This paper presents a clustering-based method for the detection of Multiple Sclerosis (MS) lesions, by including anatomical information, brain geometry and lesion features, while volume quantification is performed. The proposed method utilizes Fluid Attenuated Inversion Recovery (FLAIR) images for the delineation of the plaques and brain atrophy estimation. The methodology includes five steps: (i) image preprocessing, (ii) image segmentation utilizing the K-means clustering algorithm, (iii) post processing for elimination of false positives, (iv) delineation and visualization of the MS lesions, and (v) brain atrophy estimation. It is implemented in two different datasets; (a) a dataset of 3D FLAIR MR Images, acquired in 30 MS patients, and (b) a dataset of 15 FLAIR MR Images, provided by the MICCAI Challenge 2016. A sensitivity 73.80%, and 71.52% was achieved for the two datasets, respectively. Brain atrophy was determined only on the first dataset, since follow up scans are available.

Because of the rapid and serious nature of acute cardiovascular disease (CVD) especially ST segment elevation myocardial infarction (STEMI), a leading cause of death worldwide, prompt diagnosis and treatment is of crucial importance to reduce both mortality and morbidity. During a pandemic such as coronavirus disease-2019 (COVID-19), it is critical to balance cardiovascular emergencies with infectious risk. In this work, we recommend using wearable device based mobile health (mHealth) as an early screening and real-time monitoring tool to address this balance and facilitate remote monitoring to tackle this unprecedented challenge. This recommendation may help to improve the efficiency and effectiveness of acute CVD patient management while reducing infection risk.

Balance training has been shown to be effective in reducing risks of falling, which is a major concern for older adults. Usually, exercise programs are individually prescribed and monitored by physiotherapeutic or medical experts. Unfortunately, supervision and motivation of older adults during home-based exercises cannot be provided on a large scale, in particular, considering an ageing population. Augmented reality (AR) in combination with virtual coaches could provide a reasonable solution to this challenge.

T e-Coaches are promising intelligent systems that aims at supporting human everyday life, dispatching advices through different interfaces, such as apps, conversational interfaces and augmented reality interfaces. This workshop aims at exploring how e-coaches might benefit from spatially and time-multiplexed interfaces and from different communication modalities (e.g., text, visual, audio, etc.) according to the context of the interaction.

Coronary artery disease (CAD) is one of the leading causes of mortality worldwide. Drug-eluting stents (DES) are nowadays widely used so as to treat the occluded arteries, restore blood flow and through the diffusion of the drug achieve better clinical outcomes compared to Bare Metal Stents (BMSs), in terms of reduced numbers of cardiac death, myocardial infarction and vessel revascularization. BioCoStent targets the design and development of an innovative DES with retinoic acid. In this study the overall concept for realizing this new DES development, including the characterization of the biomaterials, the performance of in vivo and in vitro studies and the optimisation through in silico modelling, is presented.

The daily care of type 1 diabetes has been considerably improved through the increased adoption of continuous glucose monitoring, continuous subcutaneous insulin infusion, and precise behavioral monitoring (diet, physical activity) mHealth solutions. In this study, we present the food recognition and nutrient estimation components of the GlucoseML system; a type 1 diabetes self-management system relying on short-term predictive analytics of the glucose trajectory. A computer-vision-based approach is outlined combining image processing and machine learning to plate detection, food segmentation, food recognition and volume estimation of a plate's content. The systematic collection of an annotated Greek food images dataset allows the evaluation of the proposed methodology.

In this work, we present a novel and accurate methodology for the segmentation of optical coherence tomography imaging (OCT) and detection of lumen and outer wall, plaque characterization and stent struts in stented arteries. In particular, the methodology starts with pre-processing and detection of the catheter artefact. Struts detection is based on the identification of the size of the shadow behind the struts. Our methodology can be applied to metal stents as well as to polymeric and bioresorbable vascular scaffold (BVS) stents. Lumen segmentation is based on Fuzzy clustering and Fast marching on the gradient image to find the shortest path. The outer wall is segmented using a methodology, which combines K-means and 3-dimensional (3D) surface fitting on the detected edges. K-means with 3 clusters is performed at the final step on the ROI between the lumen and outer border of adventitia to characterize the plaque type. The validation is achieved by comparing the algorithm's results with manual annotations provided by experts. The results demonstrate that our methodology is accurate in lumen (R=0.99) and outer wall segmentation (R=0.77) and struts detection (R=0.82). The average Hausdorff distance and the Dice Similarity for lumen segmentation is 0.097 mm and 0.96, respectively.

Coping with breast cancer and its consequences has now become a major socioeconomic challenge. The BOUNCE EU H2020 project aims at building a quantitative mathematical model of factors associated with optimal adjustment capacity to cancer. This paper gives an overview of the project targets and on the algorithmic methods focusing on modeling the psychological resilience trajectories during breast cancer treatment.

The scope of this paper is to present the novel risk stratification framework for carotid artery disease which is under development in the TAXINOMISIS study. The study is implementing a multimodal strategy, integrating big data and advanced modeling approaches, in order to improve the stratification and management of patients with carotid artery disease, who are at risk for manifesting cerebrovascular events such as stroke. Advanced image processing tools for 3D reconstruction of the carotid artery bifurcation together with hybrid computational models of plaque growth, based on fluid dynamics and agent based modeling, are under development. Model predictions on plaque growth, rupture or erosion combined with big data from unique longitudinal cohorts and biobanks, including multi-omics, will be utilized as inputs to machine learning and data mining algorithms in order to develop a new risk stratification platform able to identify patients at high risk for cerebrovascular events, in a precise and personalized manner. Successful completion of the TAXINOMISIS platform will lead to advances beyond the state of the art in risk stratification of carotid artery disease and rationally reduce unnecessary operations, refine medical treatment and open new directions for therapeutic interventions, with high socioeconomic impact.

The revolution in modelling and simulation methodologies accompanied with the recent events in the high-performance computing (HPC) helped the development of in silico clinical platforms which integrate advanced and individualized simulation models to support drug development. These platforms incorporate patient specific models to create and generate virtual patients (VPs). A parametric methodology for resampling and generating VPs is the multivariate normal distribution which in the current work is optimized through an iterative pipeline by the Kolmogorov-Smirnov goodness-of-fit test. The proposed VP generator is integrated in the multi-repository VP model of SILICOFCM which is a multi-modular, innovative in silico clinical trials solution for the design and functional optimization of the whole heart performance and monitoring effectiveness of pharmacological treatment for familial cardiomyopathies, with aim to reduce the animal studies and the human clinical trials.

Atherosclerosis is the one of the major causes of mortality worldwide, urging the need for its treatment. This study is aiming to investigate the role of diabetes in the atherosclerotic plaque growth mechanisms through the utilization of a multi-level numerical model. To accomplish this, we developed a proof-of-concept mathematical model of the diabetes effect to plaque growth, that has been coupled to a stateof-the-art multi-level numerical model of plaque growth. Diabetes main effect is the increase of the average blood glucose concentration, which causes the decrease of the endothelial nitric oxide production rate by affecting several biologic pathways. Nitric oxide is a signaling molecule that regulates the endothelial flow rates, and any abnormal alteration leads to endothelial dysfunction, the major culprit of atherosclerosis. The derived model considers the modeling of blood flow in lumen and of species transport and reactions in the arterial wall. The considered factors include: (i) LDL, (ii) HDL, (iii) oxidized LDL, (iv) monocytes, (v) macrophages, (vi) cytokines, (vii) smooth muscle cells (contractile & synthetic), and (viii) collagen. The model is validated using 10 patients' reconstructed arterial data in two time-points. More specifically, baseline geometries are used as an input to our model, while follow-up geometries are used as benchmark for our model's output. The results presented a high coefficient of determination between the simulated with diabetes effect and the real follow-up geometries of 0.634.

