Multimodal assessment of tinnitus using functional near-infrared spectroscopy and psychophysiological measures.

OBJECTIVE: To use a multimodal approach to classify individuals with tinnitus from controls, and individuals with mild versus severe tinnitus. DESIGN: We have previously shown feasibility of a non-invasive imaging technique called functional near-infrared spectroscopy (fNIRS) to detect tinnitus-related changes in cortical activity and classify individuals with tinnitus from controls, as well as individuals with mild versus severe tinnitus. In this study we have used a multimodal approach by recording heart rate, heart rate variability and skin conductance, in addition to fNIRS signals, from individuals with tinnitus and controls. STUDY SAMPLE: Twenty-seven participants with tinnitus and 21 controls were recruited. RESULTS: Our findings show, addition of heart rate measures can improve accuracy of classifying tinnitus severity, in particular loudness as rated subjectively. The f1-score, a measure of classification accuracy, increased from 0.73 to 0.86 when using a support vector machine classifier for differentiating low versus high tinnitus loudness. CONCLUSIONS: Subjective tinnitus is a condition that can only be described by the individual experiencing it, as there are currently no objective measures to determine tinnitus presence and severity, or assess the effectiveness of treatments. Objective measurement of tinnitus is a critical step in developing reliable treatments for this debilitating condition.

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.

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.

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.

Poincaré Descriptors for Identifying Hemiparesis in Acute Stroke using Wearable Accelerometry.

Stroke survivors are often characterized by hemiparesis, i.e., paralysis in one half of the body, that severely affects upper limb movements. Continuous monitoring of the progression of hemiparesis requires manual observation of the limb movements at regular intervals and hence is a labour intensive process. In this work, we use wrist-worn accelerometers for automated assessment of hemiparetic severity in acute stroke patients through bivariate Poincaré analysis between accelerometer data from the two hands during spontaneous and instructed movements. Experiments show that while the bivariate Poincaré descriptors CSD1 and CSD2 can identify hemiparetic patients from control subjects, a novel descriptor called Complex Cross-Correlation Measure (C3M) can distinguish between moderate and severe hemiparesis. Further, we justify the use of C3M by showing that it is described by multiple-lag cross-correlations, representing the co-ordination of activity between two hands. The descriptors are compared against the National Institutes of Health Stroke Scale (NIHSS), the clinical gold standard for evaluation of hemiparetic severity, and studied using statistical tests for developing supervised models for hemiparesis classification.Clinical relevance-This study establishes the suitability of wrist-worn accelerometers in identifying hemiparetic severity in stroke patients through novel descriptors of hand co-ordination.

Analyzing Distance Measures for Upper Limb Activity Measurement in Hemiparetic Stroke Patients.

Stroke survivors are often characterized by upper limb hemiparesis due to which activities in one of the hands is significantly restricted. Manual evaluation of the progression of hemiparesis in acute stroke patients involves 24x7 medical supervision, which is prone to inter-rater variability, is labor-intensive and consequently expensive in public hospitals. In this paper, we investigate the use of wrist-worn accelerometers for automated identification of upper limb hemiparesis in acute stroke. We propose a set of spontaneous and instructed movements in order to estimate two-hand activity correlation using accelerometry data. We use this information to determine the weak hand and further investigate an Activity Based Distance (ABD) measure to quantify this correlation. We compare ABD with standard time-series distance measures such as Lp norms and Dynamic Time Warping (DTW) for hemiparetic severity estimation. We study these distance measures with respect to the National Institutes of Health Stroke Scale (NIHSS), the clinical gold standard to determine hemiparetic severity, and demonstrate their suitability for developing a wearable based automated hemiparesis detection and monitoring system.Clinical relevance-This study presents a novel experimental paradigm for identifying upper limb hemiparesis in acute stroke patients using measures of two-hand activity correlation.

Automated Scoring of Hemiparesis in Acute Stroke From Measures of Upper Limb Co-Ordination Using Wearable Accelerometry.

Stroke survivors usually experience paralysis in one half of the body, i.e., hemiparesis, and the upper limbs are severely affected. Continuous monitoring of hemiparesis progression hours after the stroke attack involves manual observation of upper limb movements by medical experts in the hospital. Hence it is resource and time intensive, in addition to being prone to human errors and inter-rater variability. Wearable devices have found significance in automated continuous monitoring of neurological disorders like stroke. In this paper, we use accelerometer signals acquired using wrist-worn devices to analyze upper limb movements and identify hemiparesis in acute stroke patients, while they perform a set of proposed spontaneous and instructed movements. We propose novel measures of time (and frequency) domain coherence between accelerometer data from two arms at different lags (and frequency bands). These measures correlate well with the clinical gold standard of measurement of hemiparetic severity in stroke, the National Institutes of Health Stroke Scale (NIHSS). The study, undertaken on 32 acute stroke patients with varying levels of hemiparesis and 15 healthy controls, validates the use of short length (< 10 minutes) accelerometry data to identify hemiparesis through leave-one-subject-out cross-validation based hierarchical discriminant analysis. The results indicate that the proposed approach can distinguish between controls, moderate and severe hemiparesis with an average accuracy of 91%.

