An Automatic Gait Analysis Pipeline for Wearable Sensors: A Pilot Study in Parkinson's Disease

Wearable sensor devices can automatically identify the ON-OFF status of patients with Parkinson's disease through an interpretable machine learning model

Introduction

Accurately and objectively quantifying the clinical features of Parkinson's disease (PD) is crucial for assisting in diagnosis and guiding the formulation of treatment plans. Therefore, based on the data on multi-site motor features, this study aimed to develop an interpretable machine learning (ML) model for classifying the "OFF" and "ON" status of patients with PD, as well as to explore the motor features that are most associated with changes in clinical symptoms.

Methods

We employed a support vector machine with a recursive feature elimination (SVM-RFE) algorithm to select promising motion features. Subsequently, 12 ML models were constructed based on these features, and we identified the model with the best classification performance. Then, we used the SHapley Additive exPlanations (SHAP) and the Local Interpretable Model agnostic Explanations (LIME) methods to explain the model and rank the importance of those motor features.

Results

A total of 96 patients were finally included in this study. The naive Bayes (NB) model had the highest classification performance (AUC = 0.956; sensitivity = 0.8947, 95% CI 0.6686-0.9870; accuracy = 0.8421, 95% CI 0.6875-0.9398). Based on the NB model, we analyzed the importance of eight motor features toward the classification results using the SHAP algorithm. The Gait: range of motion (RoM) Shank left (L) (degrees) [Mean] might be the most important motor feature for all classification horizons.

Conclusion

The symptoms of PD could be objectively quantified. By utilizing suitable motor features to construct ML models, it became possible to intelligently identify whether patients with PD were in the "ON" or "OFF" status. The variations in these motor features were significantly correlated with improvement rates in patients' quality of life. In the future, they might act as objective digital biomarkers to elucidate the changes in symptoms observed in patients with PD and might be used to assist in the diagnosis and treatment of patients with PD.

An Interpretable Deep Learning Optimized Wearable Daily Detection System for Parkinson's Disease

Walking detection in the daily life of patients with Parkinson's disease (PD) is of great significance for tracking the progress of the disease. This study aims to implement an accurate, objective, and passive detection algorithm optimized based on an interpretable deep learning architecture for the daily walking of patients with PD and to explore the most representative spatiotemporal motor features. Five inertial measurement units attached to the wrist, ankle, and waist are used to collect motion data from 100 subjects during a 10-meter walking test. The raw data of each sensor are subjected to the continuous wavelet transform to train the classification model of the constructed 6-channel convolutional neural network (CNN). The results show that the sensor located at the waist has the best classification performance with an accuracy of 98.01%±0.85% and the area under the receiver operating characteristic curve (AUC) of 0.9981±0.0017 under ten-fold cross-validation. The gradient-weighted class activation mapping shows that the feature points with greater contribution to PD were concentrated in the lower frequency band (0.5~3Hz) compared with healthy controls. The visual maps of the 3D CNN show that only three out of the six time series have a greater contribution, which is used as a basis to further optimize the model input, greatly reducing the raw data processing costs (50%) while ensuring its performance (AUC=0.9929±0.0019). To the best of our knowledge, this is the first study to consider the visual interpretation-based optimization of an intelligent classification model in the intelligent diagnosis of PD.

Enhancing Wearable Gait Monitoring Systems: Identifying Optimal Kinematic Inputs in Typical Adolescents

Machine learning-based gait systems facilitate the real-time control of gait assistive technologies in neurological conditions. Improving such systems needs the identification of kinematic signals from inertial measurement unit wearables (IMUs) that are robust across different walking conditions without extensive data processing. We quantify changes in two kinematic signals, acceleration and angular velocity, from IMUs worn on the frontal plane of bilateral shanks and thighs in 30 adolescents (8-18 years) on a treadmills and outdoor overground walking at three different speeds (self-selected, slow, and fast). Primary curve-based analyses included similarity analyses such as cosine, Euclidean distance, Poincare analysis, and a newly defined bilateral symmetry dissimilarity test (BSDT). Analysis indicated that superior-inferior shank acceleration (SI shank Acc) and medial-lateral shank angular velocity (ML shank AV) demonstrated no differences to the control signal in BSDT, indicating the least variability across the different walking conditions. Both SI shank Acc and ML shank AV were also robust in Poincare analysis. Secondary parameter-based similarity analyses with conventional spatiotemporal gait parameters were also performed. This normative dataset of walking reports raw signal kinematics that demonstrate the least to most variability in switching between treadmill and outdoor walking to help guide future machine learning models to assist gait in pediatric neurological conditions.

Gait Monitoring and Analysis: A Mathematical Approach

Gait abnormalities are common in the elderly and individuals diagnosed with Parkinson's, often leading to reduced mobility and increased fall risk. Monitoring and assessing gait patterns in these populations play a crucial role in understanding disease progression, early detection of motor impairments, and developing personalized rehabilitation strategies. In particular, by identifying gait irregularities at an early stage, healthcare professionals can implement timely interventions and personalized therapeutic approaches, potentially delaying the onset of severe motor symptoms and improving overall patient outcomes. In this paper, we studied older adults affected by chronic diseases and/or Parkinson's disease by monitoring their gait due to wearable devices that can accurately detect a person's movements. In our study, about 50 people were involved in the trial (20 with Parkinson's disease and 30 people with chronic diseases) who have worn our device for at least 6 months. During the experimentation, each device collected 25 samples from the accelerometer sensor for each second. By analyzing those data, we propose a metric for the "gait quality" based on the measure of entropy obtained by applying the Fourier transform.