The aim of this work is to present the architecture of the ProMiSi tool, a software for the analysis of magnetic resonance imaging and the extraction of information on the progression of multiple sclerosis disease. ProMiSi is based on the automatic processing, segmentation and post-processing of MRI for the automatic labeling, visualization and volumetric quantification of segmentable brain structures from magnetic resonance image. The combination of the above mentioned volumetric results with other type of information (e.g. clinical, demographic etc.), through autonomous learning intelligent techniques, allows the evaluation of the severity and the progress prediction of the multiple sclerosis and consequently the personalized management of the disease. A proof of concept study with 30 patients will take place for the validation of the algorithms, while ProMiSi will be evaluated in terms of functionality, usability, reliability, performance and supportability.

We present a short-term observational study of the fluctuation of glycemic variability with or without the presence of physical exercise based on the ambulatory glucose profile recommendations and measures using an mHealth platform for patient monitoring and data collection. The correlation of physical exercise to diabetes type 1 is presented using the Pearson's and Spearman's correlation coefficients. The multi-parametric dataset comes from the continuous monitoring of seven type 1 diabetic individuals under free living conditions for 14 consecutive days. The results enable the clinician to develop individualized treatment plans for each patient and they can potentially be used in prediction models.

Atherosclerosis is characterized by dysfunction of endothelium, vasculitis and accumulation of lipid, cholesterol and cell elements inside blood vessel wall. Determination of plaque location and plaque volume for a specific patient is very important for prediction of atherosclerotic disease progression. In this study coupled computer modeling of atherosclerosis progression is analysed. Continuum approach assumed mass transport of LDL through the wall and the simplified inflammatory process coupled with three additional reaction-diffusion equations and lesion growth model in the intima. Discrete modeling used dissipative particle dynamics method which individual blood constituents (e.g., platelets, RBCs, white blood cells) treated as particle interaction. Coupled continuum and discrete model was investigated with real patient baseline and follow up study for right and left coronary arteries.

Coronary stents are expandable scaffolds that are used to widen occluded diseased arteries and restore blood flow. Because of the strain they are exposed to and forces they must resist as well as the importance of surface interactions, material properties are dominant. Indeed, a common differentiating factors amongst commercially available stents is their material. Several performance requirements relate to stent materials including radial strength for adequate arterial support post-deployment. This study investigated the effect of the stent material in three finite element models using different stents made of: (i) Cobalt-Chromium (CoCr), (ii) Stainless Steel (SS316L), and (iii) Platinum Chromium (PtCr). Deployment was investigated in a patient specific arterial geometry, created based on a fusion of angiographic data and intravascular ultrasound images. In silico results show that: (i) the maximum von Mises stress occurs for the CoCr, however the curved areas of the stent links present higher stresses compared to the straight stent segments for all stents, (ii) more areas of high inner arterial stress exist in the case of the CoCr stent deployment, (iii) there is no significant difference in the percentage of arterial stress volume distribution among all models.

The aim of this work is to present a machine learning based method for the prediction of adverse events (mortality and relapses) in patients with heart failure (HF) by exploiting, for the first time, measurements of breath and saliva biomarkers (Tumor Necrosis Factor Alpha, Cortisol and Acetone). Data from 27 patients are used in the study and the prediction of adverse events is achieved with high accuracy (77%) using the Rotation Forest algorithm. As in the near future, biomarkers can be measured at home, together with other physiological data, the accurate prediction of adverse events on the basis of home based measurements can revolutionize HF management.

The aim of this work is to estimate the medication adherence of patients with heart failure through the application of a data mining approach on a dataset including information from saliva and breath biomarkers. The method consists of two stages. In the first stage, a model for the estimation of adherence risk of a patient, exploiting anamnestic and instrumental data, is applied. In the second stage, the output of the model, accompanied with data from saliva and breath biomarkers, is given as input to a classification model for determining if the patient is adherent, in terms of medication. The method is evaluated on a dataset of 29 patients and the achieved accuracy is 96%.

The discrimination of the preictal state in EEG signals is of great importance in neuroscience and the epileptic seizure prediction field has yet to provide conclusive evidence. In this study, three different classification approaches, including the Repeated Incremental Pruning to Produce Error Reduction (RIPPER) algorithm, Support Vector Machines (SVMs) and Neural Networks (NNs), are investigated for their ability to discriminate preictal from interictal EEG segments. Using public EEG data, a wide range of features is extracted from each segment and then applied to the classifiers. The analysis covers a patient-specific approach, so as to optimize the decision to each patient individually and a patient-independent approach in order to explore a global prediction approach that can discriminate randomly selected preictal and interictal segments from all patients. Overall, the first approach aims at revealing patient-specific epileptic characteristics, whereas the second seeks for potential general preictal-related signs. The results reveal that in the patient-specific case, the SVM classifier exhibits the highest classification accuracy in both preictal and interictal classes reaching 85.75% sensitivity and specificity. As it is expected, the classification performance is lower for the patient-independent case at 68.5%, due to the complicated nature of preictal activity and the variations among patients condition.

Coronary Computed Tomography Angiography (CCTA) has gained substantial ground in everyday clinical practice due to its non-invasive nature. In this work we present a noninvasive method to assess the hemodynamic significance of coronary stenoses using only CCTA images. Two female patients were subjected to Invasive Coronary Angiography, Virtual Histology IVUS and CCTA. The same arterial segment was reconstructed in 3D using the proposed method as well as two already validated 3D reconstruction methods using the aforementioned invasive techniques. The lumen diameter reduction (%) and the minimum lumen diameter (mm) were calculated for all cases and a relative error <;5% was observed between all three techniques.

Presents the introductory editorial for this issue of the publication.

Oral squamous cell carcinoma has been characterized as a complex disease which involves dynamic genomic changes at the molecular level. These changes indicate the worth to explore the interactions of the molecules and especially of differentially expressed genes that contribute to cancer progression. Moreover, based on this knowledge the identification of differentially expressed genes and related molecular pathways is of great importance. In the present study, we exploit differentially expressed genes in order to further perform pathway enrichment analysis. According to our results we found significant pathways in which the disease associated genes have been identified as strongly enriched. Furthermore, based on the results of the pathway enrichment analysis we propose a methodology for predicting oral cancer recurrence using dynamic Bayesian networks. The methodology takes into consideration time series gene expression data in order to predict a disease recurrence. Subsequently, we are able to conjecture about the causal interactions between genes in consecutive time intervals. Concerning the performance of the predictive models, the overall accuracy of the algorithm is 81.8% and the area under the ROC curve 89.2% regarding the knowledge from the overrepresented pre-NOTCH Expression and processing pathway.

The papers in this special section were presented at three well-known conferences organized in 2014: EAI Mobihealth, IEEE HealthCom, and IEEE Biomedical and Health Informatics. EAI Mobihealth is an annually organized conference, which started in 2010, to address the demands of the rapidly evolving disciplines of wireless communications, mobile computing, and sensing technologies in healthcare. The IEEE-Healthcom is held every year since 1999 in different countries in Asia, Europe, and in America. It aims at bringing together interested parties working in the field of healthcare to exchange ideas, discuss innovative and emerging solutions, and develop collaborations. The IEEE Biomedical Health Informatics Conference started in 2013 and is organized every year providing the forum to showcase enabling technologies of computing, devices, imaging, sensors, and systems that optimize the acquisition, transmission, processing, storage, retrieval, visualization, and analysis of medical data. The aim of this special section is to present an overview of recent advances in sensing technologies, monitoring of patients, security and privacy of data transfer, provision of collaborative environments, data gathering and analysis from various sources, and predictive models, which all finally target the best strategy for patient monitoring and treatment.

