Transcripts displayed on dictation interfaces can be hard to read due to recognition errors and disfluencies. LLM-based text auto-correction could help, but changing the text during production could lead to distraction and unintended phrasing. To understand how to balance readability, attention, and accuracy, we conducted an eye-tracking experiment with 20 participants to compare five dictation interfaces: PLAIN (real-time transcription), AOC (periodic corrections), RAKE (keyword highlights), GP-TSM (grammar-preserving highlights), and SUMMARY (LLM-generated abstractive summary). By analyzing participants’ gaze patterns during speech composition and reviewing processes, we found that during composition, participants spent only 7%-11% of their time in active reading regardless of the interface. Although SUMMARY introduced unfamiliar words and phrasing during composition, it was easier to read and more preferred by participants. Our findings suggest a high user tolerance for altering spoken words in LLM-enabled diction interfaces.

• An investigation into the effects of pairing synthesized clinical notes with image data to train a multimodal AI algorithm, using dermatology as example problem domain. • Leveraging metadata information to drive clinical note synthesis reduces hallucinations in Large Language Model (LLM) outputs. • Clinical notes generated by different LLMs using metadata lead to similar performance on downstream tasks when paired with real dermatology images. • Combination of multimodal data improves generalization performance on external datasets. Despite recent advancements in the development of foundation models and multimodal (MM) architectures in dermatology, their translation to clinical practice remains limited by the scarcity of large-scale multimodal (MM) datasets, as most publicly available resources are small, unimodal, and lack expressive clinical text. This paper investigates strategies to synthesize and exploit clinical notes paired with dermatological images to effectively train a MM architecture, focusing on solutions to limit the inherently hallucinated contents introduced by Large Language Models (LLMs) and to identify conditions under which synthetic clinical notes can be reliably leveraged. The paper proposes a MM architecture trained on real dermatological images paired with LLM-synthesized clinical notes. We systematically evaluate different note generation strategies, including metadata-guided prompting, alignment of image representations with specific keywords, sentence-level filtering of clinical notes, network architectural designs. Experiments involve 16,000 image-note couples collected from six public datasets for model training and over 37,000 images from fifteen public datasets as external data for generalization assessment. Performance is assessed on cross-modal retrieval and zero-shot learning tasks to quantify robustness and generalization. Results show that metadata inclusion into the prompts reduces the hallucinations within LLM outputs, providing more reliable notes. The resulting MM model trained with these notes show superior performance on multiple downstream tasks. Synthesized clinical notes can be paired with real dermatology images under specific conditions, providing a valuable resource to develop foundation models that can help reduce the dermatologists’ workload.

Hallucination in deep learning (DL) classification, where DL models yield confidently erroneous predictions remains a pressing concern. This study investigates whether binary classifiers are truly learning disease-specific features when distinguishing overlapping radiological presentations among pneumonia subtypes on chest X-ray (CXR) images. Specifically, we evaluate if uncertainty measure is a valuable tool in classifying signs of different pathogen-specific subtypes of pneumonia. We evaluated two binary classifiers to classify bacterial pneumonia and viral pneumonia, respectively, from normal CXRs. A third classifier explored the ability to distinguish bacterial from viral pneumonia presentation to highlight our concern regarding the observed hallucinations in the former cases. Our comprehensive analysis computes the Matthews Correlation Coefficient and prediction entropy metrics on a pediatric CXR dataset and reveals that the normal/bacterial and normal/viral classifiers consistently and confidently misclassify the unseen pneumonia subtype to their respective disease class. These findings expose a critical limitation concerning the tendency of binary classifiers to hallucinate by relying on general pneumonia indicators rather than pathogen-specific patterns, thereby challenging their utility in clinical workflows.

Storyboarding is an established method for designing user experiences. Generative AI can support this process by helping designers quickly create visual narratives. However, existing tools mainly focus on improving the accuracy of text-to-image generation. There is a lack of understanding on how to effectively support the entire creative process of storyboarding and how to develop AI-powered tools to be integrated into designers' diverse workflows. In this work, we designed and developed StoryDiffusion, a system that integrates text-to-text and text-to-image models, to support the generation of narratives and images in a single pipeline. In a user study, we observed 12 UX design students using the system for both concept ideation and illustration tasks. Our findings identified AI-directed vs. user-directed creative strategies in both tasks and revealed the importance of supporting the interchange between narrative iteration and image generation. We also found effects of the design tasks on their strategies and preferences, providing insights for future development. © 2025 Copyright held by the owner/author(s).

