Electrocardiogram (ECG) interpretation using deep learning has shown promising results in detecting cardiac rhythm abnormalities. However, growing evidence suggests that model performance can vary significantly across demographic subgroups, raising concerns about algorithmic fairness in clinical deployment. In this study, we explore whether incorporating protected variables—specifically age and sex—into multimodal contrastive pretraining can reduce downstream performance disparities. We use a CLIP-style architecture to align ECG signals with machine-generated rhythm descriptions, training two variants: one with text alone and one with demographic augmentation. After pretraining, we evaluate frozen ECG embeddings using linear probing on a binary classification task distinguishing normal from abnormal rhythms. Our results show that including demographic information during pretraining can reduce performance gaps across age groups and maintains comparable or improved accuracy across sex. These findings highlight the potential of fairness-aware representation learning to improve subgroup equity in clinical machine learning applications.

We propose an approach to estimate the macronu-trients in a meal automatically by analyzing the meal's glucose response using off-the-shelf wearable sensors (continuous glucose monitors). We rely on the fact that the shape of the glucose response to a meal depends on all the macronutrients in the meal, not just its carbohydrates (carbs). However, protein, fat, and fiber tend to affect the glucose response in similar ways, so recovering their individual amounts is numerically ill-conditioned. To address this problem, our approach compresses macronutrients into a latent variable that captures their correlated effects on glucose. Then, we train a machine learning model to predict the latent variable from the glucose response of a meal. Finally, we recover the amount of the original macronutrients by incorporating prior knowledge of how they co-occur in conventional meals. Using experimental data from 45 participants, we show that predicting carbs indirectly (through the latent variable) reduces the prediction error when compared to predicting carbs directly, i.e., without considering the protein and fats in the meal.

OBJECTIVE: Artificial intelligence (AI) detects heart disease from images of electrocardiograms (ECGs). However, traditional supervised learning is limited by the need for large amounts of labeled data. We report the development of Biometric Contrastive Learning (BCL), a self-supervised pretraining approach for label-efficient deep learning on ECG images. MATERIALS AND METHODS: Using pairs of ECGs from 78 288 individuals from Yale (2000-2015), we trained a convolutional neural network to identify temporally separated ECG pairs that varied in layouts from the same patient. We fine-tuned BCL-pretrained models to detect atrial fibrillation (AF), gender, and LVEF < 40%, using ECGs from 2015 to 2021. We externally tested the models in cohorts from Germany and the United States. We compared BCL with ImageNet initialization and general-purpose self-supervised contrastive learning for images (simCLR). RESULTS: While with 100% labeled training data, BCL performed similarly to other approaches for detecting AF/Gender/LVEF < 40% with an AUROC of 0.98/0.90/0.90 in the held-out test sets, it consistently outperformed other methods with smaller proportions of labeled data, reaching equivalent performance at 50% of data. With 0.1% data, BCL achieved AUROC of 0.88/0.79/0.75, compared with 0.51/0.52/0.60 (ImageNet) and 0.61/0.53/0.49 (simCLR). In external validation, BCL outperformed other methods even at 100% labeled training data, with an AUROC of 0.88/0.88 for Gender and LVEF < 40% compared with 0.83/0.83 (ImageNet) and 0.84/0.83 (simCLR). DISCUSSION AND CONCLUSION: A pretraining strategy that leverages biometric signatures of different ECGs from the same patient enhances the efficiency of developing AI models for ECG images. This represents a major advance in detecting disorders from ECG images with limited labeled data.

Accurate estimation of physiological biomarkers using raw waveform data from non-invasive wearable devices requires extensive data preprocessing. An automatic noise detection method in time-series data would offer significant utility for various domains. As data labeling is onerous, having a minimally supervised abnormality detection method for input data, as well as an estimation of the severity of the signal corruptness, is essential. We propose a model-free, time-series biomedical waveform noise detection framework using a Variational Autoencoder coupled with Gaussian Mixture Models, which can detect a range of waveform abnormalities without annotation, providing a confidence metric for each segment. Our technique operates on biomedical signals that exhibit periodicity of heart activities. This framework can be applied to any machine learning or deep learning model as an initial signal validator component. Moreover, the confidence score generated by the proposed framework can be incorporated into different models' optimization to construct confidence-aware modeling. We conduct experiments using dynamic time warping (DTW) distance of segments to validated cardiac cycle morphology. The result confirms that our approach removes noisy cardiac cycles and the remaining signals, classified as clean, exhibit a 59.92% reduction in the standard deviation of DTW distances. Using a dataset of bio-impedance data of 97885 cardiac cycles, we further demonstrate a significant improvement in the downstream task of cuffless blood pressure estimation, with an average reduction of 2.67 mmHg root mean square error (RMSE) of Diastolic Blood pressure and 2.13 mmHg RMSE of systolic blood pressure, with increases of average Pearson correlation of 0.28 and 0.08, with a statistically significant improvement of signal-to-noise ratio respectively in the presence of different synthetic noise sources. This enables burden-free validation of wearable sensor data for downstream biomedical applications.

