Identifying sensors-based parameters associated with fall risk in community-dwelling older adults: an investigation and interpretation of discriminatory parameters.

BACKGROUND: Falls pose a severe threat to the health of older adults worldwide. Determining gait and kinematic parameters that are related to an increased risk of falls is essential for developing effective intervention and fall prevention strategies. This study aimed to investigate the discriminatory parameter, which lay an important basis for developing effective clinical screening tools for identifying high-fall-risk older adults. METHODS: Forty-one individuals aged 65 years and above living in the community participated in this study. The older adults were classified as high-fall-risk and low-fall-risk individuals based on their BBS scores. The participants wore an inertial measurement unit (IMU) while conducting the Timed Up and Go (TUG) test. Simultaneously, a depth camera acquired images of the participants' movements during the experiment. After segmenting the data according to subtasks, 142 parameters were extracted from the sensor-based data. A t-test or Mann-Whitney U test was performed on the parameters for distinguishing older adults at high risk of falling. The logistic regression was used to further quantify the role of different parameters in identifying high-fall-risk individuals. Furthermore, we conducted an ablation experiment to explore the complementary information offered by the two sensors. RESULTS: Fifteen participants were defined as high-fall-risk individuals, while twenty-six were defined as low-fall-risk individuals. 17 parameters were tested for significance with p-values less than 0.05. Some of these parameters, such as the usage of walking assistance, maximum angular velocity around the yaw axis during turn-to-sit, and step length, exhibit the greatest discriminatory abilities in identifying high-fall-risk individuals. Additionally, combining features from both devices for fall risk assessment resulted in a higher AUC of 0.882 compared to using each device separately. CONCLUSIONS: Utilizing different types of sensors can offer more comprehensive information. Interpreting parameters to physiology provides deeper insights into the identification of high-fall-risk individuals. High-fall-risk individuals typically exhibited a cautious gait, such as larger step width and shorter step length during walking. Besides, we identified some abnormal gait patterns of high-fall-risk individuals compared to low-fall-risk individuals, such as less knee flexion and a tendency to tilt the pelvis forward during turning.

Optimal Composite Likelihood Estimation and Prediction for Distributed Gaussian Process Modeling.

Large-scale Gaussian process (GP) modeling is becoming increasingly important in machine learning. However, the standard modeling method of GPs, which uses the maximum likelihood method and the best linear unbiased predictor, is designed to run on a single computer, which often has limited computing power. Therefore, there is a growing demand for approximate alternatives, such as composite likelihood methods, that can take advantage of the power of multiple computers. However, these alternative methods in the literature offer limited options for practitioners because most methods focus more on computational efficiency rather than statistical efficiency. Limited accurate solutions to the parameter estimation and prediction for fast GP modeling are available in the literature for supercomputing practitioners. Therefore, this study develops an optimal composite likelihood (OCL) scheme for distributed GP modeling that can minimize information loss in parameter estimation and model prediction. The proposed predictor, called the best linear unbiased block predictor (BLUBP), has the minimum prediction variance given the partitioned data. Numerical examples illustrate that both the proposed composite likelihood estimation and prediction methods provide more accurate performance than their traditional counterparts under various cases, and an extremely close approximation to the standard modeling method is observed.

Design of a Sensor-Technology-Augmented Gait and Balance Monitoring System for Community-Dwelling Older Adults in Hong Kong: A Pilot Feasibility Study.

