IMU-Based Classification of Parkinson's Disease From Gait: A Sensitivity Analysis on Sensor Location and Feature Selection

NSF DARE-transforming modeling in neurorehabilitation: a patient-in-the-loop framework

In 2023, the National Science Foundation (NSF) and the National Institute of Health (NIH) brought together engineers, scientists, and clinicians by sponsoring a conference on computational modelling in neurorehabiilitation. To facilitate multidisciplinary collaborations and improve patient care, in this perspective piece we identify where and how computational modelling can support neurorehabilitation. To address the where, we developed a patient-in-the-loop framework that uses multiple and/or continual measurements to update diagnostic and treatment model parameters, treatment type, and treatment prescription, with the goal of maximizing clinically-relevant functional outcomes. This patient-in-the-loop framework has several key features: (i) it includes diagnostic and treatment models, (ii) it is clinically-grounded with the International Classification of Functioning, Disability and Health (ICF) and patient involvement, (iii) it uses multiple or continual data measurements over time, and (iv) it is applicable to a range of neurological and neurodevelopmental conditions. To address the how, we identify state-of-the-art and highlight promising avenues of future research across the realms of sensorimotor adaptation, neuroplasticity, musculoskeletal, and sensory & pain computational modelling. We also discuss both the importance of and how to perform model validation, as well as challenges to overcome when implementing computational models within a clinical setting. The patient-in-the-loop approach offers a unifying framework to guide multidisciplinary collaboration between computational and clinical stakeholders in the field of neurorehabilitation.

Gait classification for early detection and severity rating of Parkinson's disease based on hybrid signal processing and machine learning methods

Parkinson's disease (PD) is one of the cognitive degenerative disorders of the central nervous system that affects the motor system. Gait dysfunction represents the pathology of motor symptom while gait analysis provides clinicians with subclinical information reflecting subtle differences between PD patients and healthy controls (HCs). Currently neurologists usually assess several clinical manifestations of the PD patients and rate the severity level according to some established criteria. This is highly dependent on clinician's expertise which is subjective and ineffective. In the present study we address these issues by proposing a hybrid signal processing and machine learning based gait classification system for gait anomaly detection and severity rating of PD patients. Time series of vertical ground reaction force (VGRF) data are utilized to represent discriminant gait information. First, phase space of the VGRF is reconstructed, in which the properties associated with the nonlinear gait system dynamics are preserved. Then Shannon energy is used to extract the characteristic envelope of the phase space signal. Third, Shannon energy envelope is decomposed into high and low resonance components using dual Q-factor signal decomposition derived from tunable Q-factor wavelet transform. Note that the high Q-factor component consists largely of sustained oscillatory behavior, while the low Q-factor component consists largely of transients and oscillations that are not sustained. Fourth, variational mode decomposition is employed to decompose high and low resonance components into different intrinsic modes and provide representative features. Finally features are fed to five different types of machine learning based classifiers for the anomaly detection and severity rating of PD patients based on Hohen and Yahr (HY) scale. The effectiveness of this strategy is verified using a Physionet gait database consisting of 93 idiopathic PD patients and 73 age-matched asymptomatic HCs. When evaluated with 10-fold cross-validation method for early PD detection and severity rating, the highest classification accuracy is reported to be 98.20 % and 96.69 % , respectively, by using the support vector machine classifier. Compared with other state-of-the-art methods, the results demonstrate superior performance and support the validity of the proposed method.

Machine learning to detect, stage and classify diseases and their symptoms based on inertial sensor data: a mapping review

This article presents a systematic review aimed at mapping the literature published in the last decade on the use of machine learning (ML) for clinical decision-making through wearable inertial sensors. The review aims to analyze the trends, perspectives, strengths, and limitations of current literature in integrating ML and inertial measurements for clinical applications. The review process involved defining four research questions and applying four relevance assessment indicators to filter the search results, providing insights into the pathologies studied, technologies and setups used, data processing schemes, ML techniques applied, and their clinical impact. When combined with ML techniques, inertial measurement units (IMUs) have primarily been utilized to detect and classify diseases and their associated motor symptoms. They have also been used to monitor changes in movement patterns associated with the presence, severity, and progression of pathology across a diverse range of clinical conditions. ML models trained with IMU data have shown potential in improving patient care by objectively classifying and predicting motor symptoms, often with a minimally encumbering setup. The findings contribute to understanding the current state of ML integration with wearable inertial sensors in clinical practice and identify future research directions. Despite the widespread adoption of these technologies and techniques in clinical applications, there is still a need to translate them into routine clinical practice. This underscores the importance of fostering a closer collaboration between technological experts and professionals in the medical field.