The timing, intensity, and duration of postprandial exercise are important factors that reduce glucose excursions. When exercise is of moderate intensity, performed between 25 and 55 minutes after a meal, it results in greater attenuation of glucose. However, the potential glucose reduction for shorter-duration, non-exercise activity thermogenesis (NEAT) (such as activities of daily living) may also be beneficial, particularly in cases where exercise is neither feasible nor prudent. Therefore, we designed a system to capture blood glucose and activity intensity through internet of medical things devices and modeled the impact of the timing and duration of NEAT on peak glucose. This work designed a linear mixed effects model to evaluate the impact of NEAT on peak, postprandial glucose in a study of data captured on varied participants with or without diabetes. We found at least 25 minutes of NEAT starting 30 minutes after the meal most effectively reduced peak post-prandial glucose.Clinical Relevance— This work establishes the impact of NEAT on reducing post-prandial peak glucose in free-living environments as another method of controlling glucose surges

Hypertension is a prevalent risk factor for cardiovascular disease and premature mortality. Telemonitoring can be used to provide a communication pipeline between patients and clinicians for diagnosing hypertension and staging early intervention. However, it takes healthcare resources to monitor patients and identify patients at risk of experiencing a hypertensive event. To reduce the burden on the health care system, we present an automated early warning system to predict patients at risk of a hypertensive event. We first construct a fusion model that utilizes a dual stage attention mechanism to determine whether a hypertensive event occurs in the next seven days and compare its performance to XGBoost and logistic regression. Then, we measure its performance in an early warning system to determine whether it can detect the onset of the first hypertensive event for each patient. With the best threshold, the early warning system using this model has an F1 score of 0.61.

Electronic Health Record (EHR) data provide a tremendous opportunity for enhancing the quality of care by delivering personalized treatments [1]. EHR data are rich and tracked at high frequency over time, and can be integrated into a real-time, continuous warning system. One problem that can benefit from real-time monitoring of EHR is the occurrence of invasive-ventilation (iV) for Intensive Care Unit (ICU) patients. The prognostication of a future event falls in the domain of survival analysis. However, iV can occur multiple times during an ICU stay, while most survival analysis tools work only with non-recurring events. Moreover, most survival analysis models are restricted to time-static data, while EHR data changes over time, e.g. heart rate. Therefore, to model the iV problem we turn to BoXHED2.0 [2], a fully nonparametric survival machine learning method that is grounded in theory [3]. Importantly, BoXHED2.0 can handle recurring events data with time-dependent covariates, and we apply it to the MIMIC IV data set [4] to develop a real-time ICU iV warning indicator. Our ICU iV model achieves an AUCPR of 0.34 (versus 0.13 for the benchmarks) and an AUROC of 0.85 (versus 0.73 for the benchmarks) out of sample, speaking to its effectiveness in real-time risk monitoring.

Observational medical data present unique opportunities for analysis of medical outcomes and treatment decision making. However, because these datasets do not contain the strict pairing of randomized control trials, matching techniques are to draw comparisons among patients. A key limitation to such techniques is verification that the variables used to model treatment decision making are also relevant in identifying the risk of major adverse events. This article explores a deep mixture of experts approach to jointly learn how to match patients and model the risk of major adverse events in patients. Although trained with information regarding treatment and outcomes, after training, the proposed model is decomposable into a network that clusters patients into phenotypes from information available before treatment. This model is validated on a dataset of patients with acute myocardial infarction complicated by cardiogenic shock. The mixture of experts approach can predict the outcome of mortality with an area under the receiver operating characteristic curve of 0.85 ± 0.01 while jointly discovering five potential phenotypes of interest. The technique and interpretation allow for identifying clinically relevant phenotypes that may be used both for outcomes modeling as well as potentially evaluating individualized treatment effects.

OBJECTIVE: Nonexercise algorithms are cost-effective methods to estimate cardiorespiratory fitness (CRF), but the existing models have limitations in generalizability and predictive power. This study aims to improve the nonexercise algorithms using machine learning (ML) methods and data from US national population surveys. MATERIALS AND METHODS: We used the 1999-2004 data from the National Health and Nutrition Examination Survey (NHANES). Maximal oxygen uptake (VO2 max), measured through a submaximal exercise test, served as the gold standard measure for CRF in this study. We applied multiple ML algorithms to build 2 models: a parsimonious model using commonly available interview and examination data, and an extended model additionally incorporating variables from Dual-Energy X-ray Absorptiometry (DEXA) and standard laboratory tests in clinical practice. Key predictors were identified using Shapley additive explanation (SHAP). RESULTS: Among the 5668 NHANES participants in the study population, 49.9% were women and the mean (SD) age was 32.5 years (10.0). The light gradient boosting machine (LightGBM) had the best performance across multiple types of supervised ML algorithms. Compared with the best existing nonexercise algorithms that could be applied to the NHANES, the parsimonious LightGBM model (RMSE: 8.51 ml/kg/min [95% CI: 7.73-9.33]) and the extended LightGBM model (RMSE: 8.26 ml/kg/min [95% CI: 7.44-9.09]) significantly reduced the error by 15% and 12% (P < .001 for both), respectively. DISCUSSION: The integration of ML and national data source presents a novel approach for estimating cardiovascular fitness. This method provides valuable insights for cardiovascular disease risk classification and clinical decision-making, ultimately leading to improved health outcomes. CONCLUSION: Our nonexercise models provide improved accuracy in estimating VO2 max within NHANES data as compared to existing nonexercise algorithms.