Although extensive research has been conducted on modeling the stable longitudinal controller of automated vehicles (AVs) to dampen traffic oscillations, the real-world performance of these controllers in actual vehicles remains uncertain. In the operation of real-world AVs, the delay between actual dynamics and the commands prevents the controller's command from being effectively implemented to dampen traffic oscillations. Thus, this study adapts the designed controllers within an AV test platform to compare the theoretically stable conditions with the actual oscillation dampening performance. Initially, we compute the stable conditions for both the traditional car-following controller, which assumes no delay, and the longitudinal controller that accounts for the dynamic response of the vehicle. Through empirical experiments, we demonstrate that the longitudinal controller predicts vehicle stability more accurately than conventional car-following controller, showing an improvement from an average prediction accuracy rate of 0.59 to 0.91. Also, the experiments uncover specific delays inherent in dynamics systems, with a response delay of 0.34 seconds. Our work makes two principal contributions to the field of AV control systems. First, it empirically validates that the longitudinal model, which accounts for the vehicle's dynamic responses, offers a more precise representation of vehicular behavior. Second, the relatively brief response delay identified expands the stability region, thereby enhancing vehicle control and safety. The longitudinal controller is critical for enhancing AV performance and reliability in dampening traffic oscillations.

Cooperative driving systems are expected to enhance safety, mobility, and efficiency through vehicle connectivity technologies. Lower-level vehicle-to-vehicle (V2V) communication transmits high-frequency status information, such as location, velocity, and acceleration, between vehicles. This approach contributes limitedly to prediction accuracy, requires high-frequency hardware, and is sensitive to communication delays. Recent studies have shown that intent sharing, which conveys planning trajectories, significantly improves prediction accuracy and control performance but requires higher band-width. However, mainstream vehicle communication methods struggle to balance cost and bandwidth for effective intent sharing. High-bandwidth wireless communication methods such as dedicated short-range communication (DSRC) and cellular vehicle-to-everything (C-V2X) cost much for devices, while low-cost visible light communication (VLC) can hardly support the necessary bandwidth. To address this challenge, we propose a lightweight intent sharing approach that reduces data transmission volume while maintaining prediction accuracy. Specifically, intended velocity trajectories are represented using regressed polynomial functions over a fixed time period, requiring only the transmission of polynomial coefficients and a timestamp for synchronization. The feasibility of this approach is demonstrated through simulations of car-following behavior using a Linear–Quadratic Regulator (LQR). Additionally, real vehicle experiments using a designated velocity cycle further validate the method. Results show that both planned and actual trajectories of the following vehicle closely align with those using ideal intent sharing approaches under significantly reduced communication data volume.

In this paper, an urban aerial delivery problem (UADP) is investigated, where the parcel transportation service is accomplished by drones in an urban setting. The aim of the problem is to minimize the total service completion time, by taking into account of the flow balance, the energy consumption, and the response time window. To fully explore the structure of the UADP, a mixed integer linear programming (MILP) model is constructed based on an arc-flow scheme. However, directly handling the UADP with commercial solvers is time consuming. In order to enhance the responsiveness of urban courier services and speed up the solving process, a set-covering model (UADP-SC) is proposed with a linear programming based relaxation. Then a branch-and-price algorithm is designed with pricing accelerating strategies based on heuristics. The computational experiments show that the proposed branch-and-price algorithm outperforms the off-the-shelf commercial solvers in terms of computation efficiency. In the mean time, the proposed algorithm can also serve to obtain optimal battery swapping and path planing decisions in face of the large-scale urban aerial delivery problem with energy constraints.Note to Practitioners—With the intensification of the aging population issue, the manual labor costs in logistics have sharply increased. Simultaneously, advancements in drone technology enable uncrewed aerial vehicles to participate in logistics distribution systems, addressing the last-mile delivery challenge. In the planning of drone delivery routes, the constraint of drone batteries cannot be ignored. This constraint not only affects delivery safety but also impacts delivery efficiency—both crucial considerations for decision-makers. Consequently, we propose a model considering the energy constraints. We introduce a branch-and-pricing algorithm to expedite the problem solving. The results show that the proposed algorithm performs well across various problem scales. Moreover, adopting a strategy of replacing batteries only when necessary can save approximately 17% to 23% of the total completion time. We also conducted performance comparisons under different ratios of orders to drones, providing decision-makers with a useful benchmark.

