Continuous monitoring of body temperature for objective detection of health and safety risks in construction sites: An analysis of the accuracy and comfort of off-the-shelf wearable sensors.

Recent studies have shown the potential of wearable sensors for objective detection of health and safety risks in construction workers through their collected physiological data. Body temperature, as the focus of the current study, is one of the most important physiological parameters that can help to detect various health and safety risks such as heat stress, physical fatigue, and infectious diseases. This study aims to assess the applicability and performance of off-the-shelf wearable sensor devices to monitor workers' body temperature in construction sites by evaluating the accuracy of temperature measurements as well as the comfort of the devices. A total of nine off-the-shelf wearable sensor devices available on the market were initially trialed in the laboratory, and three devices were shortlisted considering a set of selection criteria for further assessment. Over three weeks, the shortlisted wearable sensors were tested on 26 workers in two large construction sites in Australia. The reliability/validity of the selected wearable sensors in measuring body temperature was investigated using Bland-Altman analysis. Human factors were also investigated in terms of the comfort of the devices, their impact on workers' performance, and the acceptability of being worn for an extended period (i.e., 8 h or more). It was found that all selected devices measured body temperature with a bias of less than one indicating a slight difference in measurements compared to the reference hospital-grade thermometers. Two devices out of the three were also comfortable. The achieved results indicate that it is feasible to develop a continuous temperature monitoring platform using off-the-shelf wearable sensors to detect a range of significant health and safety risks in construction sites objectively. Considering the rapid advancements in manufacturing wearable sensors, future research can adopt a similar approach to include the newly introduced off-the-shelf temperature sensors and select the most appropriate device.

Nonlinear Features from Multi-Modal Signals for Continuous Stress Monitoring.

Continuous monitoring of stress in individuals during their daily activities has become an inevitable need in present times. Unattended stress is a silent killer and may lead to fatal physical and mental disorders if left unidentified. Stress identification based on individual judgement often leads to under-diagnosis and delayed treatment possibilities. EEG-based stress monitoring is quite popular in this context, but impractical to use for continuous remote monitoring.Continuous remote monitoring of stress using signals acquired from everyday wearables like smart watches is the best alternative here. Non-EEG data such as heart rate and ectodermal activity can also act as indicators of physiological stress. In this work, we have explored the possibility of using nonlinear features from non-EEG data such as (a) heart rate, (b) ectodermal activity, (c) body temperature (d) SpO2 and (e) acceleration in detecting four different types of neurological states; namely (1) Relaxed state, (2) State of Physical stress, (3) State of Cognitive stress and (4) State of Emotional stress. Physiological data of 20 healthy adults have been used from the noneeg database of PhysioNet.Results: We used two machine learning models; a linear logistic regression and a nonlinear random forest to detect (a) stress from relaxed state and (4) the four different neurological states. We trained the models using linear and nonlinear features separately. For the 2-class and 4-class problems, using nonlinear features increased the accuracy of the models. Moreover, it is also proved in this study that by using nonlinear features, we can avoid the use of complex machine learning models.

Impact of synthetic noise signature and physiologic ECG signal on designing ML-based ECG noise detection framework.

Automatic signal analysis using artificial intelligence is getting popular in digital healthcare, such as ECG rhythm analysis, where ECG signals are collected from traditional ECG machines or wearable ECG sensors. However, the risk of using an automated system for ECG analysis when noise is present can lead to incorrect diagnosis or treatment decisions. A noise detector is crucial to minimise the risk of incorrect diagnosis. Machine learning (ML) models are used in ECG noise detection before clinical decision-making systems to mitigate false alarms. However, it is essential to prove the generalisation capability of the ML model in different situations. ML models performance is 50% lesser when the model is trained with synthetic and tested with physiologic ECG datasets compared to trained and tested with physiologic ECG datasets. This suggests that the ML model must be trained with physiologic ECG datasets rather than synthetic ones or add more various types of noise in synthetic ECG datasets that can mimic physiologic ECG.Clinical relevance- ML model trained with synthetic noisy ECG can increase the 50% misclassification rate in ECG noise detection compared to training with physiologic ECG datasets. The wrong classification of noise-free and noisy ECG will lead to misdiagnosis regarding the patient's condition, which could be a cause of death.