We propose our Confidence-Aware Particle Filter (CAPF) framework that analyzes a series of estimated changes in blood pressure (BP) to provide several true state hypotheses for a given instance. Particularly, our novel confidence-awareness mechanism assigns likelihood scores to each hypothesis in an effort to discard potentially erroneous measurements - based on the agreement amongst a series of estimated changes and the physiological plausibility when considering DBP/SBP pairs. The particle filter formulation (or sequential Monte Carlo method) can jointly consider the hypotheses and their probabilities over time to provide a stable trend of estimated BP measurements. In this study, we evaluate BP trend estimation from an emerging bio-impedance (Bio-Z) prototype wearable modality although it is applicable to all types of physiological modalities. Each subject in the evaluation cohort underwent a hand-gripper exercise, a cold pressor test, and a recovery state to increase the variation to the captured BP ranges. Experiments show that CAPF yields superior continuous pulse pressure (PP), diastolic blood pressure (DBP), and systolic blood pressure (SBP) estimation performance compared to ten baseline approaches. Furthermore, CAPF performs on track to comply with AAMI and BHS standards for achieving a performance classification of Grade A, with mean error accuracies of -0.16 ± 3.75 mmHg for PP (r = 0.81), 0.42 ± 4.39 mmHg for DBP (r = 0.92), and -0.09 ± 6.51 mmHg for SBP (r = 0.92) from more than test 3500 data points.

In many machine learning tasks, input features with varying degrees of predictive capability are acquired at varying costs. In order to optimize the performance-cost trade-off, one would select features to observe a priori. However, given the changing context with previous observations, the subset of predictive features to select may change dynamically. Therefore, we face the challenging new problem of foresight dynamic selection (FDS): finding a dynamic and light-weight policy to decide which features to observe next, before actually observing them, for overall performance-cost trade-offs. To tackle FDS, this paper proposes a Bayesian learning framework of Variational Foresight Dynamic Selection (VFDS). VFDS learns a policy that selects the next feature subset to observe, by optimizing a variational Bayesian objective that characterizes the trade-off between model performance and feature cost. At its core is an implicit variational distribution on binary gates that are dependent on previous observations, which will select the next subset of features to observe. We apply VFDS on the Human Activity Recognition (HAR) task where the performance-cost trade-off is critical in its practice. Extensive results demonstrate that VFDS selects different features under changing contexts, notably saving sensory costs while maintaining or improving the HAR accuracy. Moreover, the features that VFDS dynamically select are shown to be interpretable and associated with the different activity types. We will release the code.

In wearable sensing applications, data is inevitable to be irregularly sampled or partially missing, which pose challenges for any downstream application. An unique aspect of wearable data is that it is time-series data and each channel can be correlated to another one, such as x, y, z axis of accelerometer. We argue that traditional methods have rarely made use of both times-series dynamics of the data as well as the relatedness of the features from different sensors. We propose a model, termed as DynImp, to handle different time point’s missingness with nearest neighbors along feature axis and then feeding the data into a LSTM-based denoising autoen-coder which can reconstruct missingness along the time axis. We experiment the model on the extreme missingness scenario (> 50% missing rate) which has not been widely tested in wearable data. Our experiments on activity recognition show that the method can exploit the multi-modality features from related sensors and also learn from history time-series dynamics to reconstruct the data under extreme missingness.

Continual Learning (CL) is the problem of sequentially learning a set of tasks and preserving all the knowledge acquired. Many existing methods assume that the data stream is explicitly divided into a sequence of known contexts (tasks), and use this information to know when to transfer knowledge from one context to another. Unfortunately, many real-world CL scenarios have no clear task nor context boundaries, motivating the study of task-agnostic CL, where neither the specific tasks nor their switches are known both in training and testing. This paper proposes a variational architecture growing framework dubbed VariGrow. By interpreting dynamically growing neural networks as a Bayesian approximation, and defining flexible implicit variational distributions, VariGrow detects if a new task is arriving through an energy-based novelty score. If the novelty score is high and the sample is “detected" as a new task, VariGrow will grow a new expert module to be responsible for it. Otherwise, the sample will be assigned to one of the existing experts who is most “familiar" with it (i.e., one with the lowest novelty score). We have tested VariGrow on several CIFAR and ImageNet-based benchmarks for the strict task-agnostic CL setting and demonstrate its consistent superior performance. Perhaps surprisingly, its performance can even be competitive compared to task-aware methods.

Students' attention and retention to the course videos is crucial for asynchronous classes. This poster reports our pilot study on evaluating the effectiveness of using short animation videos as the replacement of regular lecture recordings to improve students' engagement in an asynchronous undergraduate-level machine learning class. We showed that while short animation videos can help students quickly grasp core ideas and visually memorize concepts, various improvements can still be made to make the video more capable of explaining complex details, thus additional work need to be done before it can be used as a replacement of regular recordings. We pointed out future direction of studying key factors that improve effective explanation of detailed materials, and how short animation videos can be jointly used with other content as a more effective method for asynchronous teaching.