Routine assessments of gait and balance have been recognized as an effective approach for preventing falls by issuing early warnings and implementing appropriate interventions. However, current limited public healthcare resources cannot meet the demand for continuous monitoring of deteriorations in gait and balance. The objective of this study was to develop and evaluate the feasibility of a prototype surrogate system driven by sensor technology and multi-sourced heterogeneous data analytics, for gait and balance assessment and monitoring. The system was designed to analyze users' multi-mode data streams collected via inertial sensors and a depth camera while performing a 3-m timed up and go test, a five-times-sit-to-stand test, and a Romberg test, for predicting scores on clinical measurements by physiotherapists. Generalized regression of sensor data was conducted to build prediction models for gait and balance estimations. Demographic correlations with user acceptance behaviors were analyzed using ordinal logistic regression. Forty-four older adults (38 females) were recruited in this pilot study (mean age = 78.5 years, standard deviation [SD] = 6.2 years). The participants perceived that using the system for their gait and balance monitoring was a good idea (mean = 5.45, SD = 0.76) and easy (mean = 4.95, SD = 1.09), and that the system is useful in improving their health (mean = 5.32, SD = 0.83), is trustworthy (mean = 5.04, SD = 0.88), and has a good fit between task and technology (mean = 4.97, SD = 0.84). In general, the participants showed a positive intention to use the proposed system in their gait and balance management (mean = 5.22, SD = 1.10). Demographic correlations with user acceptance are discussed. This study provides preliminary evidence supporting the feasibility of using a sensor-technology-augmented system to manage the gait and balance of community-dwelling older adults. The intervention is validated as being acceptable, viable, and valuable.

An Indoor Fall Monitoring System: Robust, Multistatic Radar Sensing and Explainable, Feature-Resonated Deep Neural Network.

Indoor fall monitoring is challenging for community-dwelling older adults due to the need for high accuracy and privacy concerns. Doppler radar is promising, given its low cost and contactless sensing mechanism. However, the line-of-sight restriction limits the application of radar sensing in practice, as the Doppler signature will vary when the sensing angle changes, and signal strength will be substantially degraded with large aspect angles. Additionally, the similarity of the Doppler signatures among different fall types makes it extremely challenging for classification. To address these problems, in this paper we first present a comprehensive experimental study to obtain Doppler radar signals under large and arbitrary aspect angles for diverse types of simulated falls and daily living activities. We then develop a novel, explainable, multi-stream, feature-resonated neural network (eMSFRNet) that achieves fall detection and a pioneering study of classifying seven fall types. eMSFRNet is robust to both radar sensing angles and subjects. It is also the first method that can resonate and enhance feature information from noisy/weak Doppler signatures. The multiple feature extractors - including partial pre-trained layers from ResNet, DenseNet, and VGGNet - extracts diverse feature information with various spatial abstractions from a pair of Doppler signals. The feature-resonated-fusion design translates the multi-stream features to a single salient feature that is critical to fall detection and classification. eMSFRNet achieved 99.3% accuracy detecting falls and 76.8% accuracy for classifying seven fall types. Our work is the first effective multistatic robust sensing system that overcomes the challenges associated with Doppler signatures under large and arbitrary aspect angles, via our comprehensible feature-resonated deep neural network. Our work also demonstrates the potential to accommodate different radar monitoring tasks that demand precise and robust sensing.

Impact of early phase COVID-19 precautionary behaviors on seasonal influenza in Hong Kong: A time-series modeling approach.

Background: Before major non-pharmaceutical interventions were implemented, seasonal incidence of influenza in Hong Kong showed a rapid and unexpected reduction immediately following the early spread of COVID-19 in mainland China in January 2020. This decline was presumably associated with precautionary behavioral changes (e.g., wearing face masks and avoiding crowded places). Knowing their effectiveness on the transmissibility of seasonal influenza can inform future influenza prevention strategies. Methods: We estimated the effective reproduction number (R t ) of seasonal influenza in 2019/20 winter using a time-series susceptible-infectious-recovered (TS-SIR) model with a Bayesian inference by integrated nested Laplace approximation (INLA). After taking account of changes in underreporting and herd immunity, the individual effects of the behavioral changes were quantified. Findings: The model-estimated mean R t reduced from 1.29 (95%CI, 1.27-1.32) to 0.73 (95%CI, 0.73-0.74) after the COVID-19 community spread began. Wearing face masks protected 17.4% of people (95%CI, 16.3-18.3%) from infections, having about half of the effect as avoiding crowded places (44.1%, 95%CI, 43.5-44.7%). Within the current model, if more than 85% of people had adopted both behaviors, the initial R t could have been less than 1. Conclusion: Our model results indicate that wearing face masks and avoiding crowded places could have potentially significant suppressive impacts on influenza.