Measurement of stress-induced sympathetic nervous activity using multi-wavelength PPG.

The onset of stress triggers sympathetic arousal (SA), which causes detectable changes to physiological parameters such as heart rate, blood pressure, dilation of the pupils and sweat release. The objective quantification of SA has tremendous potential to prevent and manage psychological disorders. Photoplethysmography (PPG), a non-invasive method to measure skin blood flow changes, has been used to estimate SA indirectly. However, the impact of various wavelengths of the PPG signal has not been investigated for estimating SA. In this study, we explore the feasibility of using various statistical and nonlinear features derived from peak-to-peak (AC) values of PPG signals of different wavelengths (green, blue, infrared and red) to estimate stress-induced changes in SA and compare their performances. The impact of two physical stressors: and Hand Grip are studied on 32 healthy individuals. Linear (Mean, s.d.) and nonlinear (Katz, Petrosian, Higuchi, SampEn, TotalSampEn) features are extracted from the PPG signal's AC amplitudes to identify the onset, continuation and recovery phases of those stressors. The results show that the nonlinear features are the most promising in detecting stress-induced sympathetic activity. TotalSampEn feature was capable of detecting stress-induced changes in SA for all wavelengths, whereas other features (Petrosian, AvgSampEn) are significant (AUC ≥ 0.8) only for IR and Red wavelengths. The outcomes of this study can be used to make device design decisions as well as develop stress detection algorithms.

Individual and Conjoint Factors Associated With Beliefs About the Harmfulness of Nicotine Replacement Therapies Relative to Combustible Cigarettes Among People Who Smoke: Findings From the 2020 ITC Four Country Smoking and Vaping Survey.

INTRODUCTION: This study examined individual and conjoint factors associated with beliefs about the harmfulness of nicotine replacement therapies (NRTs) relative to combustible cigarettes (CCs). AIMS AND METHODS: Data analyzed came from 8642 adults (≥18 years) who smoked daily/weekly and participated in the 2020 ITC Four Country Smoking and Vaping Survey in Australia (n = 1213), Canada (n = 2633), England (n = 3057), and United States (n = 1739). Respondents were asked: "Compared to smoking cigarettes, how harmful do you think nicotine replacement products are?" Responses were dichotomized into "much less" versus otherwise for analysis using multivariable logistic regression models, complemented by decision-tree analysis to identify conjoint factors. RESULTS: Percentages believing that NRTs are much less harmful than CCs were 29.7% (95% CI = 26.2% to 33.5%) in Australia, 27.4% (95% CI = 25.1% to 29.8%) in England, 26.4% (95% CI = 24.4% to 28.4%) in Canada, and 21.7% (95% CI = 19.2% to 24.3%) in the United States. Across all countries, believing nicotine is not at all/slightly harmful to health (aOR = 1.53-2.27), endorsing nicotine vaping products (NVPs) as less harmful than CCs (much less harmful: aOR = 7.24-14.27; somewhat less harmful: aOR = 1.97-3.23), and possessing higher knowledge of smoking harms (aOR = 1.23-1.88) were individual factors associated with increased odds of believing NRTs are much less harmful than CCs. With some country variations, these nicotine-related measures also interacted with each other and sociodemographic variables to serve as conjoint factors associated with the likelihood of accurate NRT relative harm belief. CONCLUSIONS: Many people who regularly smoke cigarettes are unaware that NRTs are much less harmful than cigarettes. Additionally, beliefs about NRTs relative harmfulness appear to be influenced by both individual and conjoint factors. IMPLICATIONS: This study demonstrates that despite past efforts to educate people who smoke about the harms of NRTs relative to CCs, misperceptions around the relative harmfulness of NRTs remain substantial. In all four studied countries, subgroups of people who smoke regularly who are misinformed about the relative harmfulness of NRTs, and who may be reluctant to use NRTs for smoking cessation can be reliably identified for corrective interventions based on their understanding of the harms related to nicotine, NVPs and smoking along with sociodemographic markers. The identified subgroup information can be used to prioritize and inform the development of effective interventions to specifically address the gaps in knowledge and understanding of the various subgroups identified. Our results suggest these may need to be tailored for each country.