Diet monitoring is an essential intervention component for a number of diseases, from type 2 diabetes to cardiovascular diseases. However, current methods for diet monitoring are burdensome and often inaccurate. In prior work, we showed that continuous glucose monitors (CGMs) may be used to predict meal macronutrients (e.g., carbohydrates, protein, fat) by analyzing the shape of the post-prandial glucose response. In this study, we examine a number of additional dietary biomarkers in blood by their ability to improve macronutrient prediction, compared to using CGMs alone. For this purpose, we conducted a nutritional study where (n = 10) participants consumed nine different mixed meals with varied but known macronutrient amounts, and we analyzed the concentration of 33 dietary biomarkers (including amino acids, insulin, triglycerides, and glucose) at various times post-prandially. Then, we built machine learning models to predict macronutrient amounts from (1) individual biomarkers and (2) their combinations. We find that the additional blood biomarkers provide complementary information, and more importantly, achieve lower normalized root mean squared error (NRMSE) for the three macronutrients (carbohydrates: 22.9%; protein: 23.4%; fat: 32.3%) than CGMs alone (carbohydrates: 28.9%, t(18) =1.64, p =0.060; protein: 46.4%, t(18) =5.38, p 0.001; fat: 40.0%, t(18) =2.09, p =0.025). Our main conclusion is that augmenting CGMs to measure these additional dietary biomarkers improves macronutrient prediction performance, and may ultimately lead to the development of automated methods to monitor nutritional intake. This work is significant to biomedical research as it provides a potential solution to the long-standing problem of diet monitoring, facilitating new interventions for a number of diseases.

Estimating physiological parameters - such as blood pressure (BP) - from raw sensor data captured by noninvasive, wearable devices rely on either burdensome manual feature extraction designed by domain experts to identify key waveform characteristics and phases, or deep learning (DL) models that require extensive data collection. We propose the Data-Driven Guided Attention (DDGA) framework to optimize DL models to learn features supported by the underlying physiology and physics of the captured waveforms, with minimal expert annotation. With only a single template waveform cardiac cycle and its labelled fiducial points, we leverage dynamic time warping (DTW) to annotate all other training samples. DL models are trained to first identify them before estimating BP to inform them which regions of the input represent key phases of the cardiac cycle, yet we still grant the flexibility for DL to determine the optimal feature set from them. In this study, we evaluate DDGA's improvements to a BP estimation task for three prominent DL-based architectures with two datasets: 1) the MIMIC-III waveform dataset with ample training data and 2) a bio-impedance (Bio-Z) dataset with less than abundant training data. Experiments show that DDGA improves personalized BP estimation models by an average 8.14% in root mean square error (RMSE) when there is an imbalanced distribution of target values in a training set and improves model generalizability by an average 4.92% in RMSE when testing estimation of BP value ranges not previously seen in training.

Measuring dietary intake is a major challenge in the management of chronic diseases. Current methods rely on self-report measures, which are cumbersome to obtain and often unreliable. This article presents an approach to estimate dietary intake automatically by analyzing the post-prandial glucose response (PPGR) of a meal, as measured with continuous glucose monitors. In particular, we propose a sparse-coding technique that can be used to estimate the amounts of macronutrients (carbohydrates, protein, fat) in a meal from the meal’s PPGR. We use Lasso regularization to represent the PPGR of a new meal as a sparse combination of PPGRs in a dictionary, then combine the sparse weights with the macronutrient amounts in the dictionary’s meals to estimate the macronutrients in the new meal. We evaluate the approach on a dataset containing nine standardized meals and their corresponding PPGRs, consumed by fifteen participants. The proposed technique consistently outperforms two baseline systems based on ridge regression and nearest-neighbors, in terms of correlation and normalized root mean square error of the predictions.

Diet monitoring is an important component of interventions in type 2 diabetes, but is time intensive and often inaccurate. To address this issue, we describe an approach to monitor diet automatically, by analyzing fluctuations in glucose after a meal is consumed. In particular, we evaluate three standardization techniques (baseline correction, feature normalization, and model personalization) that can be used to compensate for the large individual differences that exist in food metabolism. Then, we build machine learning models to predict the amounts of macronutrients in a meal from the associated glucose responses. We evaluate the approach on a dataset containing glucose responses for 15 participants who consumed 9 meals. Three techniques improve the accuracy of the models: subtracting the baseline glucose, performing z-score normalization, and scaling the amount of macronutrients by each individuals’ body mass index.

The recent breakthrough achieved by contrastive learning accelerates the pace for deploying unsupervised training on real-world data applications. However, unlabeled data in reality is commonly imbalanced and shows a long-tail distribution, and it is unclear how robustly the latest contrastive learning methods could perform in the practical scenario. This paper proposes to explicitly tackle this challenge, via a principled framework called Self-Damaging Contrastive Learning (SDCLR), to automatically balance the representation learning without knowing the classes. Our main inspiration is drawn from the recent finding that deep models have difficult-to-memorize samples, and those may be exposed through network pruning. It is further natural to hypothesize that long-tail samples are also tougher for the model to learn well due to insufficient examples. Hence, the key innovation in SDCLR is to create a dynamic self-competitor model to contrast with the target model, which is a pruned version of the latter. During training, contrasting the two models will lead to adaptive online mining of the most easily forgotten samples for the current target model, and implicitly emphasize them more in the contrastive loss. Extensive experiments across multiple datasets and imbalance settings show that SDCLR significantly improves not only overall accuracies but also balancedness, in terms of linear evaluation on the full-shot and few-shot settings. Our code is available at https://github.com/VITA-Group/SDCLR.