In this work we present the decision support of the EMBalance platform. EMBalance is a platform for the management of balance disorders in terms of diagnosis, treatment and evolution. The EMBalance platform aims to extend existing but generic and currently uncoupled balance modelling activities leading to a multi-scale and patient-specific balance model, which will be incorporated in a Decision Support System (DSS), towards the early diagnosis, prediction and the efficient treatment planning of balance disorders. The diagnosis part of the decision support system uses various data ranging from demographic characteristics to clinical examinations, auditory and vestibular tests. Currently we present some initial technical choices and indicative results of the decision support system for diagnosing balance disorders, based on data mining techniques and clinical guidelines.

Although micro-anastomosis is the most commonly performed procedure for reconnecting two blood vessels through sutures, thrombus formation and subsequently anastomotic failure remains one of the most serious clinical complications. An important stimulus to thrombus formation is the altered hemodynamics with abnormal Wall Shear Stress (WSS) distribution on endothelial cells generated by the presence of sutures. Computational simulation is a valid tool to examine the local hemodynamics of micro-anastomosed vessels, allowing for the calculation of the WSS, a factor that could otherwise not directly possible to be measured in vivo. The aim of this study is to perform Fluid-Structure Interaction (FSI) analysis of micro-anastomosis in order to examine the effects of the wall compliance on the hemodynamic quantities.

Heart Failure (HF) is a rapidly increasing cardiovascular chronic disease that affects millions of people globally. Lack of proper management of HF patients increases the risk of frailty and other undesirable effects and contributes to loss of independence. The engagement of the HF patient and all actors related to his/her disease management is critical for empowering the patients in achieving sustainable behaviour change, regarding their adherence and compliance. To address this, the concept and the architecture of a mobile co-operative platform are described. The design and development is based on a multi-stakeholder patient centered mHealth ecosystem for HF patients that will facilitate the collaboration of multidisciplinary actors.

The importance of the development of the Primary Care network in a developed country is indisputable high. The increasing pressure for productivity improvement and reduction of costs, requires activities focusing on the control and optimization of care processes improving their efficiency and effectivity. A keystone in such priority is the utilization of several effective and comprehensive processes in the everyday practice. The aim of this study is the development of a framework for the improvement of the Health Care processes introducing Business Process Modeling Notations (BPMNs) methodologies. The large majority of processes in the organizations and healthcare centers which belong to the Greek Primary Care Healthcare system have been collected. For each process the BPMNs diagram has been developed and presented. The analysis and the quantitative indexes have been captured by the integration of the processes in a web application that has been designed and implemented. The application's outcome has been analyzed partially since it will be tested in a Health Care Center in Kissamos, Crete, Greece.

Atherosclerosis is a medical condition becoming the number one cause of death worldwide. For this reason, any developement that may help physicians in early diagnostic and selection of the most appropriate treatment strategy is of great importance. In this paper we describe three-dimensional computer model of plaque formation and development for human coronary artery. In order to validate proposed model we used ten specific patients from CT study belonging to one of the following groups: (1) de-novo group - patients with new formed plaques, (2) old-lesions group - patients with plaques with progression and (3) control group - patients with plaques without progression. Plaque volume progression is fitted by using two time points for baseline and follow up. Results obtained within this study indicate high potential of this model to be used in clinical practice, thus assisting physicians by providing them valuable information about future disease progression.

The aim of this study is to investigate the effect of mallear and incudal ligaments to the tympanic membrane and the stapes footplate displacement in a finite element model of the middle ear. Three cases were simulated: one without the ligaments, one including the posterior incudal and the anterior mallear ligaments and one including in addition the superior mallear and incudal ligaments. A maximum stapes footplate displacement 0.023 μm was observed at a frequency 1024 Hz by exciting the tympanic membrane at a sinusoidal sound pressure level (SPL) of 90 dB. The computational results were validated with experimental measurements from the literature. Concluding our results show that the superior ligaments are most beneficial for an accurate representation of the middle ear frequency response. Excellent agreement is observed between our results and human temporal bone experimental data and other finite element studies.

An unsupervised methodology for the detection of Epileptic seizures in EEG recordings is proposed. The time-frequency content of the EEG signals is extracted using the Short Time Fourier Transform. The analysis focuses on the EEG energy distribution among the well-established delta, theta and alpha rhythms (2-13 Hz), as energy variations in these frequency bands are widely associated with seizure activity. Relying on seizure rhythmicity, the classification is performed by isolating the segments where each rhythm is more clearly and dominantly expressed over the others. For the first time, an unsupervised methodology is evaluated using more than 978 hours of EEG recordings from a public database. The results show that the proposed methodology achieves high seizure detection sensitivity with significantly reduced human intervention.

The aim of this special section is to provide an overview of the emerging biomedical informatics technologies and their application in research and clinical environments. Recent developments in biomedical informatics have created methods, techniques and tools, which are based on the analysis of heterogeneous data, data mining, decision support systems, multiscale modeling, etc. The distance from the development of such systems and the real clinical environments is still long enough, and only some of them have been used in a clinical scale.

Progression of atherosclerotic process constitutes a serious and quite common condition due to accumulation of fatty materials in the arterial wall, consequently posing serious cardiovascular complications. In this paper, we assemble and analyze a multitude of heterogeneous data in order to model the progression of atherosclerosis (ATS) in coronary vessels. The patient's medical record, biochemical analytes, monocyte information, adhesion molecules, and therapy-related data comprise the input for the subsequent analysis. As indicator of coronary lesion progression, two consecutive coronary computed tomography angiographies have been evaluated in the same patient. To this end, a set of 39 patients is studied using a twofold approach, namely, baseline analysis and temporal analysis. The former approach employs baseline information in order to predict the future state of the patient (in terms of progression of ATS). The latter is based on an approach encompassing dynamic Bayesian networks whereby snapshots of the patient's status over the follow-up are analyzed in order to model the evolvement of ATS, taking into account the temporal dimension of the disease. The quantitative assessment of our work has resulted in 93.3% accuracy for the case of baseline analysis, and 83% overall accuracy for the temporal analysis, in terms of modeling and predicting the evolvement of ATS. It should be noted that the application of the SMOTE algorithm for handling class imbalance and the subsequent evaluation procedure might have introduced an overestimation of the performance metrics, due to the employment of synthesized instances. The most prominent features found to play a substantial role in the progression of the disease are: diabetes, cholesterol and cholesterol/HDL. Among novel markers, the CD11b marker of leukocyte integrin complex is associated with coronary plaque progression.

The CHRONIOUS system offers an integrated platform aiming at the effective management and real-time assessment of the health status of the patient suffering from chronic obstructive pulmonary disease (COPD). An intelligent system is developed for the analysis and the real-time evaluation of patient's condition. A hybrid classifier has been implemented on a personal digital assistant, combining a support vector machine, a random forest, and a rule-based system to provide a more advanced categorization scheme for the early and in real-time characterization of a COPD episode. This is followed by a severity estimation algorithm which classifies the identified pathological situation in different levels and triggers an alerting mechanism to provide an informative and instructive message/advice to the patient and the clinical supervisor. The system has been validated using data collected from 30 patients that have been annotated by experts indicating 1) the severity level of the current patient's health status, and 2) the COPD disease level of the recruited patients according to the GOLD guidelines. The achieved characterization accuracy has been found 94%.