Design and development of a smartphone app for hypertension management: An intervention mapping approach.

Background: Several research studies have demonstrated the potential of mobile health apps in supporting health management. However, the design and development process of these apps are rarely presented. Objective: We present the design and development of a smartphone-based lifestyle app integrating a wearable device for hypertension management. Methods: We used an intervention mapping approach for the development of theory- and evidence-based intervention in hypertension management. This consisted of six fundamental steps: needs assessment, matrices, theoretical methods and practical strategies, program design, adoption and implementation plan, and evaluation plan. To design the contents of the intervention, we performed a literature review to determine the preferences of people with hypertension (Step 1) and necessary objectives toward the promotion of self-management behaviors (Step 2). Based on these findings, we implemented theoretical and practical strategies in consultation with stakeholders and researchers (Steps 3), which was used to identify the functionality and develop an mHealth app (Step 4). The adoption (Step 5) and evaluation (Step 6) of the mHealth app will be conducted in a future study. Results: Through the needs analysis, we identified that people with hypertension preferred having education, medication or treatment adherence, lifestyle modification, alcohol and smoking cessation and blood pressure monitoring support. We utilized MoSCoW analysis to consider four key elements, i.e., education, medication or treatment adherence, lifestyle modification and blood pressure support based on past experiences, and its potential benefits in hypertension management. Theoretical models such as (i) the information, motivation, and behavior skills model, and (ii) the patient health engagement model was implemented in the intervention development to ensure positive engagement and health behavior. Our app provides health education to people with hypertension related to their condition, while utilizing wearable devices to promote lifestyle modification and blood pressure management. The app also contains a clinician portal with rules and medication lists titrated by the clinician to ensure treatment adherence, with regular push notifications to prompt behavioral change. In addition, the app data can be reviewed by patients and clinicians as needed. Conclusions: This is the first study describing the design and development of an app that integrates a wearable blood pressure device and provides lifestyle support and hypertension management. Our theory-driven intervention for hypertension management is founded on the critical needs of people with hypertension to ensure treatment adherence and supports medication review and titration by clinicians. The intervention will be clinically evaluated in future studies to determine its effectiveness and usability.

Multi-stage sleep classification using photoplethysmographic sensor.

The conventional approach to monitoring sleep stages requires placing multiple sensors on patients, which is inconvenient for long-term monitoring and requires expert support. We propose a single-sensor photoplethysmographic (PPG)-based automated multi-stage sleep classification. This experimental study recorded the PPG during the entire night's sleep of 10 patients. Data analysis was performed to obtain 79 features from the recordings, which were then classified according to sleep stages. The classification results using support vector machine (SVM) with the polynomial kernel yielded an overall accuracy of 84.66%, 79.62% and 72.23% for two-, three- and four-stage sleep classification. These results show that it is possible to conduct sleep stage monitoring using only PPG. These findings open the opportunities for PPG-based wearable solutions for home-based automated sleep monitoring.

Domain Agnostic Post-Processing for QRS Detection Using Recurrent Neural Network.

Deep-learning-based QRS-detection algorithms often require essential post-processing to refine the output prediction-stream for R-peak localisation. The post-processing involves basic signal-processing tasks including the removal of random noise in the model's prediction stream using a basic Salt and Pepper filter, as well as, tasks that use domain-specific thresholds, including a minimum QRS size, and a minimum or maximum R-R distance. These thresholds were found to vary among QRS-detection studies and empirically determined for the target dataset, which may have implications if the target dataset differs such as the drop of performance in unknown test datasets. Moreover, these studies, in general, fail to identify the relative strengths of deep-learning models and the post-processing to weigh them appropriately. This study identifies the domain-specific post-processing, as found in the QRS-detection literature, as three steps based on the required domain knowledge. It was found that the use of minimal domain-specific post-processing is often sufficient for most of the cases and the use of additional domain-specific refinement ensures superior performance, however, it makes the process biased towards the training data and lacks generalisability. As a remedy, a domain-agnostic automated post-processing is introduced where a separate recurrent neural network (RNN)-based model learns required post-processing from the output generated from a QRS-segmenting deep learning model, which is, to the best of our knowledge, the first of its kind. The RNN-based post-processing shows superiority over the domain-specific post-processing for most of the cases (with shallow variants of the QRS-segmenting model and datasets like TWADB) and lags behind for others but with a small margin ( ≤ 2%). The consistency of the RNN-based post-processor is an important characteristic which can be utilised in designing a stable and domain agnostic QRS detector.