Evaluating the ability of a predictive vision-based machine learning model to measure changes in gait in response to medication and DBS within individuals with Parkinson's disease

INTRODUCTION

Gait impairments in Parkinson's disease (PD) are treated with dopaminergic medication or deep-brain stimulation (DBS), although the magnitude of the response is variable between individuals. Computer vision-based approaches have previously been evaluated for measuring the severity of parkinsonian gait in videos, but have not been evaluated for their ability to identify changes within individuals in response to treatment. This pilot study examines whether a vision-based model, trained on videos of parkinsonism, is able to detect improvement in parkinsonian gait in people with PD in response to medication and DBS use.

METHODS

A spatial-temporal graph convolutional model was trained to predict MDS-UPDRS-gait scores in 362 videos from 14 older adults with drug-induced parkinsonism. This model was then used to predict MDS-UPDRS-gait scores on a different dataset of 42 paired videos from 13 individuals with PD, recorded while ON and OFF medication and DBS treatment during the same clinical visit. Statistical methods were used to assess whether the model was responsive to changes in gait in the ON and OFF states.

RESULTS

The MDS-UPDRS-gait scores predicted by the model were lower on average (representing improved gait; p = 0.017, Cohen's d = 0.495) during the ON medication and DBS treatment conditions. The magnitude of the differences between ON and OFF state was significantly correlated between model predictions and clinician annotations (p = 0.004). The predicted scores were significantly correlated with the clinician scores (Kendall's tau-b = 0.301, p = 0.010), but were distributed in a smaller range as compared to the clinician scores.

CONCLUSION

A vision-based model trained on parkinsonian gait did not accurately predict MDS-UPDRS-gait scores in a different PD cohort, but detected weak, but statistically significant proportional changes in response to medication and DBS use. Large, clinically validated datasets of videos captured in many different settings and treatment conditions are required to develop accurate vision-based models of parkinsonian gait.

Automatic Detection of Magnetic Disturbances in Magnetic Inertial Measurement Unit Sensors Based on Recurrent Neural Networks

This paper proposes a new methodology for the automatic detection of magnetic disturbances from magnetic inertial measurement unit (MIMU) sensors based on deep learning. The proposed approach considers magnetometer data as input to a long short-term memory (LSTM) neural network and obtains a labeled time series output with the posterior probabilities of magnetic disturbance. We trained our algorithm on a data set that reproduces a wide range of magnetic perturbations and MIMU motions in a repeatable and reproducible way. The model was trained and tested using 15 folds, which considered independence in sensor, disturbance direction, and signal type. On average, the network can adequately detect the disturbances in 98% of the cases, which represents a significant improvement over current threshold-based detection algorithms.

Applications of Machine Learning to Diagnosis of Parkinson's Disease

BACKGROUND

Accurate diagnosis of Parkinson's disease (PD) is challenging due to its diverse manifestations. Machine learning (ML) algorithms can improve diagnostic precision, but their generalizability across medical centers in China is underexplored.

OBJECTIVE

To assess the accuracy of an ML algorithm for PD diagnosis, trained and tested on data from different medical centers in China.

METHODS

A total of 1656 participants were included, with 1028 from Beijing (training set) and 628 from Fuzhou (external validation set). Models were trained using the least absolute shrinkage and selection operator-logistic regression (LASSO-LR), decision tree (DT), random forest (RF), eXtreme gradient boosting (XGboost), support vector machine (SVM), and k-nearest neighbor (KNN) techniques. Hyperparameters were optimized using five-fold cross-validation and grid search techniques. Model performance was evaluated using the area under the curve (AUC) of the receiver operating characteristic (ROC) curve, accuracy, sensitivity (recall), specificity, precision, and F1 score. Variable importance was assessed for all models.