Prediction of Wellness Condition for Community-Dwelling Elderly via ECG Signals Data-Based Feature Construction and Modeling.

The accelerated growth of elderly populations in many countries and regions worldwide is creating a major burden to the healthcare system. Intelligent approaches for continuous health monitoring have the potential to promote the transition to more proactive and affordable healthcare. Electrocardiograms (ECGs), collected from portable devices, with noninvasive and cost-effective merits, have been widely used to monitor various health conditions. However, the dynamic and heterogeneous pattern of ECG signals makes relevant feature construction and predictive model development a challenging task. In this study, we aim to develop an integrated approach for one-day-forward wellness prediction in the community-dwelling elderly using single-lead short ECG signal data via multiple-features construction and predictive model implementation. Vital signs data from the elderly were collected via station-based equipment on a daily basis. After data preprocessing, a set of features were constructed from ECG signals based on the integration of various models, including time and frequency domain analysis, a wavelet transform-based model, ensemble empirical mode decomposition (EEMD), and the refined composite multiscale sample entropy (RCMSE) model. Then, a machine learning based predictive model was established to map the l-day lagged features to wellness condition. The results showed that the approach developed in this study achieved the best performance for wellness prediction in the community-dwelling elderly. In practice, the proposed approach could be useful in the timely identification of elderly people who might have health risks, and could facilitating decision-making to take appropriate interventions.

A Systematic Review of Wearable Sensor-Based Technologies for Fall Risk Assessment in Older Adults.

Falls have been recognized as the major cause of accidental death and injury in people aged 65 and above. The timely prediction of fall risks can help identify older adults prone to falls and implement preventive interventions. Recent advancements in wearable sensor-based technologies and big data analysis have spurred the development of accurate, affordable, and easy-to-use approaches to fall risk assessment. The objective of this study was to systematically assess the current state of wearable sensor-based technologies for fall risk assessment among community-dwelling older adults. Twenty-five of 614 identified research articles were included in this review. A comprehensive comparison was conducted to evaluate these approaches from several perspectives. In general, these approaches provide an accurate and effective surrogate for fall risk assessment. The accuracy of fall risk prediction can be influenced by various factors such as sensor location, sensor type, features utilized, and data processing and modeling techniques. Features constructed from the raw signals are essential for predictive model development. However, more investigations are needed to identify distinct, clinically interpretable features and develop a general framework for fall risk assessment based on the integration of sensor technologies and data modeling.

Understanding MMPI-2 response structure between schizophrenia and healthy individuals.

Background: Using Minnesota Multiphasic Personality Inventory-2 (MMPI-2) clinical scales to evaluate clinical symptoms in schizophrenia is a well-studied topic. Nonetheless, research focuses less on how these clinical scales interact with each other. Aims: Investigates the network structure and interaction of the MMPI-2 clinical scales between healthy individuals and patients with schizophrenia through the Bayesian network. Method: Data was collected from Wuhan Psychiatric Hospital from March 2008 to May 2018. A total of 714 patients with schizophrenia and 714 healthy subjects were identified through propensity score matching according to the criteria of the International Classification of Diseases (ICD-11). Separated MMPI-2 clinical scales Bayesian networks were built for healthy subjects and patients with schizophrenia, respectively. Results: The Bayesian network showed that the lower 7 scale was a consequence of the correlation between the lower 2 scale and the greater 8 scale. A solely lower 7 scale does yield neither a lower 2 scale nor a higher 8 scale. The proposed method showed 72% of accuracy with 78% area under the ROC curve (AUC), similar to the previous studies. Limitations: The proposed method simplified the continuous Bayesian network to predict binary outcomes, including other categorical data is not explored. Besides, the participants might only represent an endemic as they come from a single hospital. Conclusion: This study identified MMPI-2 clinical scales correlation and built separated Bayesian networks to investigate the difference between patients with schizophrenia and healthy people. These differences may contribute to a better understanding of the clinical symptoms of schizophrenia and provide medical professionals with new perspectives for diagnosis.