Cardiovascular disorders cause nearly one in three deaths in the United States. Short- and long-term care for these disorders is often determined in short-term settings. However, these decisions are made with minimal longitudinal and long-term data. To overcome this bias towards data from acute care settings, improved longitudinal monitoring for cardiovascular patients is needed. Longitudinal monitoring provides a more comprehensive picture of patient health, allowing for informed decision making. This work surveys sensing and machine learning in the field of remote health monitoring for cardiovascular disorders. We highlight three needs in the design of new smart health technologies: (1) need for sensing technologies that track longitudinal trends of the cardiovascular disorder despite infrequent, noisy, or missing data measurements; (2) need for new analytic techniques designed in a longitudinal, continual fashion to aid in the development of new risk prediction techniques and in tracking disease progression; and (3) need for personalized and interpretable machine learning techniques, allowing for advancements in clinical decision making. We highlight these needs based upon the current state of the art in smart health technologies and analytics. We then discuss opportunities in addressing these needs for development of smart health technologies for the field of cardiovascular disorders and care.

Activity recognition in wearable computing faces two key challenges: i) activity characteristics may be context-dependent and change under different contexts or situations; ii) unknown contexts and activities may occur from time to time, requiring flexibility and adaptability of the algorithm. We develop a context-aware mixture of deep models termed the $\alpha$-$\beta$ network coupled with uncertainty quantification (UQ) based upon maximum entropy to enhance human activity recognition performance. We improve accuracy and F score by 10% by identifying high-level contexts in a data-driven way to guide model development. In order to ensure training stability, we have used a clustering-based pre-training in both public and in-house datasets, demonstrating improved accuracy through unknown context discovery.

The proliferation of medical monitoring devices makes it possible to track health vitals at high frequency, enabling the development of dynamic health risk scores that change with the underlying readings. Survival analysis, in particular hazard estimation, is well-suited to analyzing this stream of data to predict disease onset as a function of the time-varying vitals. This paper introduces the software package BoXHED (pronounced ‘box-head’) for nonparametrically estimating hazard functions via gradient boosting. BoXHED 1.0 is a novel tree-based implementation of the generic estimator proposed in Lee et al. (2017), which was designed for handling time-dependent covariates in a fully nonparametric manner. BoXHED is also the first publicly available software implementation for Lee et al. (2017). Applying it to a cardiovascular disease dataset from the Framingham Heart Study reveals novel interaction effects among known risk factors, potentially resolving an open question in clinical literature. BoXHED is available from GitHub: www.github.com/BoXHED.

Survival data is often collected in medical applications from a heterogeneous population of patients. While in the past, popular survival models focused on modeling the average effect of the covariates on survival outcomes, rapidly advancing sensing and information technologies have provided opportunities to further model the heterogeneity of the population as well as the non-linearity of the survival risk. With this motivation, we propose a new semi-parametric Bayesian Survival Rule List model in this paper. Our model derives a rule-based decision-making approach, while within the regime defined by each rule, survival risk is modelled via a Gaussian process latent variable model. Markov Chain Monte Carlo with a nested Laplace approximation on the Gaussian process posterior is used to search over the posterior of the rule lists efficiently. The use of ordered rule lists enables us to model heterogeneity while keeping the model complexity in check. Performance evaluations on a synthetic heterogeneous survival dataset and a real world sepsis survival dataset demonstrate the effectiveness of our model.

Personal tracking algorithms for health monitoring are critical for understanding an individual's life-style and personal choices in natural environments (NE). In order to train such tracking algorithms in NE, however, annotated data is needed, particularly when tracking a variety of activities of daily living. These algorithms are often trained in laboratory settings, with expectations that they will perform equally well in NE, which is often not the case; they must be trained on annotated data collected in NE and wearable computers provide opportunities to collect such data, though the process is burdensome. Therefore, we propose an intelligent scoring algorithm that limits the number of user annotation requests through the confidence of predictions generated by the tracking algorithm and automatically annotating data with high confidence. We enhance our scoring algorithm by providing improvements in our tracking algorithm by obtaining context data from nearable sensors. Each specific context of a user bounds the set of activities that can likely occur, which in turn improves the tracking algorithm and confidence. Finally, we propose a hierarchical annotation approach, where repeated use allows us to ask for detailed annotations that differentiate fine-grained differences in ways individuals perform activities. We validate our approach in a diet monitoring case study. We vary the number of annotations requested per day to evaluate model accuracy; we improve accuracy in NE by 8% when restricting requests to 20 per day and improve F1-score of activities by 11% with hierarchical annotations, while discussing implementation, accuracy, and power consumption in real-time use.

Emerging wearable sensors have enabled the unprecedented ability to continuously monitor human activities for healthcare purposes. However, with so many ambient sensors collecting different measurements, it becomes important not only to maintain good monitoring accuracy, but also low power consumption to ensure sustainable monitoring. This power-efficient sensing scheme can be achieved by deciding which group of sensors to use at a given time, requiring an accurate characterization of the trade-off between sensor energy usage and the uncertainty in ignoring certain sensor signals while monitor- ing. To address this challenge in the context of activity monitoring, we have designed an adaptive activity monitoring framework. We first propose a switching Gaussian process to model the observed sensor signals emitting from the underlying activity states. To efficiently compute the Gaussian process model likelihood and quantify the context prediction uncertainty, we propose a block circulant embedding technique and use Fast Fourier Transforms (FFT) for inference. By computing the Bayesian loss function tailored to switching Gaussian processes, an adaptive monitoring procedure is developed to select features from available sensors that optimize the trade-off between sensor power consumption and the prediction performance quantified by state prediction entropy. We demonstrate the effectiveness of our framework on the popular benchmark of UCI Human Activity Recognition using Smartphones.