RESULTS

SVM demonstrated the best differentiation between healthy controls (HCs) and PD patients (AUC: 0.928, 95% CI: 0.908-0.947; accuracy: 0.844, 95% CI: 0.814-0.871; sensitivity: 0.826, 95% CI: 0.786-0.866; specificity: 0.861, 95% CI: 0.820-0.898; precision: 0.849, 95% CI: 0.807-0.891; F1 score: 0.837, 95% CI: 0.803-0.868) in the validation set. Constipation, olfactory decline, and daytime somnolence significantly influenced predictability.

CONCLUSION

We identified multiple pivotal variables and SVM as a precise and clinician-friendly ML algorithm for prediction of PD in Chinese patients.

Wearable multisource quantitative gait analysis of Parkinson's diseases

As the motor symptoms of Parkinson's disease (PD) are complex and influenced by many factors, it is challenging to quantify gait abnormalities adequately using a single type of signal. Therefore, a wearable multisource gait monitoring system is developed to perform a quantitative analysis of gait abnormalities for improving the effectiveness of the clinical diagnosis. To detect multisource gait data for an accurate evaluation of gait abnormalities, force sensitive sensors, piezoelectric sensors, and inertial measurement units are integrated into the devised device. The modulation circuits and wireless framework are designed to simultaneously collect plantar pressure, dynamic deformation, and postural angle of the foot and then wirelessly transmit these collected data. With the designed system, multisource gait data from PD patients and healthy controls are collected. Multisource features for quantifying gait abnormalities are extracted and evaluated by a significance test of difference and correlation analysis. The results show that the features extracted from every single type of data are able to quantify the health status of the subjects (p < 0.001, ρ > 0.50). More importantly, the validity of multisource gait data is verified. The results demonstrate that the gait feature fusing multisource data achieves a maximum correlation coefficient of 0.831, a maximum Area Under Curve of 0.9206, and a maximum feature-based classification accuracy of 88.3%. The system proposed in this study can be applied to the gait analysis and objective evaluation of PD.

New era of artificial intelligence and machine learning-based detection, diagnosis, and therapeutics in Parkinson's disease

Parkinson's disease (PD) is characterized by the loss of neuronal cells, which leads to synaptic dysfunction and cognitive defects. Despite the advancements in treatment strategies, the management of PD is still a challenging event. Early prediction and diagnosis of PD are of utmost importance for effective management of PD. In addition, the classification of patients with PD as compared to normal healthy individuals also imposes drawbacks in the early diagnosis of PD. To address these challenges, artificial intelligence (AI) and machine learning (ML) models have been implicated in the diagnosis, prediction, and treatment of PD. Recent times have also demonstrated the implication of AI and ML models in the classification of PD based on neuroimaging methods, speech recording, gait abnormalities, and others. Herein, we have briefly discussed the role of AI and ML in the diagnosis, treatment, and identification of novel biomarkers in the progression of PD. We have also highlighted the role of AI and ML in PD management through altered lipidomics and gut-brain axis. We briefly explain the role of early PD detection through AI and ML algorithms based on speech recordings, handwriting patterns, gait abnormalities, and neuroimaging techniques. Further, the review discuss the potential role of the metaverse, the Internet of Things, and electronic health records in the effective management of PD to improve the quality of life. Lastly, we also focused on the implementation of AI and ML-algorithms in neurosurgical process and drug discovery.

Objective wearable measures correlate with self-reported chronic pain levels in people with spinal cord stimulation systems

Spinal Cord Stimulation (SCS) is a well-established therapy for treating chronic pain. However, perceived treatment response to SCS therapy may vary among people with chronic pain due to diverse needs and backgrounds. Patient Reported Outcomes (PROs) from standard survey questions do not provide the full picture of what has happened to a patient since their last visit, and digital PROs require patients to visit an app or otherwise regularly engage with software. This study aims to assess the feasibility of using digital biomarkers collected from wearables during SCS treatment to predict pain and PRO outcomes. Twenty participants with chronic pain were recruited and implanted with SCS. During the six months of the study, activity and physiological metrics were collected and data from 15 participants was used to develop a machine learning pipeline to objectively predict pain levels and categories of PRO measures. The model reached an accuracy of 0.768 ± 0.012 in predicting the pain intensity of mild, moderate, and severe. Feature importance analysis showed that digital biomarkers from the smartwatch such as heart rate, heart rate variability, step count, and stand time can contribute to modeling different aspects of pain. The results of the study suggest that wearable biomarkers can be used to predict therapy outcomes in people with chronic pain, enabling continuous, real-time monitoring of patients during the use of implanted therapies.