Short-Term Nationwide Airport Throughput Prediction With Graph Attention Recurrent Neural Network.

With the dynamic air traffic demand and the constrained capacity resources, accurately predicting airport throughput is essential to ensure the efficiency and resilience of air traffic operations. Many research efforts have been made to predict traffic throughputs or flight delays at an airport or over a network. However, it is still a challenging problem due to the complex spatiotemporal dynamics of the highly interacted air transportation systems. To address this challenge, we propose a novel deep learning model, graph attention neural network stacking with a Long short-term memory unit (GAT-LSTM), to predict the short-term airport throughput over a national air traffic network. LSTM layers are included to extract the temporal correlations in the data, while the graph attention mechanism is used to capture the spatial dependencies. For the graph attention mechanism, two graph modeling methods, airport-based graph and OD-pair graph are explored in this study. We tested the proposed model using real-world air traffic data involving 65 major airports in China over 3 months in 2017 and compared its performance with other state-of-the-art models. Results showed that the temporal pattern was the dominate factor, compared to the spatial pattern, in predicting airport throughputs over an air traffic network. Among the prediction models that we compared, both the proposed model and LSTM performed well on prediction accuracy over the entire network. Better performance of the proposed model was observed when focusing on airports with larger throughputs. We also conducted an analysis on model interpretability. We found that spatiotemporal correlations in the data were learned and shown via the model parameters, which helped us to gain insights into the topology and the dynamics of the air traffic network.

Sparsity-Constrained Invariant Risk Minimization for Domain Generalization With Application to Machinery Fault Diagnosis Modeling.

Machine learning has been widely applied to study AI-informed machinery fault diagnosis. This work proposes a sparsity-constrained invariant risk minimization (SCIRM) framework, which develops machine-learning models with better generalization capacities for environmental disturbances in machinery fault diagnosis. The SCIRM is built by innovating the optimization formulation of the recently proposed invariant risk minimization (IRM) and its variants through the integration of sparsity constraints. We prove that if a sparsity measure is differentiable, scale invariant, and semistrictly quasi-convex, the SCIRM can be guaranteed to solve the domain generalization problem based on a few predefined problem settings. We mathematically derive a family of such sparsity measures. A practical process of implementing the SCIRM for machinery fault diagnosis tasks is offered. We first verify our theoretical exploration of the SCIRM by using simulation data. We further compare SCIRM with a set of state-of-the-art methods by using real machinery fault data collected under a variety of working conditions. The computational results confirm that the machinery fault diagnosis model developed by the SCIRM offers a higher generalization capacity and performs better than the other benchmarks across the different testing datasets.

A promising new tool for fault diagnosis of railway wheelset bearings: SSO-based Kurtogram.