Detection of atrial fibrillation and other abnormal rhythms from ECG using a multi-layer classifier architecture.

OBJECTIVE: Atrial fibrillation (AF) and other types of abnormal heart rhythm are related to multiple fatal cardiovascular diseases that affect the quality of human life. Hence the development of an automated robust method that can reliably detect AF, in addition to other non-sinus and sinus rhythms, would be a valuable addition to medicine. The present study focuses on developing an algorithm for the classification of short, single-lead electrocardiogram (ECG) recordings into normal, AF, other abnormal rhythms and noisy classes. APPROACH: The proposed classification framework presents a two-layer, three-node architecture comprising binary classifiers. PQRST markers are detected on each ECG recording, followed by noise removal using a spectrogram power based novel adaptive thresholding scheme. Next, a feature pool comprising time, frequency, morphological and statistical domain ECG features is extracted for the classification task. At each node of the classification framework, suitable feature subsets, identified through feature ranking and dimension reduction, are selected for use. Adaptive boosting is selected as the classifier for the present case. The training data comprises 8528 ECG recordings provided under the PhysioNet 2017 Challenge. F1 scores averaged across the three non-noisy classes are taken as the performance metric. MAIN RESULT: The final five-fold cross-validation score achieved by the proposed framework on the training data has high accuracy with low variance (0.8254 [Formula: see text] 0.0043). SIGNIFICANCE: Further, the proposed algorithm has achieved joint first place in the PhysioNet/Computing in Cardiology Challenge 2017 with a score of 0.83 computed on a hidden test dataset.

A Heart Rate Driven Kalman Filter for Continuous Arousal Trend Monitoring.

This paper proposes a continuous and unsupervised approach of monitoring the arousal trend of an individual from his heart rate using Kalman Filter. The state-space model of the filter characterizes the baseline arousal condition. Deviations from this baseline model are used to recognize the arousal trend. A publicly available dataset, DECAF, comprising the physiological responses of 30 subjects while watching 36 movie clips inducing different emotions, is used to validate the proposed technique. For each clip, annotations of arousal given by experts per second are used to quantify the ground truth of arousal change. Experimental results suggest that the proposed algorithm achieves a median correlation of 0.53 between the computed and expected arousal levels which is significantly higher than that achievable by the state-of-the-art technique.

Eliminating Individual Bias to Improve Stress Detection from Multimodal Physiological Data.

Stress monitoring is important for mental wellbeing and early detection of related disorders. The current work is focused on stress detection from multiple non-invasive physiological signals like Electroencephalogram (EEG), Photoplethysmogram (PPG) and Galvanic Skin Response (GSR). We show that, compared to using only the well known EEG band powers in different frequencies for stress detection, an early fusion with GSR and PPG features shows a significant improvement. Maximum Relevance Minimum Redundancy (mRMR) based feature selection is used to identify the most suitable physiological features correlating with stress. A major contribution of this work lies in eliminating subject-specific bias to improve the classification accuracy. We use self-reported values of Valence, Arousal and Dominance to cluster subjects and build separate classification models specific to clusters. The proposed approach is validated on a publicly available dataset comprising 146 data instances from 10 subjects. The performances of Leave-One- Subject-Out cross validation (LOSOCV) in terms of mean Fscores are 0.61 using EEG features only, 0.64 using early fusion of EEG, GSR and PPG features and 0.69 by applying our clustering technique before fusion and classification.

Automated lung sound analysis for detecting pulmonary abnormalities.

Identification of pulmonary diseases comprises of accurate auscultation as well as elaborate and expensive pulmonary function tests. Prior arts have shown that pulmonary diseases lead to abnormal lung sounds such as wheezes and crackles. This paper introduces novel spectral and spectrogram features, which are further refined by Maximal Information Coefficient, leading to the classification of healthy and abnormal lung sounds. A balanced lung sound dataset, consisting of publicly available data and data collected with a low-cost in-house digital stethoscope are used. The performance of the classifier is validated over several randomly selected non-overlapping training and validation samples and tested on separate subjects for two separate test cases: (a) overlapping and (b) non-overlapping data sources in training and testing. The results reveal that the proposed method sustains an accuracy of 80% even for non-overlapping data sources in training and testing.