Classification of mild Parkinson's disease: data augmentation of time-series gait data obtained via inertial measurement units

Data-augmentation methods have emerged as a viable approach for improving the state-of-the-art performances for classifying mild Parkinson's disease using deep learning with time-series data from an inertial measurement unit, considering the limited amount of training datasets available in the medical field. This study investigated effective data-augmentation methods to classify mild Parkinson's disease and healthy participants with deep learning using a time-series gait dataset recorded via a shank-worn inertial measurement unit. Four magnitude-domain-transformation and three time-domain-transformation data-augmentation methods, and four methods involving mixtures of the aforementioned methods were applied to a representative convolutional neural network for the classification, and their performances were compared. In terms of data-augmentation, compared with baseline classification accuracy without data-augmentation, the magnitude-domain transformation performed better than the time-domain transformation and mixed-data augmentation. In the magnitude-domain transformation, the rotation method significantly contributed to the best performance improvement, yielding accuracy and F1-score improvements of 5.5 and 5.9%, respectively. The augmented data could be varied while maintaining the features of the time-series data obtained via the sensor for detecting mild Parkinson's in gait; this data attribute may have caused the aforementioned trend. Notably, the selection of appropriate data extensions will help improve the classification performance for mild Parkinson's disease.

Objective measurement versus clinician-based assessment for Parkinson's disease

INTRODUCTION

Although clinician-based assessment through standardized clinical rating scales is currently the gold standard for quantifying motor impairment in Parkinson's disease (PD), it is not without limitations, including intra- and inter-rater variability and a degree of approximation. There is increasing evidence supporting the use of objective motion analyses to complement clinician-based assessment. Objective measurement tools hold significant potential for improving the accuracy of clinical and research-based evaluations of patients.

AREAS COVERED

The authors provide several examples from the literature demonstrating how different motion measurement tools, including optoelectronics, contactless and wearable systems allow for both the objective quantification and monitoring of key motor symptoms (such as bradykinesia, rigidity, tremor, and gait disturbances), and the identification of motor fluctuations in PD patients. Furthermore, they discuss how, from a clinician's perspective, objective measurements can help in various stages of PD management.

EXPERT OPINION

In our opinion, sufficient evidence supports the assertion that objective monitoring systems enable accurate evaluation of motor symptoms and complications in PD. A range of devices can be utilized not only to support diagnosis but also to monitor motor symptom during the disease progression and can become relevant in the therapeutic decision-making process.

Objective wearable measures and subjective questionnaires for predicting response to neurostimulation in people with chronic pain

BACKGROUND

Neurostimulation is an effective therapy for treating and management of refractory chronic pain. However, the complex nature of pain and infrequent in-clinic visits, determining subject's long-term response to the therapy remains difficult. Frequent measurement of pain in this population can help with early diagnosis, disease progression monitoring, and evaluating long-term therapeutic efficacy. This paper compares the utilization of the common subjective patient-reported outcomes with objective measures captured through a wearable device for predicting the response to neurostimulation therapy.

METHOD

Data is from the ongoing international prospective post-market REALITY clinical study, which collects long-term patient-reported outcomes from 557 subjects implanted by Spinal Cord Stimulator (SCS) or Dorsal Root Ganglia (DRG) neurostimulators. The REALITY sub-study was designed for collecting additional wearables data on a subset of 20 participants implanted with SCS devices for up to six months post implantation. We first implemented a combination of dimensionality reduction algorithms and correlation analyses to explore the mathematical relationships between objective wearable data and subjective patient-reported outcomes. We then developed machine learning models to predict therapy outcome based on the subject's response to the numerical rating scale (NRS) or patient global impression of change (PGIC).

RESULTS

Principal component analysis showed that psychological aspects of pain were associated with heart rate variability, while movement-related measures were strongly associated with patient-reported outcomes related to physical function and social role participation. Our machine learning models using objective wearable data predicted PGIC and NRS outcomes with high accuracy without subjective data. The prediction accuracy was higher for PGIC compared with the NRS using subjective-only measures primarily driven by the patient satisfaction feature. Similarly, the PGIC questions reflect an overall change since the study onset and could be a better predictor of long-term neurostimulation therapy outcome.