Biological networks in living organisms can be seen as the ultimate means of understanding the underlying mechanisms in complex diseases, such as oral cancer. During the last decade, many algorithms based on high-throughput genomic data have been developed to unravel the complexity of gene network construction and their progression in time. However, the small size of samples compared to the number of observed genes makes the inference of the network structure quite challenging. In this study, we propose a framework for constructing and analyzing gene networks from sparse experimental temporal data and investigate its potential in oral cancer. We use two network models based on partial correlations and kernel density estimation, in order to capture the genetic interactions. Using this network construction framework on real clinical data of the tissue and blood at different time stages, we identified common disease-related structures that may decipher the association between disease state and biological processes in oral cancer. Our study emphasizes an altered MET (hepatocyte growth factor receptor) network during oral cancer progression. In addition, we demonstrate that the functional changes of gene interactions during oral cancer progression might be particularly useful for patient categorization at the time of diagnosis and/or at follow-up periods.

The SIFEM project targets the development of an infrastructure in order to semantically link open source tools and libraries with existing data as well as new knowledge towards the multi-scale finite element modelling of the inner-ear. The SIFEM system is designed based on an open architecture schema that consists of a set of tools and subsystems in order to develop robust multi-scale models. The project mainly delivers: (i) tools for finite elements modelling, (ii) cochlea reconstruction tool and (iii) 3D inner ear models visualization tool. The main scientific results contribute to the knowledge of alterations associated to diverse cochlear disorders and could lead, in long-term, to personalized healthcare. The overview of the SIFEM platform and its architecture is presented in this paper.

Recovery software system operations from a state of extensive damage without human intervention is a challenging problem as it may need to be based on a different infrastructure from the one that the system was originally designed for and deployed on (i.e., computational and communication devices) and significant reorganization of system functionalities. In this paper, we introduce a bio-inspired approach for reconstructing nearly extinct complex software systems. Our approach is based on encoding a computational DNA (co-DNA) of a system and computational analogues of biological processes to enable the transmission of co-DNA over computational devices and, through it, the transformation of these devices into system cells that can realise chunks of the system functionality, and spread further its reconstruction process.

The detection of epileptic seizures is of primary interest for the diagnosis of patients with epilepsy. Epileptic seizure is a phenomenon of rhythmicity discharge for either a focal area or the entire brain and this individual behavior usually lasts from seconds to minutes. The unpredictable and rare occurrences of epileptic seizures make the automated detection of them highly recommended especially in long term EEG recordings. The present work proposes an automated method to detect the epileptic seizures by using an unsupervised method based on k-means clustering end Ensemble Empirical Decomposition (EEMD). EEG segments are obtained from a publicly available dataset and are classified in two categories “seizure” and “non-seizure”. Using EEMD the Marginal Spectrum (MS) of each one of the EEG segments is calculated. The MS is then divided into equal intervals and the averages of these intervals are used as input features for k-Means clustering. The evaluation results are very promising indicating overall accuracy 98% and is comparable with other related studies. An advantage of this method that no training data are used due to the unsupervised nature of k-Means clustering.

Chronic care of diabetes comes with large amounts of data concerning the self- and clinical management of the disease. In this paper, we propose to treat that information from two different perspectives. Firstly, a predictive model of short-term glucose homeostasis relying on machine learning is presented with the aim of preventing hypoglycemic events and prolonged hyperglycemia on a daily basis. Second, data mining approaches are proposed as a tool for explaining and predicting the long-term glucose control and the incidence of diabetic complications.

Stents are medical devices used in cardiovascular intervention for unblocking the diseased arteries and restoring blood flow. During stent implantation the deformation of the arterial wall as well as the resulted stresses caused in the arterial morphology are studied. In this paper we study the effect of the composition of the atherosclerotic plaque during the stent deployment procedure, using Finite Element modeling. The stenting procedure is simulated for two different cases; in the first the presence of the plaque is ignored whereas in the second a three dimensional (3D) stiff calcified plaque is located in the stenotic area of the artery. Results indicate that in the second case the von Mises stresses in the arterial wall are higher than the stresses occurred in the first case. In addition, the distribution of the arterial von Mises stress depends on the plaque composition.

The aim of this work is to present an automated non supervised method for the detection of occlusal caries based on photographic color images. The proposed method consists of three steps: (a) detection of decalcification areas, (b) detection of occlusal caries areas, and (c) fusion of the results. The detection process includes pre-processing of the images, segmentation and post-processing, where objects not corresponding to areas of interest are eliminated through the utilization of rules expressing the medical knowledge. The preprocessing, segmentation and post-processing are differentiated depending on the areas that have to be detected (decalcification or occlusal areas). The method was evaluated using a set of 60 images where 286 areas of interest were manually segmented by an expert. The obtained sensitivity and precision is 92% and 80%, respectively.

In this study, we present an innovative model for plaque growth utilizing a 3-Dimensional (3D) left coronary arterial tree reconstructed from computed tomographic (CT) data. The proposed model takes into consideration not only the effect of the local hemodynamic factors but also major biological processes such as the low density lipoprotein (LDL) and high density lipoprotein (HDL) transport, the macrophages recruitment and the foam cells formation. The endothelial membrane is considered semi-permeable and endothelial shear stress dependent, while its permeability is modeled using the Kedem-Katscalsky equations. Patient specific biological data are used for the accurate modeling of plaque formation process. The finite element method (FEM) is employed for the solution of the system of partial differential equations. The results of the simulation are compared to the plaque progression in a follow-up CT examination performed three years after the initial investigation. The results show that the proposed model can be used to predict regions prone for plaque development of progression.

Data-driven techniques have recently drawn significant interest in the predictive modeling of subcutaneous (s.c.) glucose concentration in type 1 diabetes. In this study, the s.c. glucose prediction is treated as a multivariate regression problem, which is addressed using support vector regression (SVR). The proposed method is based on variables concerning: (i) the s.c. glucose profile, (ii) the plasma insulin concentration, (iii) the appearance of meal-derived glucose in the systemic circulation, and (iv) the energy expenditure during physical activities. Six cases corresponding to different combinations of the aforementioned variables are used to investigate the influence of the input on the daily glucose prediction. The proposed method is evaluated using a dataset of 27 patients in free-living conditions. 10-fold cross validation is applied to each dataset individually to both optimize and test the SVR model. In the case where all the input variables are considered, the average prediction errors are 5.21, 6.03, 7.14 and 7.62 mg/dl for 15, 30, 60 and 120 min prediction horizons, respectively. The results clearly indicate that the availability of multivariable data and their effective combination can significantly increase the accuracy of both short-term and long-term predictions.

In this paper, we propose a method to estimate the density of a data space represented by a geometric transformation of an initial Gaussian mixture model. The geometric transformation is hierarchical, and it is decomposed into two steps. At first, the initial model is assumed to undergo a global similarity transformation modeled by translation, rotation, and scaling of the model components. Then, to increase the degrees of freedom of the model and allow it to capture fine data structures, each individual mixture component may be transformed by another, local similarity transformation, whose parameters are distinct for each component of the mixture. In addition, to constrain the order of magnitude of the local transformation (LT) with respect to the global transformation (GT), zero-mean Gaussian priors are imposed onto the local parameters. The estimation of both GT and LT parameters is obtained through the expectation maximization framework. Experiments on artificial data are conducted to evaluate the proposed model, with varying data dimensionality, number of model components, and transformation parameters. In addition, the method is evaluated using real data from a speech recognition task. The obtained results show a high model accuracy and demonstrate the potential application of the proposed method to similar classification problems.