Performance of a Convolutional Neural Network Derived From PPG Signal in Classifying Sleep Stages.

Automatic sleep stage classification is vital for evaluating the quality of sleep. Conventionally, sleep is monitored using multiple physiological sensors that are uncomfortable for long-term monitoring and require expert intervention. In this study, we propose an automatic technique for multi-stage sleep classification using photoplethysmographic (PPG) signal. We have proposed a convolutional neural network (CNN) that learns directly from the PPG signal and classifies multiple sleep stages. We developed models for two- (Wake-Sleep), three- (Wake-NREM-REM) and four- (Wake-Light sleep-Deep sleep-REM) stages of sleep classification. Our proposed approach shows an average classification accuracy of 94.4%, 94.2%, and 92.9% for two, three, and four stages, respectively. Experimental results show that the proposed CNN model outperforms existing state-of-the-art models (classical and deep learning) in the literature.

Interpretability and Optimisation of Convolutional Neural Networks Based on Sinc-Convolution.

Interpretability often seeks domain-specific facts, which is understandable to human, from deep-learning (DL) or other machine-learning (ML) models of black-box nature. This is particularly important to establish transparency in ML model's inner-working and decision-making, so that a certain level of trust is achieved when a model is deployed in a sensitive and mission-critical context, such as health-care. Model-level transparency can be achieved when its components are transparent and are capable of explaining reason of a decision, for a given input, which can be linked to domain-knowledge. This article used convolutional neural network (CNN), with sinc-convolution as its constrained first-layer, to explore if such a model's decision-making can be explained, for a given task, by observing the sinc-convolution's sinc-kernels. These kernels work like band-pass filters, having only two parameters per kernel - lower and upper cutoff frequencies, and optimised through back-propagation. The optimised frequency-bands of sinc-kernels may provide domain-specific insights for a given task. For a given input instance, the effects of sinc-kernels was visualised by means of explanation vector, which may help to identify comparatively significant frequency-bands, that may provide domain-specific interpretation, for the given task. In addition, a CNN model was further optimised by considering the identified subset of prominent sinc frequency-bands as the constrained first-layer, which yielded comparable or better performance, as compared to its all sinc-bands counterpart, as well as, a classical CNN. A minimal CNN structure, achieved through such an optimisation process, may help design task-specific interpretable models. To the best of our knowledge, the idea of sinc-convolution layer's task-specific significant sinc-kernel-based network optimisation is the first of its kind. Additionally, the idea of explanation-vector-based joint time-frequency representation to analyse time-series signals is rare in the literature. The above concept was validated for two tasks, ECG beat-classification (five-class classification task), and R-peak localisation (sample-wise segmentation task).

Scalable Cluster Tendency Assessment for Streaming Activity Data using Recurring Shapelets.

Automatic interpretation of cluster structure in rapidly arriving data streams is essential for timely detection of interesting events. Human activities often contain bursts of repeating patterns. In this paper, we propose a new relative of the Visual Assessment of Cluster Tendency (VAT) model, to interpret cluster evolution in streaming activity data where shapes of recurring patterns are important. Existing VAT algorithms are either suitable only for small batch data and unscalable to rapidly evolving streams, or cannot capture shape patterns. Our proposed incremental algorithm processes streaming data in chunks and identifies repeating patterns or shapelets from each chunk, creating a Dictionary-of-Shapes (DoS) that is updated on the fly. Each chunk is transformed into a lower dimensional representation based on it's distance from the shapelets in the current DoS. Then a small set of transformed chunks are sampled using an intelligent Maximin Random Sampling (MMRS) scheme, to create a scalable VAT image that is incrementally updated as the data stream progresses. Experiments on two upper limb activity datasets demonstrate that the proposed method can successfully and efficiently visualize clusters in long streams of data and can also identify anomalous movements.

Robustness of electrocardiogram signal quality indices.