A promising method is proposed systematically to select an accurate resonance frequency band and separate refined resonance response from periodic excitation in this study. This work expanded the short-time Fourier transform (STFT)- and wavelet transform (WT)-based Kurtograms and developed a hybrid signal separation operator (SSO)-spectral kurtosis computational scheme to implement Kurtogram by introducing the SSO method-SSO-based Kurtogram. The ability to accurately extract the refined resonance frequency band of SSO greatly improves its adaptivity for engineering applications. The effectiveness of the SSO-based Kurtogram is studied by using a bearing fault simulation signal, and the influence of window function on the detection effect of the proposed method is explored. Furthermore the validity of the SSO-based Kurtogram for bearing fault detection is verified by a set of railway wheelset-bearing experiments on the wheelset running-in testbed bench. Experimental results show that the SSO-based Kurtogram performs highly in detecting various kinds of single and compound faults of bearings. Compared with the WT- and STFT-based Kurtogram, the proposed method has obvious advantages in terms of effectiveness and visual inspection ability. In engineering practice, a railway wheelset-bearing-fault experiment on an in-service high-speed train in the real world is taken as a case study, which makes the verification of SSO-based Kurtogram more convincing and demonstrates the practical engineering value of the proposed method. The results show that in case of equal effectiveness, SSO-based Kurtogram has an absolute advantage in the visual inspection ability, embodied in eliminating other vibrations unrelated to the target fault and making the fault feature frequency and its harmonics remarkable.

Seven-year excess mortality, functional outcome and health status after trauma in Hong Kong.

PURPOSE: The purpose was to investigate long-term health impacts of trauma and the aim was to describe the functional outcome and health status up to 7 years after trauma. METHODS: We conducted a prospective, multi-centre cohort study of adult trauma patients admitted to three regional trauma centres with moderate or major trauma (ISS ≥ 9) in Hong Kong (HK). Patients were followed up at regular time points (1, 6 months and 1, 2, 3, 4, 5, 6, and 7 years) by telephone using extended Glasgow Outcome Scale (GOSE) and the Short-Form 36 (SF36). Observed annual mortality rate was compared with the expected mortality rate estimated using the HK population cohort. Linear mixed model (LMM) analyses examined the changes in SF36 with subgroups of age ≥ 65 years, ISS > 15, and GOSE ≥ 5 over time. RESULTS: At 7 years, 115 patients had died and 48% (138/285) of the survivors responded. The annual mortality rate (AMR) of the trauma cohort was consistently higher than the expected mortality rate from the general population. Forty-one percent of respondents had upper good recovery (GOSE = 8) at 7 years. Seven-year mean PCS and MCS were 45.06 and 52.06, respectively. LMM showed PCS improved over time in patients aged < 65 years and with baseline GOSE ≥ 5, and the MCS improved over time with baseline GOSE ≥ 5. Higher mortality rate, limited functional recovery and worse physical health status persisted up to 7 years post-injury. CONCLUSION: Long-term mortality and morbidity should be monitored for Asian trauma centre patients to understand the impact of trauma beyond hospital discharge.

Clinical prediction rule of termination of resuscitation for out-of-hospital cardiac arrest patient with pre-hospital defibrillation given.

OBJECTIVE: To derive a clinical prediction rule of termination of resuscitation (TOR) for out-of-hospital cardiac arrest (OHCA) with pre-hospital defibrillation given. METHOD: This was a retrospective multicenter cohort study performed in three emergency departments (EDs) of three regional hospitals from 1/1/2012 to 31/12/2018. Patients of OHCA aged ≥18 years old were included. Those with post-mortem changes, return of spontaneous circulation and receiving no resuscitation in EDs were excluded. A TOR rule was derived by logistic regression analysis based on demographics and end-tidal carbon dioxide level of included subjects with pre-hospital defibrillation given. RESULTS: There were 447 included patients had received pre-hospital defibrillation, in which 148 had return of spontaneous circulation (ROSC), with 22 survived to discharge (STD). Independent predictors for death on or before ED arrival (no ROSC) included EMS call to ED time >20 min and ETCO2 level <20 mmHg from first three sets. A 2-criteria rule predicting death on or before ED arrival by fulfilling both of the independent predictors had a specificity of 0.95 (95% CI 0.90-0.98) and positive predictive value (PPV) of 0.95 (95% CI 0.90-0.98), if 2nd set of ETCO2 was used. The positive likelihood ratio was 10.04 (95% CI 4.83-20.89). CONCLUSION: The 2-criteria TOR rule for OHCA patients with pre-hospital defibrillation had a high specificity and PPV for predicting death on or before ED arrival.