In this paper, we introduce a new suction detection approach based on online learning of a Gaussian Mixture Model (GMM) with constrained parameters to model the reduction in pump flow signals baseline during suction events. A novel three-step methodology is employed: i) signal windowing, ii) GMM based classification and iii) GMM parameter adaptation. More specifically, the first 5 second segment is used for the parameter initialization and the consequent 1 second windows are classified and used for model adaptation. The proposed approach has been tested in simulation (pump flow) signals and satisfactory results have been obtained.

Intravascular ultrasound (IVUS) virtual histology (VH-IVUS) is a new technique, which provides automated plaque characterization in IVUS frames, using the ultrasound backscattered RF-signals. However, its computation can only be performed once per cardiac cycle (ECG-gated technique), which significantly decreases the number of characterized IVUS frames. Also atherosclerotic plaques in images that have been acquired by machines, which are not equipped with the VH software, cannot be characterized. To address these limitations, we have developed a plaque characterization technique that can be applied in grayscale IVUS images. Our semiautomated method is based on a three-step approach. In the first step, the plaque area [region of interest (ROI)] is detected semiautomatically. In the second step, a set of features is extracted for each pixel of the ROI and in the third step, a random forest classifier is used to classify these pixels into four classes: dense calcium, necrotic core, fibrotic tissue, and fibro-fatty tissue. In order to train and validate our method, we used 300 IVUS frames acquired from virtual histology examinations from ten patients. The overall accuracy of the proposed method was 85.65% suggesting that our approach is reliable and may be further investigated in the clinical and research arena.

Oral squamous cell carcinoma (OSCC) constitutes the predominant neoplasm of the head and neck region, featuring particularly aggressive nature, associated with quite unfavorable prognosis. In this work we formulate a Decision Support System (DSS) which integrates a multitude of heterogeneous data (clinical, imaging and genomic), thus, framing all manifestations of the disease. Our primary aim is to identify the factors that dictate OSCC progression and subsequently predict potential relapses (local or metastatic) of the disease. The discrimination potential of each source of data is initially explored separately, and afterwards the individual predictions are combined to yield a consensus decision achieving complete discrimination between patients with and without a disease relapse.

Atherosclerosis is a progressive disease characterized by the accumulation of lipids and fibrous elements in arteries. It is characterized by dysfunction of endothelium and vasculitis, and accumulation of lipid, cholesterol, and cell elements inside blood vessel wall. In this study, a continuum-based approach for plaque formation and development in 3-D is presented. The blood flow is simulated by the 3-D Navier-Stokes equations, together with the continuity equation while low-density lipoprotein (LDL) transport in lumen of the vessel is coupled with Kedem-Katchalsky equations. The inflammatory process was solved using three additional reaction-diffusion partial differential equations. Transport of labeled LDL was fitted with our experiment on the rabbit animal model. Matching with histological data for LDL localization was achieved. Also, 3-D model of the straight artery with initial mild constriction of 30% plaque for formation and development is presented.

Computational fluid dynamics methods based on in vivo 3-D vessel reconstructions have recently been identified the influence of wall shear stress on endothelial cells as well as on vascular smooth muscle cells, resulting in different events such as flow mediated vasodilatation, atherosclerosis, and vascular remodeling. Development of image-based modeling technologies for simulating patient-specific local blood flows is introducing a novel approach to risk prediction for coronary plaque growth and progression. In this study, we developed 3-D model of plaque formation and progression that was tested in a set of patients who underwent coronary computed tomography angiography (CTA) for anginal symptoms. The 3-D blood flow is described by the Navier-Stokes equations, together with the continuity equation. Mass transfer within the blood lumen and through the arterial wall is coupled with the blood flow and is modeled by a convection-diffusion equation. The low density lipoprotein (LDL) transports in lumen of the vessel and through the vessel tissue (which has a mass consumption term) are coupled by Kedem-Katchalsky equations. The inflammatory process is modeled using three additional reaction-diffusion partial differential equations. A full 3-D model was created. It includes blood flow and LDL concentration, as well as plaque formation and progression. Furthermore, features potentially affecting plaque growth, such as patient risk score, circulating biomarkers, localization and composition of the initial plaque, and coronary vasodilating capability were also investigated. The proof of concept of the model effectiveness was assessed by repetition of CTA, six months after the baseline evaluation. Besides the low values of local shear stress, plaque characteristics, risk profile, pattern of circulating adhesion molecules, and reduced coronary flow reserve at baseline appeared to affect plaque progression toward flow-limiting lesions at follow-up evaluation. Although preliminary, our multidisciplinary approach to a “personalized” prediction of coronary plaque progression suggests that incorporation in atherosclerotic models of systemic and local hemodynamic features may better predict evolution of plaques in coronary artery disease stable patients.

Tremor is the most common motor disorder of Parkinson's disease (PD) and consequently its detection plays a crucial role in the management and treatment of PD patients. The current diagnosis procedure is based on subject-dependent clinical assessment, which has a difficulty in capturing subtle tremor features. In this paper, an automated method for both resting and action/postural tremor assessment is proposed using a set of accelerometers mounted on different patient's body segments. The estimation of tremor type (resting/action postural) and severity is based on features extracted from the acquired signals and hidden Markov models. The method is evaluated using data collected from 23 subjects (18 PD patients and 5 control subjects). The obtained results verified that the proposed method successfully: 1) quantifies tremor severity with 87 % accuracy, 2) discriminates resting from postural tremor, and 3) discriminates tremor from other Parkinsonian motor symptoms during daily activities.

The accurate diagnosis of diseases with high prevalence rate, such as Alzheimer, Parkinson, diabetes, breast cancer, and heart diseases, is one of the most important biomedical problems whose administration is imperative. In this paper, we present a new method for the automated diagnosis of diseases based on the improvement of random forests classification algorithm. More specifically, the dynamic determination of the optimum number of base classifiers composing the random forests is addressed. The proposed method is different from most of the methods reported in the literature, which follow an overproduce-and-choose strategy, where the members of the ensemble are selected from a pool of classifiers, which is known a priori. In our case, the number of classifiers is determined during the growing procedure of the forest. Additionally, the proposed method produces an ensemble not only accurate, but also diverse, ensuring the two important properties that should characterize an ensemble classifier. The method is based on an online fitting procedure and it is evaluated using eight biomedical datasets and five versions of the random forests algorithm (40 cases). The method decided correctly the number of trees in 90% of the test cases.

In this paper, a real-time methodology for the detection of stress events while driving is presented. The detection is based on the use of physiological signals, i.e., electrocardiogram, electrodermal activity, and respiration, as well as past observations of driving behavior. Features are calculated over windows of specific length and are introduced in a Bayesian network to detect driver's stress events. The accuracy of the stress event detection based only on physiological features, evaluated on a data set obtained in real driving conditions, resulted in an accuracy of 82%. Enhancement of the stress event detection model with the incorporation of driving event information has reduced false positives, yielding an increased accuracy of 96%. Furthermore, our methodology demonstrates good adaptability due to the application of online learning of the model parameters.

BACKGROUND: In peptides and proteins, only a small percentile of peptide bonds adopts the cis configuration. Especially in the case of amide peptide bonds, the amount of cis conformations is quite limited thus hampering systematic studies, until recently. However, lately the emerging population of databases with more 3D structures of proteins has produced a considerable number of sequences containing non-proline cis formations (cis-nonPro). RESULTS: In our work, we extract regular expression-type patterns that are descriptive of regions surrounding the cis-nonPro formations. For this purpose, three types of pattern discovery are performed: i) exact pattern discovery, ii) pattern discovery using a chemical equivalency set, and iii) pattern discovery using a structural equivalency set. Afterwards, using each pattern as predicate, we search the Eukaryotic Linear Motif (ELM) resource to identify potential functional implications of regions with cis-nonPro peptide bonds. The patterns extracted from each type of pattern discovery are further employed, in order to formulate a pattern-based classifier, which is used to discriminate between cis-nonPro and trans-nonPro formations. CONCLUSIONS: In terms of functional implications, we observe a significant association of cis-nonPro peptide bonds towards ligand/binding functionalities. As for the pattern-based classification scheme, the highest results were obtained using the structural equivalency set, which yielded 70% accuracy, 77% sensitivity and 63% specificity.