Deep learning (DL) has transformed medical image classification; however, its efficacy is often limited by significant data imbalance due to far fewer cases (minority class) compared to controls (majority class). It has been shown that synthetic image augmentation techniques can simulate clinical variability, leading to enhanced model performance. We hypothesize that they could also mitigate the challenge of data imbalance, thereby addressing overfitting to the majority class and enhancing generalization. Recently, latent diffusion models (LDMs) have shown promise in synthesizing high-quality medical images. This study evaluates the effectiveness of a text-guided image-to-image LDM in synthesizing disease-positive chest X-rays (CXRs) and augmenting a pediatric CXR dataset to improve classification performance. We first establish baseline performance by fine-tuning an ImageNet-pretrained Inception-V3 model on class-imbalanced data for two tasks-normal vs. pneumonia and normal vs. bronchopneumonia. Next, we fine-tune individual text-guided image-to-image LDMs to generate CXRs showing signs of pneumonia and bronchopneumonia. The Inception-V3 model is retrained on an updated data set that includes these synthesized images as part of augmented training and validation sets. Classification performance is compared using balanced accuracy, sensitivity, specificity, F-score, Matthews correlation coefficient (MCC), Kappa, and Youden's index against the baseline performance. Results show that the augmentation significantly improves Youden's index (p<0.05) and markedly enhances other metrics, indicating that data augmentation using LDM-synthesized images is an effective strategy for addressing class imbalance in medical image classification.

Many studies have demonstrated the eco-driving capabilities of connected and automated vehicles (CAVs) to significantly enhance mobility systems. The majority of these studies have been conducted using simulations, which fail to capture the effects of practical uncertainties encountered in vehicle-to-anything (V2X) communications. In this paper, we investigated the performance of current cellular V2X (C-V2X) communications through systematic testing and provided a quantitative analysis of key performance indices (e.g., inter-packet gap and packet error rate) across various test scenarios. As one use case to demonstrate the benefits of C-V2X communication on the road, we tested the feasibility of eco-driving for a SAE level 3 (L3) automated vehicle (AV) communicating with a connected urban corridor capable of transmitting traffic light information (i.e., signal phase and timing). To achieve this, we implemented the eco-speed planning algorithm at a high-level in the AV control software system and ensured its interactions with other existing low-level control algorithms, as well as the C-V2X onboard unit. Finally, we experimentally demonstrated eco-driving of the L3 CAV on a scaled-down corridor with two signal-controlled intersections, revealing the AV’s ability to maintain smoother trajectories and avoid unnecessary stops compared to human-driven vehicles.

Deep reinforcement learning (DRL) aims to train software agents that can understand environments and learn effective strategies, and has achieved significant breakthroughs in performance and capabilities, particularly in areas such as Go, Atari games, and autonomous vehicles. Unlike traditional deep learning, the goals of reinforcement learning can be more abstract and require careful modification of reward functions. The training process involves unstructured sequential data, which can be difficult for human experts to analyze and gain insights from. To address this challenge, we propose SampleViz, a visual analytics system that enables flexible interaction between human experts and DRL sequence data, allowing for the extraction of crucial concepts from massive amounts of data and their provision to the agent. SampleViz transforms the tedious task of modifying reward functions and policy debugging into an engaging concept exploration process, allowing for the efficient integration of human expertise with automatic sampling algorithms for effective model improvement. Through case studies and expert feedback, we demonstrate that SampleViz can effectively assist experts in concept extraction and model improvement, and enables the incorporation of interpretability and human-in-the-loop concepts into DRL policy settings.

This study introduces a new ensemble architecture to improve the wait time forecast for healthcare service in the emergency department (ED) of hospital. The new model first used a fine-tuned text embedding model to extract the contextual semantic meaning of patients’ chief complaint from the electronic patient records to estimate the degree of case urgency and combined to a recurrent neural network to process the regular ED wait time patterns. Four text embedding models including the universal sentence encoder with DAN and transformer encoders, the NNLM, and the Swivel were used for semantic analysis. The results show that the new ensemble model can reduce the prediction errors maximumly by 20.0% in mean of absolute error (MAE), 46.0% in mean of squared error (MSE), and 26.6% in root mean squared error (RMSE). A 5-fold cross validation verified that the new model is robust to the ED wait time prediction before and during the COVID-19 pandemic. We conclude that the new model provides an innovative approach to apply semantic analysis of natural language processing to the domain of time series prediction in the healthcare domain.

Vehicles with adaptive cruise control, i.e., SAE Levels 1 and 2 automated vehicles (AVs), have been operating on roads with a significant and rapidly growing penetration rate. Identifying these AVs is critical to understanding near-future mixed traffic characteristics and managing highway mobility and safety. This study identifies adaptive cruise control-equipped vehicles from human-driven vehicles (HVs) by constructing a set of learning-based models using car-following trajectories in a short time window. It is extendible to Level 3 and + AV identification when data is available. To compare model performance and draw physical insights, two physics-based models are proposed based on the premise that, in general, the car-following behavior of an AV is less volatile than an HV. Four car-following datasets, including AV makes from different manufacturers, are mixed to build a comprehensive identification model. Results show that physics-based approaches identify more than 80% AVs and 70% HVs. The identification accuracy of learning-based models is even higher. For example, the cluster-aware long short-term memory network identifies 98.79% of AVs and 95.45% of HVs. Learning-based identification models developed by this study can be integrated with the existing infrastructure (e.g., surveillance cameras), which have been used to extract car-following trajectories, to detect AVs in mixed traffic streams. This opens unparalleled data-driven opportunities to analyze and control mixed traffic to enhance safety (e.g., notifying surrounding traffic of the presence of AVs) and mobility (e.g., opening AV dedicated lanes when the percentage is great enough).