Electrocardiogram (ECG) signal quality indices (SQIs) are essential for improving diagnostic accuracy and reliability of ECG analysis systems. In various practical applications, the ECG signals are corrupted by different types of noise. These corrupted ECG signals often provide insufficient and incorrect information regarding a patient's health. To solve this problem, signal quality measurements should be made before an ECG signal is used for decision-making. This paper investigates the robustness of existing popular statistical signal quality indices (SSQIs): relative power of QRS complex (SQIp), skewness (SQIskew), signal-to-noise ratio (SQIsnr), higher order statistics SQI (SQIhos) and peakedness of kurtosis (SQIkur). We analysed the robustness of these SSQIs against different window sizes across diverse datasets. Results showed that the performance of SSQIs considerably fluctuates against varying datasets, whereas the impact of varying window sizes was minimal. This fluctuation occurred due to the use of a static threshold value for classifying noise-free ECG signals from the raw ECG signals. Another drawback of these SSQIs is the bias towards noise-free ECG signals, that limits their usefulness in clinical settings. In summary, the fixed threshold-based SSQIs cannot be used as a robust noise detection system. In order to solve this fixed threshold problem, other techniques can be developed using adaptive thresholds and machine-learning mechanisms.

Detection of fetal arrhythmias in non-invasive fetal ECG recordings using data-driven entropy profiling.

Objective.Fetal arrhythmias are a life-threatening disorder occurring in up to 2% of pregnancies. If identified, many fetal arrhythmias can be effectively treated using anti-arrhythmic therapies. In this paper, we present a novel method of detecting fetal arrhythmias in short length non-invasive fetal electrocardiography (NI-FECG) recordings.Approach.Our method consists of extracting a fetal heart rate time series from each NI-FECG recording and computing an entropy profile using a data-driven range of the entropy tolerance parameterr. To validate our approach, we apply our entropy profiling method to a large clinical data set of 318 NI-FECG recordings.Main Results.We demonstrate that our method (TotalSampEn) provides strong performance for classifying arrhythmic fetuses (AUC of 0.83) and outperforms entropy measures such asSampEn(AUC of 0.68) andFuzzyEn(AUC of 0.72). We also find that NI-FECG recordings incorrectly classified using the investigated entropy measures have significantly lower signal quality, and that excluding recordings of low signal quality (13.5% of recordings) increases the classification performance ofTotalSampEn(AUC of 0.90).Significance.The superior performance of our approach enables automated detection of fetal arrhythmias and warrants further investigation in a prospective clinical trial.

Wearable cuffless blood pressure monitoring devices: a systematic review and meta-analysis.

Aims: High blood pressure (BP) is the commonest modifiable cardiovascular risk factor, yet its monitoring remains problematic. Wearable cuffless BP devices offer potential solutions; however, little is known about their validity and utility. We aimed to systematically review the validity, features and clinical use of wearable cuffless BP devices. Methods and results: We searched MEDLINE, Embase, IEEE Xplore and the Cochrane Database till December 2019 for studies that reported validating cuffless BP devices. We extracted information about study characteristics, device features, validation processes, and clinical applications. Devices were classified according to their functions and features. We defined devices with a mean systolic BP (SBP) and diastolic BP (DBP) biases of <5 mmHg as valid as a consensus. Our definition of validity did not include assessment of device measurement precision, which is assessed by standard deviation of the mean difference-a critical component of ISO protocol validation criteria. Study quality was assessed using the Quality Assessment of Diagnostic Accuracy Studies version 2 tool. A random-effects model meta-analysis was performed to summarise the mean biases for SBP and DBP across studies. Of the 430 studies identified, 16 studies (15 devices, 974 participants) were selected. The majority of devices (81.3%) used photoplethysmography to estimate BP against a reference device; other technologies included tonometry, auscultation and electrocardiogram. In addition to BP and heart rate, some devices also measured night-time BP (n = 5), sleep monitoring (n = 3), oxygen saturation (n = 3), temperature (n = 2) and electrocardiogram (n = 3). Eight devices showed mean biases of <5 mmHg for SBP and DBP compared with a reference device and three devices were commercially available. The meta-analysis showed no statistically significant differences between the wearable and reference devices for SBP (pooled mean difference = 3.42 mmHg, 95% CI: -2.17, 9.01, I2 95.4%) and DBP (pooled mean = 1.16 mmHg, 95% CI: -1.26, 3.58, I2 87.1%). Conclusion: Several cuffless BP devices are currently available using different technologies, offering the potential for continuous BP monitoring. The variation in standards and validation protocols limited the comparability of findings across studies and the identification of the most accurate device. Challenges such as validation using standard protocols and in real-life settings must be overcome before they can be recommended for uptake into clinical practice.