The 20 papers in this special issue were originally presented in the International Special Topic Conference on Information Technology in Biomedicine, held in October 2009, in Larnaka, Cyprus.

The 15 papers in this special section on new and emerging technologies in bioinformatics and bioengineering have been grouped into the following categories: 1) computational intelligence and data mining in support of decision making in biomedicine; 2) new applications and wireless communication issues in body sensor networks; 3) human-computer interaction; and 4) medical imaging and physiological systems modeling.

In this paper, the Bayesian framework is used for the analysis of functional MRI (fMRI) data. Two algorithms are proposed to deal with the nonstationarity of the noise. The first algorithm is based on the temporal analysis of the data, while the second algorithm is based on the spatiotemporal analysis. Both algorithms estimate the variance of the noise across the images and the voxels. The first algorithm is based on the generalized linear model (GLM), while the second algorithm is based on a spatiotemporal version of it. In the GLM, an extended design matrix is used to deal with the presence of the drift in the fMRI time series. To estimate the regression parameters of the GLM as well as the variance components of the noise, the variational Bayesian (VB) methodology is employed. The use of the VB methodology results in an iterative algorithm, where the estimation of the regression coefficients and the estimation of variance components of the noise, across images and voxels, are interchanged in an elegant and fully automated way. The performance of the proposed algorithms (under the assumption of different noise models) is compared with the weighted least-squares (WLSs) method. Results using simulated and real data indicate the superiority of the proposed approach compared to the WLS method, thus taking into account the complex noise structure of the fMRI time series.

BACKGROUND: Polypeptides are composed of amino acids covalently bonded via a peptide bond. The majority of peptide bonds in proteins is found to occur in the trans conformation. In spite of their infrequent occurrence, cis peptide bonds play a key role in the protein structure and function, as well as in many significant biological processes. RESULTS: We perform a systematic analysis of regions in protein sequences that contain a proline cis peptide bond in order to discover non-random associations between the primary sequence and the nature of proline cis/trans isomerization. For this purpose an efficient pattern discovery algorithm is employed which discovers regular expression-type patterns that are overrepresented (i.e. appear frequently repeated) in a set of sequences. Four types of pattern discovery are performed: i) exact pattern discovery, ii) pattern discovery using a chemical equivalency set, iii) pattern discovery using a structural equivalency set and iv) pattern discovery using certain amino acids' physicochemical properties. The extracted patterns are carefully validated using a specially implemented scoring function and a significance measure (i.e. log-probability estimate) indicative of their specificity. The score threshold for the first three types of pattern discovery is 0.90 while for the last type of pattern discovery 0.80. Regarding the significance measure, all patterns yielded values in the range [-9, -31] which ensure that the derived patterns are highly unlikely to have emerged by chance. Among the highest scoring patterns, most of them are consistent with previous investigations concerning the neighborhood of cis proline peptide bonds, and many new ones are identified. Finally, the extracted patterns are systematically compared against the PROSITE database, in order to gain insight into the functional implications of cis prolyl bonds. CONCLUSION: Cis patterns with matches in the PROSITE database fell mostly into two main functional clusters: family signatures and protein signatures. However considerable propensity was also observed for targeting signals, active and phosphorylation sites as well as domain signatures.

Multichannel chromosome image acquisition is used for cancer diagnosis and research on genetic disorders. This type of imaging, apart from aiding the cytogeneticist in several ways, facilitates the visual detection of chromosome abnormalities. However, chromosome misclassification errors result from different factors, such as uneven hybridization, spectral overlap among fluors, and biochemical noise. In this paper, we enhance the chromosome classification accuracy by making use of a region Bayes classifier that increases the classification accuracy when compared to the already developed pixel-by-pixel classifier and by incorporating the vector median filtering approach for filtering of the image. The method is evaluated using a publicly available database that contains 183 six-channel chromosome sets of images. The overall improvement on the chromosome classification accuracy is 9.99%, compared to the pixel-by-pixel classifier without filtering. This improvement in the chromosome classification accuracy would allow subtle deoxyribonucleic acid abnormalities to be identified easily. The efficiency of the method might further improve by using features extracted from each region and a more sophisticated classifier.

The six papers in this special section focus on the most recent applications of computational intelligent systems in medicine. Some papers accepted for this issue (10 in total) were published earlier by mistake.

The detection of recorded epileptic seizure activity in EEG segments is crucial for the localization and classification of epileptic seizures. However, since seizure evolution is typically a dynamic and nonstationary process and the signals are composed of multiple frequencies, visual and conventional frequency-based methods have limited application. In this paper, we demonstrate the suitability of the time-frequency (t-f) analysis to classify EEG segments for epileptic seizures, and we compare several methods for t-f analysis of EEGs. Short-time Fourier transform and several t-f distributions are used to calculate the power spectrum density (PSD) of each segment. The analysis is performed in three stages: 1) t-f analysis and calculation of the PSD of each EEG segment; 2) feature extraction, measuring the signal segment fractional energy on specific t-f windows; and 3) classification of the EEG segment (existence of epileptic seizure or not), using artificial neural networks. The methods are evaluated using three classification problems obtained from a benchmark EEG dataset, and qualitative and quantitative results are presented.

Non-prolinecispeptide bonds have been quite underrated for many years, due to the limited amount of structural information available. There is now significant evidence that non-prolinecispeptide bonds occur more frequently than previously thought, and that they are often located at or near important sites of the protein molecule. In this work, we employ a combinatorial pattern discovery algorithm in order to identify simple and specific amino acid patterns, associated with the occurrence of non-proline cis peptide bonds in proteins. The derived patterns after careful validation help in gaining insight into the factors that influence the formation of non-proline cis peptide bonds.

The selection of a personalized treatment plan for a patient with cancer can be of critical importance for his health or even survival. A Decision Support Platform that can associate the patient clinical situation with the patient DNA Single Nucleotide Polymorphisms (SNPs) can provide the oncologist with a better understanding of the personalized conditions of every single patient. In this paper we present the MATCH platform which performs data integration between medicine and molecular biology, by developing a framework where, clinical and genomic features are appropriately combined in order to handle colon cancer diseases. The core of the platform is based on clustering techniques which provide profiles of patients with similar clinical features and genetic predispositions to cancer. The patients which share the same profile should probably have similar treatment plan and follow up. Through the integration of the clinical and genetic data of a patient, real time conclusions can be drawn for his early diagnosis, staging and more effective colon cancer treatment. Intelligent components are designed and developed which identify single nucleotide polymorphisms (SNPs) from the gene sequences and combine them with the clinical situation of the patient. The produced clinico-genomic profiles are used as a decision support tool for newly sequenced patients.

In this paper we present the POCEMON platform, a platform aiming to the early prognosis and diagnosis of autoimmune diseases at any point of care, even the primary. The objective of the POCEMON platform is the development of a diagnostic lab-on-chip device based on genomic microarrays of HLA-typing. The POCEMON is going to advance and promote the primary health care across Europe by supporting a) point-of-care diagnostics, b) monitoring of immune system status and c) management of the chronic multiple sclerosis (MS) and rheumatoid arthritis (RA) autoimmune diseases. The platform combines high-end Information and Communication Technologies based on microfluidics, microelectronics, microarrays and intelligent diagnosis algorithms.