Automatic Recognition and Analysis of Balance Activity in Community-Dwelling Older Adults: Algorithm Validation.

BACKGROUND: Clinical mobility and balance assessments identify older adults who have a high risk of falls in clinics. In the past two decades, sensors have been a popular supplement to mobility and balance assessment to provide quantitative information and a cost-effective solution in the community environment. Nonetheless, the current sensor-based balance assessment relies on manual observation or motion-specific features to identify motions of research interest. OBJECTIVE: The objective of this study was to develop an automatic motion data analytics framework using signal data collected from an inertial sensor for balance activity analysis in community-dwelling older adults. METHODS: In total, 59 community-dwelling older adults (19 males and 40 females; mean age = 81.86 years, SD 6.95 years) were recruited in this study. Data were collected using a body-worn inertial measurement unit (including an accelerometer and a gyroscope) at the L4 vertebra of each individual. After data preprocessing and motion detection via a convolutional long short-term memory (LSTM) neural network, a one-class support vector machine (SVM), linear discriminant analysis (LDA), and k-nearest neighborhood (k-NN) were adopted to classify high-risk individuals. RESULTS: The framework developed in this study yielded mean accuracies of 87%, 86%, and 89% in detecting sit-to-stand, turning 360°, and stand-to-sit motions, respectively. The balance assessment classification showed accuracies of 90%, 92%, and 86% in classifying abnormal sit-to-stand, turning 360°, and stand-to-sit motions, respectively, using Tinetti Performance Oriented Mobility Assessment-Balance (POMA-B) criteria by the one-class SVM and k-NN. CONCLUSIONS: The sensor-based approach presented in this study provided a time-effective manner with less human efforts to identify and preprocess the inertial signal and thus enabled an efficient balance assessment tool for medical professionals. In the long run, the approach may offer a flexible solution to relieve the community's burden of continuous health monitoring.

Influencing factors of Barthel index scores among the community-dwelling elderly in Hong Kong: a random intercept model.

BACKGROUND: Barthel Index (BI) is one of the most widely utilized tools for assessing functional independence in activities of daily living. Most existing BI studies used populations with specific diseases (e.g., Alzheimer's and stroke) to test prognostic factors of BI scores; however, the generalization of these findings was limited when the target populations varied. OBJECTIVES: The aim of the present study was to utilize electronic health records (EHRs) and data mining techniques to develop a generic procedure for identifying prognostic factors that influence BI score changes among community-dwelling elderly. METHODS: Longitudinal data were collected from 113 older adults (81 females; mean age = 84 years, SD = 6.9 years) in Hong Kong elderly care centers. Visualization technologies were used to align annual BI scores with individual EHRs chronologically. Linear mixed-effects (LME) regression was conducted to model longitudinal BI scores based on socio-demographics, disease conditions, and features extracted from EHRs. RESULTS: The visualization presented a decline in BI scores changed by time and health history events. The LME model yielded a conditional R2 of 84%, a marginal R2 of 75%, and a Cohen's f2 of 0.68 in the design of random intercepts for individual heterogeneity. Changes in BI scores were significantly influenced by a set of socio-demographics (i.e., sex, education, living arrangement, and hobbies), disease conditions (i.e., dementia and diabetes mellitus), and EHRs features (i.e., event counts in allergies, diagnoses, accidents, wounds, hospital admissions, injections, etc.). CONCLUSIONS: The proposed visualization approach and the LME model estimation can help to trace older adults' BI score changes and identify the influencing factors. The constructed long-term surveillance system provides reference data in clinical practice and help healthcare providers manage the time, cost, data and human resources in community-dwelling settings.

Prognostics for lithium-ion batteries using a two-phase gamma degradation process model.