The severe pneumonia induced by the infection of the SARS-CoV-2 virus causes massive death in the ongoing COVID-19 pandemic. The early detection of the SARS-CoV-2 induced pneumonia relies on the unique patterns of the chest XRay images. Deep learning is a data-greedy algorithm to achieve high performance when adequately trained. A common challenge for machine learning in the medical domain is the accessibility to properly annotated data. In this study, we apply a conditional adversarial network (cGAN) to perform image to image (Pix2Pix) translation from the non-COVID-19 chest X-Ray domain to the COVID-19 chest X-Ray domain. The objective is to learn a mapping from the normal chest X-Ray visual patterns to the COVID-19 pneumonia chest X-ray patterns. The original dataset has a typical imbalanced issue because it contains only 219 COVID-19 positive images but has 1,341 images for normal chest X-Ray and 1,345 images for viral pneumonia. A U-Net based architecture is applied for the image-to-image translation to generate synthesized COVID-19 X-Ray chest images from the normal chest X-ray images. A 50-convolutional-layer residual net (ResNet) architecture is applied for the final classification task. After training the GAN model for 100 epochs, we use the GAN generator to translate 1,100 COVID-19 images from the normal X-Ray to form a balanced training dataset (3,762 images) for the classification task. The ResNet based classifier trained by the enhanced dataset achieves the classification accuracy of 97.8% compared to 96.1% in the transfer learning mode. When trained with the original imbalanced dataset, the model achieves an accuracy of 96.1% compared to 95.6% in the training from trainby-scratch model. In addition, the classifier trained by the enhanced dataset has more stable measures in precision, recall, and F1 scores across different image classes. We conclude that the GAN-based data enhancement strategy is applicable to most medical image pattern recognition tasks, and it provides an effective way to solve the common expertise dependence issue in the medical domain.

Patient entity recognition or patient entity extraction is to detect the relevant electronic health records (EHRs) across multiple data sources belonging to an identical patient, and to link the relevant data together. Patient entity recognition is a useful technology for cross-system electronic health data analysis to define commonality, to synthesize multiple data sources, and to reduce data redundancy. In this paper, we propose a deep learning solution, a sequential LSTM + Word Embedding network model (WE + LSTM) to filter and represent the non-structured electronic health records by measuring their context similarity and link them to the identical patient entities. The text context features are at first filtered by a trained bidirectional LSTM network to filter the irrelevant patient entities, and the related patient information context is estimated by a trained shallow word embedding network for its word vector similarity with the existing entities in the database. Finally, the new input patient data will be linked to the existing patient entity in the dataset with the greatest context similarity. Our hypothesis is that the records pointing to the identical patient have closest context similarity, so the patterns can be encoded by a trained word embedding network. An infection disease registration dataset (5304 patient entities) is used to evaluate the performance of the proposed WE+LSTM model. The classification accuracy is 0.837 and the F score is 0.843, which is the highest compared to the comparators including a single word embedding model, a random forest model, and a conventional neural network model. In addition, the WE + LSTM model has the greatest AUG area when the ROC of the four models are compared. This result indicates the proposed WE + LSTM model provides a feasible solution to correctly recognize the patient identities from electronic records by measure the text context similarity. It provides a solution for patient identity recognition through multi-source health big data integration, which is an urgent task for health big data projects.

Malaria is a major global health threat. The standard way of diagnosing malaria is by visually examining blood smears for parasite-infected red blood cells under the microscope by qualified technicians. This method is inefficient and the diagnosis depends on the experience and the knowledge of the person doing the examination. Automatic image recognition technologies based on machine learning have been applied to malaria blood smears for diagnosis before. However, the practical performance has not been sufficient so far. This study proposes a new and robust machine learning model based on a convolutional neural network (CNN) to automatically classify single cells in thin blood smears on standard microscope slides as either infected or uninfected. In a ten-fold cross-validation based on 27,578 single cell images, the average accuracy of our new 16-layer CNN model is 97.37%. A transfer learning model only achieves 91.99% on the same images. The CNN model shows superiority over the transfer learning model in all performance indicators such as sensitivity (96.99% vs 89.00%), specificity (97.75% vs 94.98%), precision (97.73% vs 95.12%), F1 score (97.36% vs 90.24%), and Matthews correlation coefficient (94.75% vs 85.25%).