Electronic health records (EHR) provide opportunities to leverage vast arrays of data to help prevent adverse events, improve patient outcomes, and reduce hospital costs. This paper develops a postoperative complications prediction system by extracting data from the EHR and creating features. The analytic engine then provides model accuracy, calibration, feature ranking, and personalized feature responses. This allows clinicians to interpret the likelihood of an adverse event occurring, general causes for these events, and the contributing factors for each specific patient. The patient cohort considered was 5214 patients in Yale-New Haven Hospital undergoing major cardiovascular procedures. Cohort-specific models predicted the likelihood of postoperative respiratory failure and infection, and achieved an area under the receiver operating characteristic curve of 0.81 for respiratory failure and 0.83 for infection.

Predicting the functional outcomes of spinal cord disorder patients after medical treatments, such as a surgical operation, has always been of great interest. Accurate posttreatment prediction is especially beneficial for clinicians, patients, care givers, and therapists. This paper introduces a prediction method for postoperative functional outcomes by a novel use of Gaussian process regression. The proposed method specifically considers the restricted value range of the target variables by modeling the Gaussian process based on a truncated Normal distribution, which significantly improves the prediction results. The prediction has been made in assistance with target tracking examinations using a highly portable and inexpensive handgrip device, which greatly contributes to the prediction performance. The proposed method has been validated through a dataset collected from a clinical cohort pilot involving 15 patients with cervical spinal cord disorder. The results show that the proposed method can accurately predict postoperative functional outcomes, Oswestry disability index and target tracking scores, based on the patient's preoperative information with a mean absolute error of 0.079 and 0.014 (out of 1.0), respectively.

Metabolic equivalent of task (MET) indicates the intensity of physical activities. This measurement is used in providing physical activity intervention in many chronic illnesses such as coronary heart disease, type-2 diabetes, and cancer. Due to the small size, portability, low power consumption, and low cost, wearable motion sensors are widely used to estimate MET values. However, one major obstacle in widespread adoption of current wearable monitoring systems is that the sensors must be worn on predefined locations on the body. This imposes much discomfort for users as they are not allowed to wear the sensors on their own desired body locations. In addition, non-adherence to the predefined location of the sensors results in significant reduction in the accuracy of physical activity monitoring. In this paper, we propose a framework for sensor location-independent MET estimation. We introduce a sensor localization approach that allows users to wear the sensors on different body locations without having to adhere to a specific installation protocol. We study how such an algorithm impacts the performance of MET estimation algorithms. Using daily physical activity data, we demonstrate that an automatic sensor localization algorithm decreases the estimation error of the MET calculation by a factor of 2.3 compared to the case without sensor localization. Furthermore, our sensor localization algorithm achieves an accuracy of 90.8% in detecting on-body locations of wearable sensors. The integration of sensor localization and MET estimation achieves an accuracy of 80% in calculating the MET values of daily physical activities.

Exergaming as a tool to combat obesity yields an interesting take on the problem of design and implementation of activity recognition systems for truly mobile games that achieve moderate levels of intensity. This work presents SoccAR, a mobile, sensor-based wearable exergaming system with fine-grain activity recognition. The system in this paper presents a recognition algorithm for the appropriate classification of 26 movements by extracting a large number of features and selecting the most important, as well as developing a multiple model strategy to better classify movements. This movement strategy allows for a trade off of detailed classification versus classification speed. A metric to define the accuracy in terms of the importance of particular movements is defined. The scheme presented develops a framework for more accurately classifying movements with a smaller number of features for a large, multiclass real-time environment. This results in a more accurate classification of movements, with an F-score in cross-validation of .937 using a PUK-kernel based SVM and multiple models, to .755 using only a single RBF-based model and 20 features.

Wireless health systems enable remote and continuous monitoring of individuals, with applications in elderly care support, chronic disease management, and preventive care. The underlying sensing platform provides constructs that consider the quality of information driven from the system and ensure the reliability/validity of the outcomes to support the decision-making processes. In this paper, we present an approach to integrate contextual information within the data processing flow in order to improve the quality of measurements. We focus on a pilot application that uses wearable motion sensors to calculate metabolic equivalent of task (MET) of exergaming movements. Exergames need to show energy expenditure values, often using accelerometer approximations applied to general activities. We focus on two contextual factors, namely “activity type” and “sensor location,” and demonstrate how these factors can be used to enhance the measured values, since allocating larger weights to more informative sensors can improve the final measurements. Further, designing regression models for each activity provides better results than any generalized model. Indeed, the averaged R2 value for the movements using simple sensor location improve from a general 0.71 to as high as 0.84 for an individual activity type. The different methods present a range of R2 value averages across activity type from 0.64 for sensor location to 0.89 for multidimensional regression, with an average game play MET value of 7.93. Finally, in a leaveone-subject-out cross validation, a mean absolute error of 2.231 METs is found when predicting the activity levels using the best models.