Performance Analysis of Entropy Methods in Detecting Epileptic Seizure from Surface Electroencephalograms.

Physiological signals like Electrocardiography (ECG) and Electroencephalography (EEG) are complex and nonlinear in nature. To retrieve diagnostic information from these, we need the help of nonlinear methods of analysis. Entropy estimation is a very popular approach in the nonlinear category, where entropy estimates are used as features for signal classification and analysis. In this study, we analyze and compare the performances of four entropy methods; namely Distribution entropy (DistEn), Shannon entropy (ShanEn), Renyi entropy (RenEn) and LempelZiv complexity (LempelZiv) as classification features to detect epileptic seizure (ES) from surface Electroencephalography (sEEG) signal. Experiments were conducted on sEEG data from 23 subjects, obtained from the CHB-MIT database of PhysioNet. ShanEn, RenEn and LempelZiv entropy are found to be potential features for accurate and consistent detection of ES from sEEG, across multiple channels and subjects.

Evaluation of Mesh and Sensor Resolution for Finite Element Modeling of Non-Invasive Fetal ECG Signals.

Non-invasive fetal electrocardiography (NI-FECG) is an emerging tool with novel diagnostic potential for monitoring fetal wellbeing using electrical signals acquired from the maternal abdomen. However, variations in the geometric structure and conductivity of maternal-fetal tissues have been shown to affect the reliability of NI-FECG signals. Previous studies have utilized detailed finite element models to simulate these impacts, however this approach is computationally expensive. In this study, we investigate a range of mesh and sensor resolutions to determine an optimal trade-off between computational cost and modeling accuracy for simulating NI-FECG signals. Our results demonstrate that an optimal refinement of mesh resolution provides comparable accuracy to a detailed reference solution while requiring approximately 12 times less computation time and one-third of the memory usage. Furthermore, positioning simulated sensors at a 20 mm grid spacing provides a sufficient representation of abdominal surface potentials. These findings represent default parameters to be used in future simulations of NI-FECG signals. Code for the model utilized in this work is available under an open-source GPL license as part of the fecgsyn toolbox.Clinical Relevance- Simulating NI-FECG signals provides the opportunity to study the effects of sensor placement and maternal-fetal anatomic variations in a controlled setting. This work has relevance in determining default parameters for efficiently performing these simulations.

Measures of Bipedal Toe-Ground Clearance Asymmetry to Characterize Gait in Stroke Survivors.

Post-stroke hemiparesis often impairs gait and increases the risks of falls. Low and variable Minimum Toe Clearance (MTC) from the ground during the swing phase of the gait cycle has been identified as a major cause of such falls. In this paper, we study MTC characteristics in 30 chronic stroke patients, extracted from gait patterns during treadmill walking, using infrared sensors and motion analysis camera units. We propose objective measures to quantify MTC asymmetry between the paretic and non-paretic limbs using Poincaré analysis. We show that these subject independent Gait Asymmetry Indices (GAIs) represent temporal variations of relative MTC differences between the two limbs and can distinguish between healthy and stroke participants. Compared to traditional measures of cross-correlation between the MTC of the two limbs, these measures are better suited to automate gait monitoring during stroke rehabilitation. Further, we explore possible clusters within the stroke data by analysing temporal dispersion of MTC features, which reveals that the proposed GAIs can also be potentially used to quantify the severity of lower limb hemiparesis in chronic stroke.

Detection of Coronary Artery Disease Using Multi-Domain Feature Fusion of Multi-Channel Heart Sound Signals.