The genetic polymorphism of Cytochrome P450 (CYP 450) is considered as one of the main causes for adverse drug reactions (ADRs). In order to explore the latent correlations between ADRs and the genetic polymorphism, a new model is proposed in which both the inputs of the genetic locuses (i.e.CYP2D6*2, CYP2D6*10, CYP2D6*14, CYP1A2*1C and CYP1A2*1F) and occurrence as probabilistic distribution. A generative model is proposed to describe the joint distributions of occurrence of ADRs and the diversity of genetic sub-types of the input variables. The new algorithm is developed based on Generative Stochastic Networks (GSN) model. A Markov chain from a training data set is applied for the learning as a transition operator to simulate a probabilistic distribution. The transition distribution is conditional on the previous step of the chain thus it is able to perform learning at a much lower cost than the conventional maximal likelihood method. The experiment results show that the newly algorithm is more effective than the available conventional methods.

Bell's palsy is nonspecific inflammation stylomastoid foramen caused by facial nerve. This is a common disease of self limiting, non progressive. The incidence rate of about 30/100000[1], clinical manifestations include dry eyes, dry mouth, and taste disorders or loss, Hyperacusis, incomplete eyelid closure, numbness of the mouth droop[2, 3]. Risk of ear and facial pain is rare[4, 5]. The prognosis is good, there is some 70% with or without treatment within six months to fully recover. But still some 30% in patients with Bell paralysis sequela and residual facial paralysis (29%), contractures (17%), and hemifacial spasm or associated with sports (16%)[1]. The use of traditional Chinese medicine and acupuncturetherapy is effective, but the clinical study of Zhao's thunder fire moxibustion treatment of Bell palsy is lack of evidence. In this study, Zhao's thunder fire moxibustion cure coldBell's palsy, observation of clinical efficacy, and explore the possible mechanism of its effect.

Migraine, one type of common headache, has gradually increased incidence rate, whose pathogenesis is not clearly understood, and no special medicine treatment. This article discussed migraine treatment in terms of its channel feature, applied acupuncture integrated with Chinese traditional medicine together and investigated the mechanism synergy effects from the aspects of excess ache, deficient ache and deficiency-excess complex ache. Finally, put forward the resent research progresses on the treatment of acupuncture integrated with Chinese traditional medicine.

Facial paralysis is the mouth, eyes to the side of the skew disorder as the main performance, also known as the deviation of mouth and eye, peripheral nerve paralysis of the facial nerve is equivalent to western medicine. Acupuncture treatment of facial paralysis has a very big advantage, acupuncture and moxibustion combined with acupoint injection for treatment of peripheral facial paralysis can significantly improve the clinical efficacy, shorten the course of treatment, is attracting more and more attention. Now the author summarize it that "acupuncture combined with acupoint injection for treatment of peripheral facial paralysis"for nearly 15 years from the VIP (Chinese Journal Database).

The combination of acupuncture with Chinese medicine has a long history. Both acupuncture and Chinese medicine have their own advantages, the combination of acupuncture with Chinese medicine thought is to combine the two, to play a more comprehensive effect. Combination of acupuncture with Chinese medicine thought can be applied to a variety of clinical disease. In our study, some cases are cited to describe the advantages of combination of acupuncture with Chinese medicine.

Computer aid technology is widely applied in decision-making and outcome assessment of healthcare delivery, in which modeling knowledge and expert experience is technically important. However, the conventional rule-based models are incapable of capturing the underlying knowledge because they are incapable of simulating the complexity of human brains and highly rely on feature representation of problem domains. Thus we attempt to apply a deep model to overcome this weakness. The deep model can simulate the thinking procedure of human and combine feature representation and learning in a unified model. A modified version of convolutional deep belief networks is used as an effective training method for large-scale data sets. Then it is tested by two instances: a dataset on hypertension retrieved from a HIS system, and a dataset on Chinese medical diagnosis and treatment prescription from a manual converted electronic medical record (EMR) database. The experimental results indicate that the proposed deep model is able to reveal previously unknown concepts and performs much better than the conventional shallow models.

To introduce the epidemiology and pathogenesis of knee osteoarthritis, review the literature from home and abroad and introduce the research progress of osteoarthritis of the knee. Represent the treatment methods and mechanism of knee osteoarthritis by the needle-medicine of mutual reinforcement of school. The academic thoughts of needle-medicine of mutual reinforcement can be traced to the same origin of traditional medicine on treatment of stasis. Its operation is simple, fewer adverse events, patient compliance is high, it easy to spread.

Medicinal vesiculation therapy has a long history, dating back to the warring States era. Along with the change of dynasties, medicinal vesiculation therapy continues to develop and extensive use, especially in the South of the present, it is favorable for a universal therapy. Now researching literatures on the clinical application, analysis medicinal vesiculation therapy in nearly 4 years, for the improvement and promotion of medicinal vesiculation therapy further development for reference.