The aim of this work is to propose a new approach for the determination of the design matrix in fMRI experiments. The design matrix embodies all available knowledge about experimentally controlled factors and potential confounds. This knowledge is expressed through the regressors of the design matrix. However, in a particular fMRI time series some of those regressors may not be present. In order to take into account this prior information a Bayesian approach based on hierarchical prior, which expresses the sparsity of the design matrix, is used over the parameters of the generalized linear model. The proposed method automatically prunes the columns of the design matrix which are irrelevant to the generation of data. The evaluation of the proposed approach on simulated and real experiments have shown higher performance compared to the conventional t-test approach.

The present study investigates the effect of transosseous low-intensity pulsed ultrasound (LiUS) during lingamentization process on the healing at tendon graft-bone interface in rabbits. Analysis of the RT-PCR products showed statistically significant up-regulation of genes encoding collagen type I and tRNAGlyin the study group compared to the control group. Histological examination indicated a faster healing rate and a more efficient lingamentization process after ultrasound treatment. Our results suggest that transosseous application of LiUS enhances the healing rate of the tendon graft-bone interface, possibly by affecting the expression levels of significant genes.

In this paper we explore the use of weights in the generation of fuzzy models. We automatically generate a fuzzy model, using a three-stage methodology: (i) generation of a crisp model from a decision tree, induced from the data, (ii) transformation of the crisp model into a fuzzy one, and (iii) optimization of the fuzzy modelpsilas parameters. Based on this methodology, the generated fuzzy model includes a set of parameters, which are all the parameters included in the sigmoid functions. In addition, local, global and class weights are included, thus the fuzzy model is optimized with respect to both sigmoid function parameters and weights. The class weight introduction, which is a novel approach, grants to the fuzzy model the ability to identify the individual importance of each class and thus more accurately reflect the underlying properties of the classes under examination, in the domain of application. The above described methodology is applied to five known classification problems, obtained from the UCI machine learning repository, and the obtained classification accuracy is high.

M-FISH (multiplex fluorescent in situ hybridization) is a multichannel channel chromosome imaging technique that allows the color discrimination of human chromosomes. Although M-FISH facilitates the visual detection of chromosome rearrangements, the success of this technique largely depends on the accuracy of the pixel-by-pixel classification. In this paper, we present a new method that enhances the classification ratio based on a region based decorrelation stretch transform. Utilizing the decomposition of the multichannel image into homogenous regions, the classification results improved after the application of the decorrelation stretch transform. Fifteen M-FISH images were used to test our method. To quantitatively estimate the enhancement we have used a Bayes pixel-by-pixel classifier and an improvement of 12.28% is achieved.

This work investigates the use of a point distribution model to detect prominent features in a face (eyes, brows, mouth, etc) and the subsequent facial feature extraction and facial expression classification into seven categories (anger, fear, surprise, happiness, disgust, neutral and sadness). A multi-scale and multi-orientation Gabor filter bank, designed in such a way so as to avoid redundant information, is used to extract facial features at selected locations of the prominent features of a face (fiducial points). A region based approach is employed at the location of the fiducial points using different region sizes to allow some degree of flexibility and avoid artefacts due to incorrect automatic discovery of these points. A feed forward back propagation Artificial Neural Network is employed to classify the extracted feature vectors. The methodology is evaluated by forming 7 different regions and the feature vector is extracted at the location of 20 fiducial points.

This paper describes the Alert Manager subsystem which merges information coming from: (i) an in-vehicle sensing system, (ii) the road infrastructure and (iii) neighbouring vehicles to generate high level and useful information for car drivers. The subsystem is a part of the I-WAY system, whose aim is to provide drivers with timely warnings and meaningful suggestions to avoid potential hazards in the driving environment. The Alert Manager can efficiently handle multiple information sources, fusion of complementary data and management of incoming events' priorities. Moreover, the Alert Manager controls the broadcasting of messages to keep Road Infrastructure and other vehicles updated about potential hazards. We focus on the determination of the dominant risk prevailing in the road environment.

The ever increasing number of external and internal data available in modern cars can only become beneficial if the data are assessed correctly and presented according to the drivers' needs. This paper presents a well-designed method based on advanced information fusion that assembles and processes data centralized, which has been developed within the framework of the European funded research project I-WAY. A key task of this method is the reduction of the input data to a manageable amount that supports the unobtrusive delivery of useful and safety critical information to drivers. The solution proposed introduces the transformation of mainly cyclic arriving data from the time to the event domain. The main advantage is that the communication load is reduced to the minimum, as only relevant changes-events-must be processed in subsequent modules. The pre-selection of events thereby serves as data filter and data fusion, allowing for fast decision making. The use case at the end of the paper presents preliminary results on the application of this data fusion method gathered in a vehicle from video, radar, and weather information.

A fuzzy rule-based decision support system (DSS) is presented for the diagnosis of coronary artery disease (CAD). The system is automatically generated from an initial annotated dataset, using a four stage methodology: 1) induction of a decision tree from the data; 2) extraction of a set of rules from the decision tree, in disjunctive normal form and formulation of a crisp model; 3) transformation of the crisp set of rules into a fuzzy model; and 4) optimization of the parameters of the fuzzy model. The dataset used for the DSS generation and evaluation consists of 199 subjects, each one characterized by 19 features, including demographic and history data, as well as laboratory examinations. Tenfold cross validation is employed, and the average sensitivity and specificity obtained is 62% and 54%, respectively, using the set of rules extracted from the decision tree (first and second stages), while the average sensitivity and specificity increase to 80% and 65%, respectively, when the fuzzification and optimization stages are used. The system offers several advantages since it is automatically generated, it provides CAD diagnosis based on easily and noninvasively acquired features, and is able to provide interpretation for the decisions made.

Multiplex fluorescent in situ hybridization (M-FISH) is a recently developed chromosome imaging technique where each chromosome class appears to have a distinct color. This technique not only facilitates the detection of subtle chromosomal aberrations but also makes the analysis of chromosome images easier; both for human inspection and computerized analysis. In this paper, a novel method for segmentation and classification of M-FISH chromosome images is presented. The segmentation is based on the multichannel watershed transform in order to define regions of similar spatial and spectral characteristics. Then, a Bayes classifier, task-specific on region classification, is applied. Our method consists of four basic steps: 1) computation of the gradient magnitude of the image, 2) application of the watershed transform to decompose the image into a set of homogenous regions, 3) classification of each region, and 4) merging of similar adjacent regions. The method is evaluated using a publicly available chromosome image database and the obtained overall accuracy is 82.4%. By introducing the classification of each watershed region, the proposed method achieves substantially better results compared to other methods at a lower computational cost. The combination of the multichannel segmentation and the region-based classification is found to improve the overall classification accuracy compared to pixel-by-pixel approaches.

In this paper, we present a methodology and a wearable system for the evaluation of the emotional states of car-racing drivers. The proposed approach performs an assessment of the emotional states using facial electromyograms, electrocardiogram, respiration, and electrodermal activity. The system consists of the following: 1) the multisensorial wearable module; 2) the centralized computing module; and 3) the system's interface. The system has been preliminary validated by using data obtained from ten subjects in simulated racing conditions. The emotional classes identified are high stress, low stress, disappointment, and euphoria. Support vector machines (SVMs) and adaptive neuro-fuzzy inference system (ANFIS) have been used for the classification. The overall classification rates achieved by using tenfold cross validation are 79.3% and 76.7% for the SVM and the ANFIS, respectively.