To address the degradation of rechargeable batteries, this paper presents a two-phase gamma process model with a fixed change-point for modeling the voltage-discharge curves of battery cycle aging under a constant current. The model can be applied to estimate the state of charge (SOC) and the remaining useful discharge time (RUT) in a cycle with consideration of the effect of cycle aging, and can also be applied to estimate the state of life (SOL) and the remaining useful life (RUL) across cycles. The applications of the proposed model are demonstrated using the experimental cycle aging data of a lithium iron phosphate battery. A comparison shows that the proposed model generates a more accurate prediction than the conventional two-term exponential model with capacity data under a particle filter framework, and this reveals the superiority of modeling with voltage over modeling with capacity. The analytical expression of mean useful discharge time in a cycle (or mean time to failure) is developed with approximation by a Taylor expansion and the Birnbaum-Saunders distribution, and the result is shown to be in good agreement with the true mean of a gamma process.

Evaluating resampling methods and structured features to improve fall incident report identification by the severity level.

OBJECTIVE: This study aims to improve the classification of the fall incident severity level by considering data imbalance issues and structured features through machine learning. MATERIALS AND METHODS: We present an incident report classification (IRC) framework to classify the in-hospital fall incident severity level by addressing the imbalanced class problem and incorporating structured attributes. After text preprocessing, bag-of-words features, structured text features, and structured clinical features were extracted from the reports. Next, resampling techniques were incorporated into the training process. Machine learning algorithms were used to build classification models. IRC systems were trained, validated, and tested using a repeated and randomly stratified shuffle-split cross-validation method. Finally, we evaluated the system performance using the F1-measure, precision, and recall over 15 stratified test sets. RESULTS: The experimental results demonstrated that the classification system setting considering both data imbalance issues and structured features outperformed the other system settings (with a mean macro-averaged F1-measure of 0.733). Considering the structured features and resampling techniques, this classification system setting significantly improved the mean F1-measure for the rare class by 30.88% (P value < .001) and the mean macro-averaged F1-measure by 8.26% from the baseline system setting (P value < .001). In general, the classification system employing the random forest algorithm and random oversampling method outperformed the others. CONCLUSIONS: Structured features provide essential information for categorizing the fall incident severity level. Resampling methods help rebalance the class distribution of the original incident report data, which improves the performance of machine learning models. The IRC framework presented in this study effectively automates the identification of fall incident reports by the severity level.

An Adaptive Weight Learning-Based Multitask Deep Network for Continuous Blood Pressure Estimation Using Electrocardiogram Signals.

Estimating blood pressure via combination analysis with electrocardiogram and photoplethysmography signals has attracted growing interest in continuous monitoring patients' health conditions. However, most wearable/portal monitoring devices generally acquire only one kind of physiological signals due to the consideration of energy cost, device weight and size, etc. In this study, a novel adaptive weight learning-based multitask deep learning framework based on single lead electrocardiogram signals is proposed for continuous blood pressure estimation. Specifically, the proposed method utilizes a 2-layer bidirectional long short-term memory network as the sharing layer, followed by three identical architectures of 2-layer fully connected networks for task-specific blood pressure estimation. To learn the importance of task-specific losses automatically, an adaptive weight learning scheme based on the trend of validation loss is proposed. Extensive experiment results on Physionet Multiparameter Intelligent Monitoring in Intensive Care (MIMIC) II waveform database demonstrate that the proposed method using electrocardiogram signals obtains estimating performance of 0.12±10.83 mmHg, 0.13±5.90 mmHg, and 0.08±6.47 mmHg for systolic blood pressure, diastolic blood pressure, and mean arterial pressure, respectively. It can meet the requirements of the British Hypertension Society standard and US Association of Advancement of Medical Instrumentation standard with a considerable margin. Combined with a wearable/portal electrocardiogram device, the proposed model can be deployed to a healthcare system to provide a long-term continuous blood pressure monitoring service, which would help to reduce the incidence of malignant complications to hypertension.