Cloud computing, as a new system and architecture of data mutual sharing, is composed of three service models i.e. cloud software as a service (SaaS), cloud platform as a service (PaaS) and cloud infrastructure as a service (IaaS), as well as including three key enabling technologies i.e. networks of fast wide-area, server computers of powerful and inexpensive specialty, and commodity hardware of high-performance virtualization. Cloud computing technology brings in innovative and constructive ideas for the medical and health informatization. However, it also challenges many traditional approaches to application design and management of medical-sanitary institutions or other datacenters, especially the relevant issues of security, interoperability, portability, et al. that cited as major barriers to broader adoption. Based on the concept, key technology, core problem and principles, the author attempts to discuss the main issues of cloud computing in the construction and development of the medical and health informatization. We hope these considerations can provide reference to the service for the present medical informatization construction and practical decision-making in the context of big data.

Objective: To review the effectiveness and safety of stroke unit of integrative medicine for post stroke comorbid anxiety and depression (PSCAD) systematically. Methods: Electronic databases of MEDLINE, Chinese Biomedical Literature Database, VIP Database, Wan-fang Database, CNKI Database were handled by computer retrieval, and Journal of Traditional Chinese Medicine were manually searched for papers of randomized controlled trial (RCT) on Chinese herbal medicine (CHM) plus pharmacotherapy versus pharmacotherapy in treating PSCAD. In accordance with the inclusion criteria, two reviewers independently screened the related literatures, assessed the risk of bias and extracted the literature data, while the software of RevMan5.2.6 was used for the combining data analysis. Results: A total of 25 studies involving 2,044 patients were identified for this review. Meta-analysis results indicated that the integrative group i.e. CHM plus pharmacotherapy group showed more effective for PSCAD (OR=3.63, 95%CI (2.67, 4.95)), lower HAMD (Hamilton depression scale) score (WMD=-3.84, 95%CI (-4.66, -3.02)), and less adverse events (OR=0.71, 95%CI (0.51, 0.97)) compared with the control group i.e. routine pharmacotherapy group. Conclusion: The meta-analysis indicated that the integrative medicine treatment could be more helpful in strengthening the clinical efficacy and reducing the incidence of adverse events in the treatment of PSCAD compared with routine pharmacotherapy. However, due to the small sample size of included trials and the relatively low-rating quality in the majority of studies, further large-scale, multi-center and rigorously-designed trials should be required to confirm the effectiveness and safety of integrative medicine for PSCAD.

A novel algorithm that combines LASSO regression and decision tree is proposed to explore the correlation of adverse events (AE) and genetic polymorphism of CYP2D6*2, *10, *14, CYP1A2*1C, *1F in human subjects in a clinical trial. The genotypes of 30 healthy human subjects in a clinical trial for a natural herbal drug and 53 subjects in the blank group were detected by polymerase chain reaction (PCR) and DNA sequencing. The AEs occurring during the trial were recorded. The correlations of AE and genetic polymorphism are analyzed by the new combined algorithm. 53 AEs are reported in the end of the study. Five gene subtypes are selected as correlative factors to the specific AEs by the new algorithm: wild type of CYP1A2*1F and abnormal platelet counting, homozygous CYP1A2*1C and abnormal fibrinogen, heterozygous CYP1A2*1C and abnormal blood chlorine, heterozygous CYP1A2*1C and abnormal urobilinogen, wild type of CYP2D6*2 and abnormal APTT (activated partial thromboplastin time). The result indicates the novel algorithm is effective and is able to detect the correlation of AEs and genetic polymorphism in clinical trials.

Traditional Chinese medicines (CM) topical herbs for atopic dermatitis are mainly consist of nourishing the blood, dryness-moistening, dry-dampness, skin-moisturizing and itching-relief, of which therapeutic principles are taken as dryness-moistening to relieve itching. Based on the modified mutual information, complex system entropy cluster and unsupervised hierarchical clustering, the CM recipes for atopic dermatitis can be better collected and stored in the database, and the correlation coefficient between herbs, core combinations of herbs and new recipes also can be analyzed. In our study, the objective is to evaluate and analyze the component law of CM topical herbs and explore new recipes for atopic dermatitis through data mining methods so as to provide references for dermatologists in the clinical practice and decision-making for the treatment of atopic dermatitis.

English translation of Chinese pediatrie points is a long neglected field in all kinds of TCM nomenclatures and dictionaries. However, the authors believe it is necessary to include it in the future international standardized TCM nomenclatures or dictionaries in three aspects and the principles and protocol of its English translation are thus proposed.