Multiplex fluorescent in situ hybridization (M-FISH) is a newly chromosome imaging technique where each chromosome class appears to have a distinct color. This technique although it makes the analysis of chromosome images easier, still exhibits misclassification errors that can be misinterpreted as chromosome abnormalities. A new method for the multichannel image segmentation and region classification is proposed. The segmentation of M-FISH images is based on a multichannel watershed segmentation method in order to define regions of same spectral characteristics. The region Bayes classification method which focuses on region classification is used. The classifier was trained and tested on nonoverlapping chromosome images and an overall accuracy 89% is achieved. The superiority of the proposed method over methods that use pixel-by-pixel classification is demonstrated.

A electroencephalographic (EEG) signals, concerning epileptic seizures, is proposed. First, segments of the EEG signals are analyzed using a time-frequency distribution and then, several features are extracted for each segment, representing the energy distribution over the time-frequency plane. Those features are used as an input in an artificial neural network (ANN), which provides the final classification of the EEG segments (existence of epileptic seizure or not). The evaluation results are very promising, indicating overall accuracy from 89.4% to 99%.

This paper introduces an automated methodology for the extraction of fetal heart rate from cutaneous potential abdominal electrocardiogram (abdECG) recordings. A three-stage methodology is proposed. Having the initial recording, which consists of a small number of abdECG leads in the first stage, the maternal R-peaks and fiducial points (QRS onset and offset) are detected using time-frequency (t-f) analysis and medical knowledge. Then, the maternal QRS complexes are eliminated. In the second stage, the positions of the candidate fetal R-peaks are located using complex wavelets and matching theory techniques. In the third stage, the fetal R-peaks, which overlap with the maternal QRS complexes (eliminated in the first stage) are found using two approaches: a heuristic algorithm technique and a histogram-based technique. The fetal R-peaks detected are used to calculate the fetal heart rate. The methodology is validated using a dataset of eight short and ten long-duration recordings, obtained between the 20th and the 41st week of gestation, and the obtained accuracy is 97.47%. The proposed methodology is advantageous, since it is based on the analysis of few abdominal leads in contrast to other proposed methods, which need a large number of leads.

A three-stage method for fetal heart rate extraction, from abdominal ECG recordings, is proposed. In the first stage the maternal R-peaks and fiducial points (QRS onset and offset) are detected, using time-frequency analysis, and the maternal QRS complexes are eliminated. The second stage locates the positions of the candidate fetal R-peaks, using complex wavelets and pattern matching theory techniques. In the third stage, the fetal R-peaks that overlap with the maternal QRS complexes are found. The method is validated using a dataset of 4 long duration recordings and the obtained results indicate high detection ability of the method (96% accuracy)

A rule-based decision support system is presented for the diagnosis of coronary artery disease. The generation of the decision support system is realized automatically using a three stage methodology: (a) induction of a decision tree from a training set and extraction of a set of rules; (b) transformation of the set of rules into a fuzzy model and (c) optimization of the parameters of the fuzzy model. The system is evaluated using 199 subjects, each one characterized by 19 features, including demographic and history data, as well as laboratory examinations. Ten fold cross validation was employed and the average sensitivity and specificity obtained was 80% and 65% respectively. Our approach provides diagnosis based on easily acquired features and, since it is rule based, is able to provide interpretation for the decisions made

In this paper, a methodology for the automated detection and classification of transient events in electroencephalographic (EEG) recordings is presented. It is based on association rule mining and classifies transient events into four categories: epileptic spikes, muscle activity, eye blinking activity, and sharp alpha activity. The methodology involves four stages: 1) transient event detection; 2) clustering of transient events and feature extraction; 3) feature discretization and feature subset selection; and 4) association rule mining and classification of transient events. The methodology is evaluated using 25 EEG recordings, and the best obtained accuracy was 87.38%. The proposed approach combines high accuracy with the ability to provide interpretation for the decisions made, since it is based on a set of association rules.

An automated methodology which detects transient events in EEG recordings and classifies those as epileptic spikes, muscle activity, eye blinking activity and sharp alpha activity is presented. It is based on data mining algorithms and includes four stages: (I) EEG preprocessing and transient events detection, (II) clustering of transient events and feature extraction, (III) feature discretization and (IV) association rule mining and classification. The methodology is evaluated using a dataset of 25 EEG recordings and the obtained overall accuracy is 84.35%. The major advantage of our approach is that it is able to provide interpretation for the decisions made since it is based on a set of association rules.

An information brokerage environment for effective information structuring, indexing, and retrieval in the health-care administration sector is presented. The system is based on ontology modeling, natural language processing, extensible markup language, semantics analysis, and behavioral description. Semantics-based information acquisition is achieved through the uniform modeling, representation, and handling of domain-specific knowledge, both content-based and procedural. The system has been validated using information located on several repositories in the web and its performance is reported in terms of precision and recall.

In this paper, we present a method for the automated detection of lumen and media-adventitia border in sequential intravascular ultrasound (IVUS) frames. The method is based on the use of deformable models. The energy function is appropriately modified and minimized using a Hopfield neural network. Proper modifications in the definition of the bias of the neurons have been introduced to incorporate image characteristics. A simulated annealing scheme is included to ensure convergence at a global minimum. The method overcomes distortions in the expected image pattern, due to the presence of calcium, employing a specialized structure of the neural network and boundary correction schemas which are based on a priori knowledge about the vessel geometry. The proposed method is evaluated using sequences of IVUS frames from 18 arterial segments, some of them indicating calcified regions. The obtained results demonstrate that our method is statistically accurate, reproducible, and capable to identify the regions of interest in sequences of IVUS frames.

MOTIVATION: This paper studies the problem of discovering subsequences, known as motifs, that are common to a given collection of related biosequences, by proposing a greedy algorithm for learning a mixture of motifs model through likelihood maximization. The approach adds sequentially a new motif to a mixture model by performing a combined scheme of global and local search for appropriately initializing its parameters. In addition, a hierarchical partitioning scheme based on kd-trees is presented for partitioning the input dataset in order to speed-up the global searching procedure. The proposed method compares favorably over the well-known MEME approach and treats successfully several drawbacks of MEME. RESULTS: Experimental results indicate that the algorithm is advantageous in identifying larger groups of motifs characteristic of biological families with significant conservation. In addition, it offers better diagnostic capabilities by building more powerful statistical motif-models with improved classification accuracy.

In cases where the signal-to-noise ratio (SNR) in ECGs is very poor, the correct definition of characteristics such as the isoelectric line and the J-point (beginning of the ST segment) is difficult. Inaccurate definition of those ECG characteristics can lead an automated ischemia detector to an incorrect diagnosis. We propose a method capable of extracting from noisy long duration ECG recordings those ECG characteristics that can be used for myocardial ischemia detection and analysis. We tested the performance of the method using noisy ECGs from the European Society of Cardiology ST-T database (ESC ST-T database). The results were more than satisfactory and the performance of our ischemia detector was improved in all cases. The proposed technique has low computational effort and can be executed in real time.

We present a method to solve initial and boundary value problems using artificial neural networks. A trial solution of the differential equation is written as a sum of two parts. The first part satisfies the initial/boundary conditions and contains no adjustable parameters. The second part is constructed so as not to affect the initial/boundary conditions. This part involves a feedforward neural network containing adjustable parameters (the weights). Hence by construction the initial/boundary conditions are satisfied and the network is trained to satisfy the differential equation. The applicability of this approach ranges from single ordinary differential equations (ODE's), to systems of coupled ODE's and also to partial differential equations (PDE's). In this article, we illustrate the method by solving a variety of model problems and present comparisons with solutions obtained using the Galekrkin finite element method for several cases of partial differential equations. With the advent of neuroprocessors and digital signal processors the method becomes particularly interesting due to the expected essential gains in the execution speed.