In remote health monitoring of patient's physical activity, ensuring correctness and authenticity of the received data is essential. Although many activity monitoring systems, devices and techniques have been developed, preventing patient cheating of an activity monitor has been a primarily unaddressed challenge across the board. Patients can manually shake an activity monitor device (sensor) with their hand and watch their physical activity points or rewards increase, we define this as "self-inflicted" cheating. A second type of cheating, "impersonator" cheating, is when subjects hand the activity sensor over to a friend or second party to wear and perform physical activity on their behalf. In this paper, we propose two novel methods based on classification algorithms to address the cheating problems. The first classification framework improves the correctness of our data by detecting self-inflicted cheatings. The second technique is an advanced classification scheme that extracts and learns unique patient-specific activity patterns from prior data collected on a patient to distinguish the true subject from an impersonator. We tested our proposed techniques on Wanda, a remote health monitoring system used in our Women's Heart Health study of 90 African American women at risk of cardiovascular disease. We were able to distinguish cheating from other physical activities such as walking and running, as well as other common activities of daily living such as driving and playing video games. The self-inflicted cheating classifier achieved an accuracy of above 90% and an AUC of 99%. The impersonator cheater framework results in an average accuracy of above 90% and an average AUC of 94%. Our results provide insight into the randomness of cheating activities, successfully detects cheaters, and attempts to build more context-aware remote activity monitors that more accurately capture patient activity.

Due to the exploding costs of chronic diseasesstemming from physical inactivity, wearable sensor systems toenable remote, continuous monitoring of individuals has increasedin popularity. Many research and commercial systems exist inorder to track the activity levels of users from general dailymotion to detailed movements. This work examines this problemfrom the space of smartwatches, using the Samsung GalaxyGear, a commercial device containing an accelerometer and agyroscope, to be used in recognizing physical activity. This workalso shows the sensors and features necessary to enable suchsmartwatches to accurately count, in real-time, the repetitions offree-weight and body-weight exercises. The goal of this work isto try and select only the best single axis for each activity byextracting only the most informative activity-specific features, inorder to minimize computational load and power consumptionin repetition counting. The five activities are incorporated in aworkout routine, and knowing this information, a random forestclassifier is built with average area under the curve (AUC) of: 974, with average accuracy of 93%, in cross validation to identify eachrepetition of a given exercise using all available sensors and AUCof: 950 with accuracy of 89:9% using the single best axis foreach activity alone. Adding a gyroscope with the accelerometerincreased the average AUC from: 968 to: 974, increasing theaccuracy of specific movements as much as 2%. Results show that, while a combination of accelerometer and gyroscope provide thestrongest classification results, often times features extracted froma single, best axis are enough to accurately identify movementsfor a personal training routine, where that axis is often, but notalways, an accelerometer axis.

Detecting human activity independent of intensity is essential in many applications, primarily in calculating metabolic equivalent rates and extracting human context awareness. Many classifiers that train on an activity at a subset of intensity levels fail to recognize the same activity at other intensity levels. This demonstrates weakness in the underlying classification method. Training a classifier for an activity at every intensity level is also not practical. In this paper, we tackle a novel intensity-independent activity recognition problem where the class labels exhibit large variability, the data are of high dimensionality, and clustering algorithms are necessary. We propose a new robust stochastic approximation framework for enhanced classification of such data. Experiments are reported using two clustering techniques, K-Means and Gaussian Mixture Models. The stochastic approximation algorithm consistently outperforms other well-known classification schemes which validate the use of our proposed clustered data representation. We verify the motivation of our framework in two applications that benefit from intensity-independent activity recognition. The first application shows how our framework can be used to enhance energy expenditure calculations. The second application is a novel exergaming environment aimed at using games to reward physical activity performed throughout the day, to encourage a healthy lifestyle.

Exergaming is expanding as an option for sedentary behavior in childhood/adult obesity and for extra exercise for gamers. This paper presents the development process for a mobile active sports exergame with near-realistic motions through the usage of body-wearable sensors. The process begins by collecting a dataset specifically targeted to mapping real-world activities directly to the games, then, developing the recognition system in a fashion to produce an enjoyable game. The classification algorithm in this paper has precision and recall of 77% and 77% respectively, compared with 40% and 19% precision and recall on current activity monitoring algorithms intended for general daily living activities. Aside from classification, the user experience must be strong enough to be a successful system for adoption. Indeed, fast and intense activities as well as competitive, multiplayer environments make for a successful, enjoyable exergame. This enjoyment is evaluated through a 30 person user study. Multiple aspects of the exergaming user experience trials have been merged into a comprehensive survey, called ExerSurvey. All but one user thought the motions in the game were realistic and difficult to cheat. Ultimately, a game with near-realistic motions was shown to be an enjoyable, active video exergame for any environment.

Detecting human activity independent of intensity is essential in many applications, primarily in calculating metabolic equivalent rates (MET) and extracting human context awareness from on-body inertial sensors. Many classifiers that train on an activity at a subset of intensity levels fail to classify the same activity at other intensity levels. This demonstrates weakness in the underlying activity model. Training a classifier for an activity at every intensity level is also not practical. In this paper we tackle a novel intensity-independent activity recognition application where the class labels exhibit large variability, the data is of high dimensionality, and clustering algorithms are necessary. We propose a new robust Stochastic Approximation framework for enhanced classification of such data. Experiments are reported for each dataset using two clustering techniques, K-Means and Gaussian Mixture Models. The Stochastic Approximation algorithm consistently outperforms other well-known classification schemes which validates the use of our proposed clustered data representation.