This paper firstly define the concept of Combined Acupuncture with medicine, to explore the theoretical basis of acupuncture and drugs, Analyzed from the following aspects: comparative analysis of the advantages and disadvantages of acupuncture and Chinese Medicine, the way and method of combination, he current research progress, study on the mechanism of acupuncture combined with medicine. The objective is to grasp the characteristics and advantages of treatment of the acupuncture and Chinese herbal medicine, to explore organic combination of the two modes of treatment, to find the optimal treatment plan, summary of the law of combination of acupuncture and medicine clinical application. Give full play to the advantages of acupuncture and medicine complementary.

Insomnia is common psychophysiogical disorder, characterized by sleeping difficultly or lightly, restless sleep and early awakening, usually with a series of disease, such as neurasthenia, anxiety, depression and so on. Nowadays acupuncture is a complementary therapy for insomnia which is regarded as one of most effective, widely used and well-accepted method. However, acupuncture is usually used independently. In this paper, we present a research protocol designed for a parallel, randomized, controlled trial to evaluate the effect of the acupoint injection combined with acupuncture treatment for insomnia with cardiac-splenic asthenia. In our study, the objective is to evaluate the clinical effect of the acupoint injection combined with acupuncture treatment compared with the acupuncture used independently.

To explore the difference in treatment thoughts and therapy method between traditional acupuncture combines with herbal medicine and the needle-medicine of mutual reinforcement school in the treatment of tinnitus and deafness. Firstly, studied to the ancient cultural heritage and research, in order to understand the application of traditional acupuncture combines with herbal medicine. Secondly, to descry the needle-medicine of mutual reinforcement school in Guangdong Provincial Hospital of Chinese Medicine, base on the cure of tinnitus and deafness, to make a comparison with traditional acupuncture combines with herbal medicine. The needle-medicine of mutual reinforcement school in Guangdong Provincial Hospital of Chinese Medicine carries on the traditional Chinese medicines theory and traditional innovation, even has better clinical operability, strengthens the patients' compliance, lightens the patients' home burden, is the one can continuously inherit and develop the traditional Chinese medicine.

The concept and methodology of evidence-based medicine (EBM) and the strategy to promote efficacy of acupuncture in clinical practice are introduced in this paper. Then it focuses on using the data mining approaches to integrate the primary evidence from real practice based on conventional clinical data and secondary evidence by systematic literature review or Meta-analysis. The new analytic method is capable of explore in-depth on the latent rules and relations of acupuncture and Chinese medicine versus the effectiveness in real practice. A data warehouse is recommended to be set up to store and manage the above evidence processed by appropriate data mining algorithms and models. As the data from different origins is hopefully to be integrated in a clinical decision support system, it will be able to provide evidence-based references and recommendations for the clinical practice of acupuncture and Chinese medicine.

Cervical spondylosis (CS) is a disease caused by nonspecific degenerative disorders, therefore it requires high demands for diagnosis due to its diversity and complexity. Patient-reported outcomes (PRO) assessment techniques are on the foundation of psychometrics, which obtain patients' own feelings about daily life, health, subjective satisfaction with treatment and other aspects of personal experience through interviews, questionnaires and other forms of self-assessment. This paper explores the applicability of patient-reported outcomes for clinical evaluation of therapeutic effect of acupuncture for CS and attempts to establish a clinical outcome evaluation model consequently. We introduce SF-36 life quality questionnaire as the main index and visual analogue scale (VAS) as reference index, observe 162 cases as experimental data from a multi-center randomized controlled trial (RCT) on acupuncture for neck pain caused by cervical spondylosis, among others, 150 cases finished the whole course. During the initial phases of study, to verify whether PRO technique is suitable to evaluate the effect of acupuncture for CS, we apply some statistical methods in reliability analysis, validity analysis and responsiveness analysis at different measure times, that is, pre-treatment, post-treatment and during follow-up. The results of reliability analysis show that the Cronbach's statistic alpha of whole scale is 0.834 and that of the standardized items is 0.872. The results of validity analysis shows that 8 common factors selected from SF-36 have an accumulative variance contribution rate of 75.621%, which are represented as physical function (PF), role-physical (RP), general health (GH), mental health (MH), vitality (VT), role-emotion (RE), bodily pain (BP), and society function (SF) respectively. The results of the responsiveness analysis show that except mental health, SF-36 scores at the end of treatment, one month and 3 months after the follow-up differed from those before treatment (P<;0.05). In the further study, we employ three-layer, feed forward neural networks with a back propagation algorithm for the evaluation of acupuncture for CS on the basis of features that were extracted from SF-36. Consequently, the comprehensive assessment model for therapeutic effect of acupuncture for CS based on ANN has good performance with learning precision 96.88%. In general, the experimental results indicate that the PRO techniques have good applicability to the evaluation of therapeutic effect of acupuncture for CS and artificial neural network can offer a feasible approach to the comprehensive assessment as well.