Heart sound signals reflect valuable information about heart condition. Previous studies have suggested that the information contained in single-channel heart sound signals can be used to detect coronary artery disease (CAD). But accuracy based on single-channel heart sound signal is not satisfactory. This paper proposed a method based on multi-domain feature fusion of multi-channel heart sound signals, in which entropy features and cross entropy features are also included. A total of 36 subjects enrolled in the data collection, including 21 CAD patients and 15 non-CAD subjects. For each subject, five-channel heart sound signals were recorded synchronously for 5 min. After data segmentation and quality evaluation, 553 samples were left in the CAD group and 438 samples in the non-CAD group. The time-domain, frequency-domain, entropy, and cross entropy features were extracted. After feature selection, the optimal feature set was fed into the support vector machine for classification. The results showed that from single-channel to multi-channel, the classification accuracy has increased from 78.75% to 86.70%. After adding entropy features and cross entropy features, the classification accuracy continued to increase to 90.92%. The study indicated that the method based on multi-domain feature fusion of multi-channel heart sound signals could provide more information for CAD detection, and entropy features and cross entropy features played an important role in it.

Upper limb movement profiles during spontaneous motion in acute stroke.

Objective.The clinical assessment of upper limb hemiparesis in acute stroke involves repeated manual examination of hand movements during instructed tasks. This process is labour-intensive and prone to human error as well as being strenuous for the patient. Wearable motion sensors can automate the process by measuring characteristics of hand activity. Existing work in this direction either uses multiple sensors or complex instructed movements, or analyzes only thequantityof upper limb motion. These methods are obtrusive and strenuous for acute stroke patients and are also sensitive to noise. In this work, we propose to use only two wrist-worn accelerometer sensors to study thequalityof completely spontaneous upper limb motion and investigate correlation with clinical scores for acute stroke care.Approach.The velocity time series estimated from acquired acceleration data during spontaneous motion is decomposed into smaller movement elements. Measures of density, duration and smoothness of these component elements are extracted and their disparity is studied across the two hands.Main results.Spontaneous upper limb motion in acute stroke can be decomposed into movement elements that resemble point-to-point reaching tasks. These elements are smoother and sparser in the normal hand than in the hemiparetic hand, and the amount of smoothness correlates with hemiparetic severity. Features characterizing the disparity of these movement elements between the two hands show statistical significance in differentiating mild-to-moderate and severe hemiparesis. Using data from 67 acute stroke patients, the proposed method can classify the two levels of hemiparetic severity with 85% accuracy. Additionally, compared to activity-based features, the proposed method is robust to the presence of noise in acquired data.Significance.This work demonstrates that the quality of upper limb motion can characterize and identify hemiparesis in stroke survivors. This is clinically significant towards the continuous automated assessment of hemiparesis in acute stroke using minimally intrusive wearable sensors.

Novel Measures of Similarity and Asymmetry in Upper Limb Activities for Identifying Hemiparetic Severity in Stroke Survivors.

Stroke survivors are often characterized by hemiparesis, i.e., paralysis in one half of the body, severely affecting upper limb movements. Monitoring the progression of hemiparesis requires manual observation of limb movements at regular intervals, and hence is a labour intensive process. In this work, we use wrist-worn accelerometers for automated assessment of hemiparesis in acute stroke. We propose novel measures of similarity and asymmetry in hand activities through bivariate Poincaré analysis between two-hand accelerometer data for quantifying hemiparetic severity. The proposed descriptors characterize the distribution of activity surrogates derived from acceleration of the two hands, on a 2D bivariate Poincaré Plot. Experiments show that while the descriptors CSD1 and CSD2 can identify hemiparetic patients from control subjects, their normalized difference CSDR and the descriptors Complex Cross-Correlation Measure ( C3M) and Activity Asymmetry Index ( AAI) can distinguish between mild, moderate and severe hemiparesis. These measures are compared with traditional measures of cross-correlation and evaluated against the National Institutes of Health Stroke Scale (NIHSS), the clinical gold standard for hemiparetic severity estimation. This study, undertaken on 40 acute stroke patients with varying levels of hemiparesis and 15 healthy controls, validates the use of short length ( 5 minutes) wearable accelerometry data for identifying hemiparesis with greater clinical sensitivity. Results show that the proposed descriptors with a hierarchical classification model outperform state-of-the-art methods with overall accuracy of 0.78 and 0.85 for 4-class and 3-class hemiparesis identification respectively.