CONCLUSIONS

The significance of this study is to introduce a novel use of wearable data collected from a subset of patients to capture multi-dimensional aspects of pain and compare the prediction power with the subjective data from a larger data set. The discovery of pain digital biomarkers could result in a better understanding of the patient's response to therapy and their general well-being.

Evaluating Gait Impairment in Parkinson's Disease from Instrumented Insole and IMU Sensor Data

Parkinson's disease (PD) is characterized by a variety of motor and non-motor symptoms, some of them pertaining to gait and balance. The use of sensors for the monitoring of patients' mobility and the extraction of gait parameters, has emerged as an objective method for assessing the efficacy of their treatment and the progression of the disease. To that end, two popular solutions are pressure insoles and body-worn IMU-based devices, which have been used for precise, continuous, remote, and passive gait assessment. In this work, insole and IMU-based solutions were evaluated for assessing gait impairment, and were subsequently compared, producing evidence to support the use of instrumentation in everyday clinical practice. The evaluation was conducted using two datasets, generated during a clinical study, in which patients with PD wore, simultaneously, a pair of instrumented insoles and a set of wearable IMU-based devices. The data from the study were used to extract and compare gait features, independently, from the two aforementioned systems. Subsequently, subsets comprised of the extracted features, were used by machine learning algorithms for gait impairment assessment. The results indicated that insole gait kinematic features were highly correlated with those extracted from IMU-based devices. Moreover, both had the capacity to train accurate machine learning models for the detection of PD gait impairment.

Optimal locations and computational frameworks of FSR and IMU sensors for measuring gait abnormalities

Neuromuscular diseases cause abnormal joint movements and drastically alter gait patterns in patients. The analysis of abnormal gait patterns can provide clinicians with an in-depth insight into implementing appropriate rehabilitation therapies. Wearable sensors are used to measure the gait patterns of neuromuscular patients due to their non-invasive and cost-efficient characteristics. FSR and IMU sensors are the most popular and efficient options. When assessing abnormal gait patterns, it is important to determine the optimal locations of FSRs and IMUs on the human body, along with their computational framework. The gait abnormalities of different types and the gait analysis systems based on IMUs and FSRs have therefore been investigated. After studying a variety of research articles, the optimal locations of the FSR and IMU sensors were determined by analysing the main pressure points under the feet and prime anatomical locations on the human body. A total of seven locations (the big toe, heel, first, third, and fifth metatarsals, as well as two close to the medial arch) can be used to measure gate cycles for normal and flat feet. It has been found that IMU sensors can be placed in four standard anatomical locations (the feet, shank, thigh, and pelvis). A section on computational analysis is included to illustrate how data from the FSR and IMU sensors are processed. Sensor data is typically sampled at 100 Hz, and wireless systems use a range of microcontrollers to capture and transmit the signals. The findings reported in this article are expected to help develop efficient and cost-effective gait analysis systems by using an optimal number of FSRs and IMUs.

Automatic Assessments of Parkinsonian Gait with Wearable Sensors for Human Assistive Systems

The rehabilitation evaluation of Parkinson's disease has always been the research focus of human assistive systems. It is a research hotspot to objectively and accurately evaluate the gait condition of Parkinson's disease patients, thereby adjusting the actuators of the human-machine system and making rehabilitation robots better adapt to the recovery process of patients. The rehabilitation evaluation of Parkinson's disease has always been the research focus of rehabilitation robots. It is a research hotspot to be able to objectively and accurately evaluate the recovery of Parkinson's disease patients, thereby adjusting the driving module of the human-machine collaboration system in real time, so that rehabilitation robots can better adapt to the recovery process of Parkinson's disease. The gait task in the Unified Parkinson's Disease Rating Scale (UPDRS) is a widely accepted standard for assessing the gait impairments of patients with Parkinson's disease (PD). However, the assessments conducted by neurologists are always subjective and inaccurate, and the results are determined by the neurologists' observation and clinical experience. Thus, in this study, we proposed a novel machine learning-based method of automatically assessing the gait task in UPDRS with wearable sensors as a more convenient and objective alternative means for PD gait assessment. In the design, twelve gait features, including three spatial-temporal features and nine kinematic features, were extracted and calculated from two shank-mounted IMUs. A novel nonlinear model is developed for calculating the score of gait task from the gait features. Twenty-five PD patients and twenty-eight healthy subjects were recruited for validating the proposed method. For comparison purpose, three traditional models, which have been used in previous studies, were also tested by the same dataset. In terms of percentages of participants, 84.9%, 73.6%, 73.6%, and 66.0% of the participants were accurately assigned into the true level with the proposed nonlinear model, the support vector machine model, the naive Bayes model, and the linear regression model, respectively, which indicates that the proposed method has a good performance on calculating the score of the UPDRS gait task and conformance with the rating done by neurologists.