The intervention of traditional Chinese medicine always focus on two highlight aspects: one is the ZHENG (syndrome) differentiation and treatment, the other is the concept of holism. By the process of fully collecting clinical data, establishing data warehouse and model, making the best of mathematical statistics, data mining, etc., the Chinese medicine (CM) clinical auxiliary decision towards the patients can be better maintained, promoted and accomplished, which can help the construction of clinical decision support system (CDSS), the improvement of clinical efficacy and the inheritance of CM knowledge. In this paper, the author went over the traits of CM clinical experiences based on the clinical decision support thoughts, and then attempted to summarize an architecture approach to syndrome differentiation of information technology, so as to serve as reference for the practice of CM standardization.

As a significant complement for skin surface images, skin biopsy image may reveal causes and severity of many skin diseases, especially in the case of skin cancer inspection. With rapid increment of skin disease patients, computational methods have been introduced for automatic classification of skin images. However, due to the complex relationship among annotation terms and features of local regions, it becomes a great challenge for skin biopsy image feature recognition and annotation. In this paper, we attempt to model the potential knowledge and experience of doctors on skin biopsy image annotation by using a recent proposed machine learning model, named multi-instance multi-label (MIML) model. We show that the relationship among annotation terms and skin biopsy images is naturally consistent with the MIML framework. We further propose a sparse Bayesian MIML algorithm which can produce a probability indicating the confidence of annotating a term. The proposed algorithm framework is evaluated on a real dataset from a large local hospital containing 12,700 skin biopsy images. The results show that the proposed algorithm is effective and prominent.

An expert consensus survey based on electronic communication of Delphi method is conducted to develop the TCM clinical pathway for acute ischemie stroke. An initial protocol of the clinical pathway is developed based on literature survey and by an internal panel of experts, which forms the basis of the questionnaire of the Delphi survey. The content of the initial questionnaire is classified into two aspects. A national expert panel is called up for the expert consensus by the e-Delphi method. 100% of the panel members replied in the first round, and only 3 members missed in the second round. The total authority coefficient (Cr) is 0.84 and the Kendall's W for coordination is kept below 0.5 in all domains. In conclusion, we believe the finalized version of the clinical pathway developed by Delphi method in the study is reliable and feasible for the clinical TCM and IM management of acute ischemie stroke.

In this paper, a multi-instance learning framework is introduced to solve the problem of skin biopsy image features recognition. Previously reported methods for skin surface images were mostly based on color features extraction. They are incapable to be directly applied to skin biopsy image features recognition because biopsy images are often dyed and have obvious inner structures with different textures. Therefore, we regard skin biopsy images as multi-instance samples, whose instances are regions or structures captured by applying Normalized Cut. Texture feature extraction methods are used to express each region as a vectorial expression. Then two multi-instance learning algorithms reported successful in various image retrieval tasks were applied. Nine features were manually selected as target features to evaluate the proposed method on a skin disease diagnosis datasets of 6579 biopsy images from 2010 to 2011. The result showed that the proposed method is effective and medically acceptable.

Recent years have witnessed an increasing threat from kernel rootkits. A common feature of such attack is hiding malicious objects to conceal their presence, including processes, sockets, and kernel modules. Scanning memory with object signatures to detect the stealthy rootkit has been proven to be a powerful approach only when it is hard for adversaries to evade. However, it is difficult, if not impossible, to select fields from a single data structure as robust signatures with traditional techniques. In this paper, we propose the concepts of inter-structure signature and imported signature, and present techniques to detect stealthy malware based on these concepts. The key idea is to use cross-reference relationships of multiple data structures as signatures to detect stealthy malware, and to import some extra information into regions attached to target data structures as signatures. We have inferred four invariants as signatures to detect hidden processes, sockets, and kernel modules in Linux respectively and implemented a prototype detection system called DeepScanner. Meanwhile, we have also developed a hypervisor-based monitor to protect imported signatures. Our experimental result shows that our DeepScanner can effectively and efficiently detect stealthy objects hidden by seven real-world rootkits without any false positives and false negatives, and an adversary can hardly evade DeepScanner if he/she does not break the normal functions of target objects and the system.

Implementing runtime integrity measurement in an acceptable way is a big challenge. We tackle this challenge by developing a framework called Patos. This paper discusses the design and implementation concepts of our operating system mechanisms for runtime process integrity measurement, which is an important part of the Patos framework and is named Patos-RIP. Patos-RIP is developed into the main-stream Linux operating system and utilizes TPM as hardware support for tamper-resistance. From the beginning a process is created to the moment the process dies, Patos-RIP conducts integrity measurement at appropriate points of time when the process runs, so as to ensure that the integrity of a process is not compromised during its whole lifetime. This way, Patos-RIP can improve trustworthiness of processes by effectively detecting runtime tampering attacks on processes' integrity.