Hyperexcitability in hand is a disorder characterized by exaggerated muscle movement, and is a common symptom associated with neuro-degenerative diseases and spinal cord injuries. Current assessment methods for hyperexcitability rely on subjective examination, or on methods that evaluate the overall hand grip performance without particularization in the excitation. This paper introduces a system that utilizes an inexpensive body sensor device combined with a series of signal processing units that extract information specifically related to physiological phenomena generated by hyperexcitability. A clinical cohort study has been conducted on nine patients with cervical spinal cord injuries (mean age 58.2 ± 13.5). The experimental results show that the proposed signal processing mechanism accurately detects and analyzes the body signal. The medical significance of the experimental results is also investigated. This opens up a new opportunity for patients and clinical professionals to obtain accurate feedback of patient's motor function in an economical and ubiquitous manner.

Although most of the medical and healthcare monitoring systems generate multi-dimensional time series (via multiple sensors), most of the work by research community has been focused on defining distance metrics and matching algorithms to improve accuracy and optimize performance of search in single dimensional time series. In this work we motivate the need for multidimensional time series matching and propose a scalable technique that has high accuracy in presence of noise, uncertainty, and lack of synchronization between dimensions. We focus on two medical monitoring devices and their applications to showcase the advantages, performance, and accuracy of our multi-dimensional time series search technique. We demonstrate effectiveness of our signal search technique by using precision and recall metrics.

Although most of the medical and healthcare monitoring systems generate multi-dimensional time series (via multiple sensors), most of the work by research community has been focused on defining distance metrics and matching algorithms to improve accuracy and optimize performance of search in single dimensional time series. In this work we motivate the need for multidimensional time series matching and propose a scalable technique that has high accuracy in presence of noise, uncertainty, and lack of synchronization between dimensions. We focus on two medical monitoring devices and their applications to showcase the advantages, performance, and accuracy of our multi-dimensional time series search technique. We demonstrate effectiveness of our signal search technique by using precision and recall metrics.

The use of accelerometers to approximate energy expenditure and serve as inputs for exergaming, have both increased in prevalence in response to the worldwide obesity epidemic. Exergames have a need to show energy expenditure values to validate their results, often using accelerometer approximations applied to general daily-living activities. This work presents a method for estimating the metabolic equivalent of task (MET) values achieved when users perform exergaming-specific movements. This shows the caloric expenditure achieved by active video games, based upon raw gravity values of accelerations. Results show that, while a fusion of sensors monitoring the entire body achieves the best results, sensors placed closest to the primary location of movement achieve the most accurate approximations to the METs achieved per activity as well as the overall MET achieved for the soccer exergame under consideration. The METs achieved approach 7, the value considered to be actual casual soccer game play.

With the growing cost associated with the diagnosis and treatment of chronic neuro-degenerative diseases, the design and development of portable monitoring systems becomes essential. Such portable systems will allow for early diagnosis of motor function ability and provide new insight into the physical characteristics of ailment condition. This paper introduces a highly mobile and inexpensive monitoring system to quantify upper-limb performance for patients with movement disorders. With respect to the data analysis, we first present an approach to quantify general motor performance using the introduced sensing hardware. Next, we propose an ailment-based analysis which employs a significant-feature identification algorithm to perform cross-patient data analysis and classification. The efficacy of the proposed framework is demonstrated using real data collected through a clinical trial. The results show that the system can be utilized as a preliminary diagnostic tool to inspect the level of hand-movement performance. The ailment-based analysis performs an intergroup comparison of physiological signals for cerebral vascular accident (CVA) patients, chronic inflammatory demyelinating polyneuropathy (CIDP) patients, and healthy individuals. The system can classify each patient group with an accuracy of up to 95.00% and 91.42% for CVA and CIDP, respectively.

Time series subsequence matching (or signal searching) has importance in a variety of areas in health care informatics. These areas include case-based diagnosis and treatment as well as the discovery of trends and correlations between data. Much of the traditional research in signal searching has focused on high dimensional R-NN matching. However, the results of R-NN are often small and yield minimal information gain; especially with higher dimensional data. This paper proposes a randomized Monte Carlo sampling method to broaden search criteria such that the query results are an accurate sampling of the complete result set. The proposed method is shown both theoretically and empirically to improve information gain. The number of query results are increased by several orders of magnitude over approximate exact matching schemes and fall within a Gaussian distribution. The proposed method also shows excellent performance as the majority of overhead added by sampling can be mitigated through parallelization. Experiments are run on both simulated and real-world biomedical datasets.

Human activity monitoring, through the use of body-wearable sensors, allows for many exciting possibilities, from gaming, to exercise, to preventative health care, where childhood obesity is a growing epidemic. The rapidly increasing nature of this trend requires serious thought at targeting its causes and finding solutions. One major influence is video gaming and the hours of sedentary behavior associated with it. In this paper, we present our system for enforcing physical activity of humans playing video games with our body-worn sensor system as the controller. Body movements are communicated with the host computer that calculates physical activity via the metabolic equivalent of task, and runs signal processing algorithms to classify and enforce movements. A user study was conducted to validate the effectiveness and realism of the system while playing an actual video game and data was collected from these same users in order to verify the accuracy of our system. The results show a system that not only allows physical activity, but also enforces it, leading to healthier gaming and accurate motion analysis.