Artificial Neural Network-Based Activities Classification, Gait Phase Estimation, and Prediction

Gait patterns are critical to health monitoring, gait impairment assessment, and wearable device control. Unrhythmic gait pattern detection under community-based conditions is a new frontier in this area. The present paper describes a high-accuracy gait phase estimation and prediction algorithm built on a two-stage artificial neural network. This work targets to develop an algorithm that can estimate and predict the gait cycle in real time using a portable controller with only two IMU sensors (one on each thigh) in the community setting. Our algorithm can detect the gait phase in unrhythmic conditions during walking, stair ascending, and stair descending, and classify these activities with standing. Moreover, our algorithm is able to predict both future intra- and inter-stride gait phases, offering a potential means to improve wearable device controller performance. The proposed data-driven algorithm is based on a dataset consisting of 5 able-bodied subjects and validated on 3 different able-bodied subjects. Under unrhythmic activity situations, validation shows that the algorithm can accurately identify multiple activities with 99.55% accuracy, and estimate ([Formula: see text]: 6.3%) and predict 200-ms-ahead ([Formula: see text]: 8.6%) the gait phase percentage in real time, which are on average 57.7 and 54.0% smaller than the error from the event-based method in the same conditions. This study showcases a solution to estimate and predict gait status for multiple unrhythmic activities, which may be deployed to controllers for wearable robots or health monitoring devices.

Classification of Kinematic and Electromyographic Signals Associated with Pathological Tremor Using Machine and Deep Learning

Peripheral Electrical Stimulation (PES) of afferent pathways has received increased interest as a solution to reduce pathological tremors with minimal side effects. Closed-loop PES systems might present some advantages in reducing tremors, but further developments are required in order to reliably detect pathological tremors to accurately enable the stimulation only if a tremor is present. This study explores different machine learning (K-Nearest Neighbors, Random Forest and Support Vector Machines) and deep learning (Long Short-Term Memory neural networks) models in order to provide a binary (Tremor; No Tremor) classification of kinematic (angle displacement) and electromyography (EMG) signals recorded from patients diagnosed with essential tremors and healthy subjects. Three types of signal sequences without any feature extraction were used as inputs for the classifiers: kinematics (wrist flexion-extension angle), raw EMG and EMG envelopes from wrist flexor and extensor muscles. All the models showed high classification scores (Tremor vs. No Tremor) for the different input data modalities, ranging from 0.8 to 0.99 for the f₁ score. The LSTM models achieved 0.98 f₁ scores for the classification of raw EMG signals, showing high potential to detect tremors without any processed features or preliminary information. These models may be explored in real-time closed-loop PES strategies to detect tremors and enable stimulation with minimal signal processing steps.

Classification of Vogt-Koyanagi-Harada disease using feature selection and classification based on wide-field swept-source optical coherence tomography angiography