Machine Learning Techniques for Developing Remotely Monitored Central Nervous System Biomarkers Using Wearable Sensors: A Narrative Literature Review

BACKGROUND

Central nervous system (CNS) disorders benefit from ongoing monitoring to assess disease progression and treatment efficacy. Mobile health (mHealth) technologies offer a means for the remote and continuous symptom monitoring of patients. Machine Learning (ML) techniques can process and engineer mHealth data into a precise and multidimensional biomarker of disease activity.

OBJECTIVE

This narrative literature review aims to provide an overview of the current landscape of biomarker development using mHealth technologies and ML. Additionally, it proposes recommendations to ensure the accuracy, reliability, and interpretability of these biomarkers.

METHODS

This review extracted relevant publications from databases such as PubMed, IEEE, and CTTI. The ML methods employed across the selected publications were then extracted, aggregated, and reviewed.

RESULTS

This review synthesized and presented the diverse approaches of 66 publications that address creating mHealth-based biomarkers using ML. The reviewed publications provide a foundation for effective biomarker development and offer recommendations for creating representative, reproducible, and interpretable biomarkers for future clinical trials.

CONCLUSION

mHealth-based and ML-derived biomarkers have great potential for the remote monitoring of CNS disorders. However, further research and standardization of study designs are needed to advance this field. With continued innovation, mHealth-based biomarkers hold promise for improving the monitoring of CNS disorders.

Validity and reliability of the Apple Health app on iPhone for measuring gait parameters in children, adults, and seniors

This study assessed the concurrent validity and test-retest-reliability of the Apple Health app on iPhone for measuring gait parameters in different age groups. Twenty-seven children, 28 adults and 28 seniors equipped with an iPhone completed a 6-min walk test (6MWT). Gait speed (GS), step length (SL), and double support time (DST) were extracted from the gait recordings of the Health app. Gait parameters were simultaneously collected with an inertial sensors system (APDM Mobility Lab) to assess concurrent validity. Test-retest reliability was assessed via a second iPhone-instrumented 6MWT 1 week later. Agreement of the Health App with the APDM Mobility Lab was good for GS in all age groups and for SL in adults/seniors, but poor to moderate for DST in all age groups and for SL in children. Consistency between repeated measurements was good to excellent for all gait parameters in adults/seniors, and moderate to good for GS and DST but poor for SL in children. The Health app on iPhone is reliable and valid for measuring GS and SL in adults and seniors. Careful interpretation is required when using the Health app in children and when measuring DST in general, as both have shown limited validity and/or reliability.

A Single Wearable Sensor for Gait Analysis in Parkinson’s Disease: A Preliminary Study

Movement monitoring in patients with Parkinson’s disease (PD) is critical for quantifying disease progression and assessing how a subject responds to medication administration over time. In this work, we propose a continuous monitoring system based on a single wearable sensor placed on the lower back and an algorithm for gait parameters evaluation. In order to preliminarily validate the proposed system, seven PD subjects took part in an experimental protocol in preparation for a larger randomized controlled study. We validated the feasibility of our algorithm in a constrained environment through a laboratory scenario. Successively, it was tested in an unsupervised environment, such as the home scenario, for a total of almost 12 h of daily living activity data. During all phases of the experimental protocol, videos were shot to document the tasks. The obtained results showed a good accuracy of the proposed algorithm. For all PD subjects in the laboratory scenario, the algorithm for step identification reached a percentage error low of 2%, 99.13% of sensitivity and 100% of specificity. In the home scenario the Bland–Altman plot showed a mean difference of −3.29 and −1 between the algorithm and the video recording for walking bout detection and steps identification, respectively.

Validity and Reliability of a Smartphone App for Gait and Balance Assessment

Advances in technology provide an opportunity to enhance the accuracy of gait and balance assessment, improving the diagnosis and rehabilitation processes for people with acute or chronic health conditions. This study investigated the validity and reliability of a smartphone-based application to measure postural stability and spatiotemporal aspects of gait during four static balance and two gait tasks. Thirty healthy participants (aged 20–69 years) performed the following tasks: (1) standing on a firm surface with eyes opened, (2) standing on a firm surface with eyes closed, (3) standing on a compliant surface with eyes open, (4) standing on a compliant surface with eyes closed, (5) walking in a straight line, and (6) walking in a straight line while turning their head from side to side. During these tasks, the app quantified the participants’ postural stability and spatiotemporal gait parameters. The concurrent validity of the smartphone app with respect to a 3D motion capture system was evaluated using partial Pearson’s correlations (r_p) and limits of the agreement (LoA%). The within-session test–retest reliability over three repeated measures was assessed with the intraclass correlation coefficient (ICC) and the standard error of measurement (SEM). One-way repeated measures analyses of variance (ANOVAs) were used to evaluate responsiveness to differences across tasks and repetitions. Periodicity index, step length, step time, and walking speed during the gait tasks and postural stability outcomes during the static tasks showed moderate-to-excellent validity (0.55 ≤ r_p ≤ 0.98; 3% ≤ LoA% ≤ 12%) and reliability scores (0.52 ≤ ICC ≤ 0.92; 1% ≤ SEM% ≤ 6%) when the repetition effect was removed. Conversely, step variability and asymmetry parameters during both gait tasks generally showed poor validity and reliability except step length asymmetry, which showed moderate reliability (0.53 ≤ ICC ≤ 0.62) in both tasks when the repetition effect was removed. Postural stability and spatiotemporal gait parameters were found responsive (p < 0.05) to differences across tasks and test repetitions. Along with sound clinical judgement, the app can potentially be used in clinical practice to detect gait and balance impairments and track the effectiveness of rehabilitation programs. Further evaluation and refinement of the app in people with significant gait and balance deficits is needed.