Assessing elderly's functional balance and mobility via analyzing data from waist-mounted tri-axial wearable accelerometers in timed up and go tests.

BACKGROUND: Poor balance has been cited as one of the key causal factors of falls. Timely detection of balance impairment can help identify the elderly prone to falls and also trigger early interventions to prevent them. The goal of this study was to develop a surrogate approach for assessing elderly's functional balance based on Short Form Berg Balance Scale (SFBBS) score. METHODS: Data were collected from a waist-mounted tri-axial accelerometer while participants performed a timed up and go test. Clinically relevant variables were extracted from the segmented accelerometer signals for fitting SFBBS predictive models. Regularized regression together with random-shuffle-split cross-validation was used to facilitate the development of the predictive models for automatic balance estimation. RESULTS: Eighty-five community-dwelling older adults (72.12 ± 6.99 year) participated in our study. Our results demonstrated that combined clinical and sensor-based variables, together with regularized regression and cross-validation, achieved moderate-high predictive accuracy of SFBBS scores (mean MAE = 2.01 and mean RMSE = 2.55). Step length, gender, gait speed and linear acceleration variables describe the motor coordination were identified as significantly contributed variables of balance estimation. The predictive model also showed moderate-high discriminations in classifying the risk levels in the performance of three balance assessment motions in terms of AUC values of 0.72, 0.79 and 0.76 respectively. CONCLUSIONS: The study presented a feasible option for quantitatively accurate, objectively measured, and unobtrusively collected functional balance assessment at the point-of-care or home environment. It also provided clinicians and elderly with stable and sensitive biomarkers for long-term monitoring of functional balance.

A Personalized Health Monitoring System for Community-Dwelling Elderly People in Hong Kong: Design, Implementation, and Evaluation Study.

BACKGROUND: Telehealth is an effective means to assist existing health care systems, particularly for the current aging society. However, most extant telehealth systems employ individual data sources by offline data processing, which may not recognize health deterioration in a timely way. OBJECTIVE: Our study objective was two-fold: to design and implement an integrated, personalized telehealth system on a community-based level; and to evaluate the system from the perspective of user acceptance. METHODS: The system was designed to capture and record older adults' health-related information (eg, daily activities, continuous vital signs, and gait behaviors) through multiple measuring tools. State-of-the-art data mining techniques can be integrated to detect statistically significant changes in daily records, based on which a decision support system could emit warnings to older adults, their family members, and their caregivers for appropriate interventions to prevent further health deterioration. A total of 45 older adults recruited from 3 elderly care centers in Hong Kong were instructed to use the system for 3 months. Exploratory data analysis was conducted to summarize the collected datasets. For system evaluation, we used a customized acceptance questionnaire to examine users' attitudes, self-efficacy, perceived usefulness, perceived ease of use, and behavioral intention on the system. RESULTS: A total of 179 follow-up sessions were conducted in the 3 elderly care centers. The results of exploratory data analysis showed some significant differences in the participants' daily records and vital signs (eg, steps, body temperature, and systolic blood pressure) among the 3 centers. The participants perceived that using the system is a good idea (ie, attitude: mean 5.67, SD 1.06), comfortable (ie, self-efficacy: mean 4.92, SD 1.11), useful to improve their health (ie, perceived usefulness: mean 4.99, SD 0.91), and easy to use (ie, perceived ease of use: mean 4.99, SD 1.00). In general, the participants showed a positive intention to use the first version of our personalized telehealth system in their future health management (ie, behavioral intention: mean 4.45, SD 1.78). CONCLUSIONS: The proposed health monitoring system provides an example design for monitoring older adults' health status based on multiple data sources, which can help develop reliable and accurate predictive analytics. The results can serve as a guideline for researchers and stakeholders (eg, policymakers, elderly care centers, and health care providers) who provide care for older adults through such a telehealth system.