Background: Vogt-Koyanagi-Harada (VKH) disease is a common and easily blinded uveitis entity, with choroid being the main involved site. Classification of VKH disease and its different stages is crucial because they differ in clinical manifestations and therapeutic interventions. Wide-field swept-source optical coherence tomography angiography (WSS-OCTA) provides the advantages of non-invasiveness, large-field-of-view, high resolution, and ease of measuring and calculating choroid, offering the potential feasibility of simplified VKH classification assessment based on WSS-OCTA. Methods: 15 healthy controls (HC), 13 acute-phase and 17 convalescent-phase VKH patients were included, undertaken WSS-OCTA examination with a scanning field of 15 × 9 mm². 20 WSS-OCTA parameters were then extracted from WSS-OCTA images. To classify HC and VKH patients in acute and convalescent phases, two 2-class VKH datasets (HC and VKH) and two 3-class VKH datasets (HC, acute-phase VKH, and convalescent-phase VKH) were established by the WSS-OCTA parameters alone or in combination with best-corrected visual acuity (logMAR BCVA) and intraocular pressure (IOP), respectively. A new feature selection and classification method that combines an equilibrium optimizer and a support vector machine (called SVM-EO) was adopted to select classification-sensitive parameters among the massive datasets and to achieve outstanding classification performance. The interpretability of the VKH classification models was demonstrated based on SHapley Additive exPlanations (SHAP). Results: Based on pure WSS-OCTA parameters, we achieved classification accuracies of 91.61% ± 12.17% and 86.69% ± 8.30% for 2- and 3-class VKH classification tasks. By combining the WSS-OCTA parameters and logMAR BCVA, we achieved better classification performance of 98.82% ± 2.63% and 96.16% ± 5.88%, respectively. Through SHAP analysis, we found that logMAR BCVA and vascular perfusion density (VPD) calculated from the whole field of view region in the choriocapillaris (whole FOV CC-VPD) were the most important features for VKH classification in our models. Conclusion: We achieved excellent VKH classification performance based on a non-invasive WSS-OCTA examination, which provides the possibility for future clinical VKH classification with high sensitivity and specificity.

Parkinson's disease classification with CWNN: Using wavelet transformations and IMU data fusion for improved accuracy

BACKGROUND

Parkinson's disease (PD) is a chronic neurodegenerative disorder characterized by motor impairments and various other symptoms. Early and accurate classification of PD patients is crucial for timely intervention and personalized treatment. Inertial measurement units (IMUs) have emerged as a promising tool for gathering movement data and aiding in PD classification.

OBJECTIVE

This paper proposes a Convolutional Wavelet Neural Network (CWNN) approach for PD classification using IMU data. CWNNs have emerged as effective models for sensor data classification. The objective is to determine the optimal combination of wavelet transform and IMU data type that yields the highest classification accuracy for PD.

METHODS

The proposed CWNN architecture integrates convolutional neural networks and wavelet neural networks to capture spatial and temporal dependencies in IMU data. Different wavelet functions, such as Morlet, Mexican Hat, and Gaussian, are employed in the continuous wavelet transform (CWT) step. The CWNN is trained and evaluated using various combinations of accelerometer data, gyroscope data, and fusion data.

RESULTS

Extensive experiments are conducted using a comprehensive dataset of IMU data collected from individuals with and without PD. The performance of the proposed CWNN is evaluated in terms of classification accuracy, precision, recall, and F1-score. The results demonstrate the impact of different wavelet functions and IMU data types on PD classification performance, revealing that the combination of Morlet wavelet function and IMU data fusion achieves the highest accuracy.

CONCLUSION

The findings highlight the significance of combining CWT with IMU data fusion for PD classification using CWNNs. The integration of CWT-based feature extraction and the fusion of IMU data from multiple sensors enhance the representation of PD-related patterns, leading to improved classification accuracy. This research provides valuable insights into the potential of CWT and IMU data fusion for advancing PD classification models, enabling more accurate and reliable diagnosis.

Wearable sensors and features for diagnosis of neurodegenerative diseases: A systematic review

Objective

Neurodegenerative diseases affect millions of families around the world, while various wearable sensors and corresponding data analysis can be of great support for clinical diagnosis and health assessment. This systematic review aims to provide a comprehensive overview of the existing research that uses wearable sensors and features for the diagnosis of neurodegenerative diseases.

Methods

A systematic review was conducted of studies published between 2015 and 2022 in major scientific databases such as Web of Science, Google Scholar, PubMed, and Scopes. The obtained studies were analyzed and organized into the process of diagnosis: wearable sensors, feature extraction, and feature selection.

Results

The search led to 171 eligible studies included in this overview. Wearable sensors such as force sensors, inertial sensors, electromyography, electroencephalography, acoustic sensors, optical fiber sensors, and global positioning systems were employed to monitor and diagnose neurodegenerative diseases. Various features including physical features, statistical features, nonlinear features, and features from the network can be extracted from these wearable sensors, and the alteration of features toward neurodegenerative diseases was illustrated. Moreover, different kinds of feature selection methods such as filter, wrapper, and embedded methods help to find the distinctive indicator of the diseases and benefit to a better diagnosis performance.

Conclusions

This systematic review enables a comprehensive understanding of wearable sensors and features for the diagnosis of neurodegenerative diseases.

Machine Learning and Wearable Sensors for the Early Detection of Balance Disorders in Parkinson's Disease

Dynamic posturography combined with wearable sensors has high sensitivity in recognizing subclinical balance abnormalities in patients with Parkinson's disease (PD). However, this approach is burdened by a high analytical load for motion analysis, potentially limiting a routine application in clinical practice. In this study, we used machine learning to distinguish PD patients from controls, as well as patients under and not under dopaminergic therapy (i.e., ON and OFF states), based on kinematic measures recorded during dynamic posturography through portable sensors. We compared 52 different classifiers derived from Decision Tree, K-Nearest Neighbor, Support Vector Machine and Artificial Neural Network with different kernel functions to automatically analyze reactive postural responses to yaw perturbations recorded through IMUs in 20 PD patients and 15 healthy subjects. To identify the most efficient machine learning algorithm, we applied three threshold-based selection criteria (i.e., accuracy, recall and precision) and one evaluation criterion (i.e., goodness index). Twenty-one out of 52 classifiers passed the three selection criteria based on a threshold of 80%. Among these, only nine classifiers were considered "optimum" in distinguishing PD patients from healthy subjects according to a goodness index ≤ 0.25. The Fine K-Nearest Neighbor was the best-performing algorithm in the automatic classification of PD patients and healthy subjects, irrespective of therapeutic condition. By contrast, none of the classifiers passed the three threshold-based selection criteria in the comparison of patients in ON and OFF states. Overall, machine learning is a suitable solution for the early identification of balance disorders in PD through the automatic analysis of kinematic data from dynamic posturography.

A high-pressure resistant ternary network hydrogel based flexible strain sensor with a uniaxially oriented porous structure toward gait detection

Gait abnormalities have been widely investigated in the diagnosis and treatment of neurodegenerative diseases. However, it is still a great challenge to achieve a comfortable, convenient, sensitive and high-pressure resistant flexible gait detection sensor for real-time health monitoring. In this work, a polyaniline (PANI)@(polyacrylic acid (PAA)-polyvinyl alcohol (PVA)) (PANI@(PVA-PAA)) ternary network hydrogel with a uniaxially oriented porous featured structure was successfully prepared using a simple freeze-thaw method and in situ polymerization. The PANI@(PVA-PAA) hydrogel shows excellent compressive mechanical properties (423.44 kPa), favorable conductivity (2.02 S m^-1) and remarkable durability (500 loading-unloading cycle), and can sensitively detect the effect of pressure with a fast response time (200 ms). The PANI@(PVA-PAA) hydrogel assembled into a flexible sensor can effectively identify the movement state of the shoulder, knee and even the sole of the plantar for gait detection. The uniaxially oriented porous structure enables the hydrogel-based sensor to have a high rate of change in the longitudinal direction and can effectively distinguish various gaits. The construction of a hydrogen bond between PANI and the PVA-PAA hydrogel ensures the uniform distribution of PANI in the hydrogel to form a ternary network structure, which improves the pressure resistance and conductivity of the PANI@(PVA-PAA) hydrogel. Thus, PANI@(PVA-PAA) hydrogel flexible sensor for gait detection can not only effectively monitor some serious diseases but also detect some unscientific exercise in people's daily life.

Automatic ML-based vestibular gait classification: examining the effects of IMU placement and gait task selection

BACKGROUND

Vestibular deficits can impair an individual's ability to maintain postural and/or gaze stability. Characterizing gait abnormalities among individuals affected by vestibular deficits could help identify patients at high risk of falling and inform rehabilitation programs. Commonly used gait assessment tools rely on simple measures such as timing and visual observations of path deviations by clinicians. These simple measures may not capture subtle changes in gait kinematics. Therefore, we investigated the use of wearable inertial measurement units (IMUs) and machine learning (ML) approaches to automatically discriminate between gait patterns of individuals with vestibular deficits and age-matched controls. The goal of this study was to examine the effects of IMU placement and gait task selection on the performance of automatic vestibular gait classifiers.

METHODS

Thirty study participants (15 with vestibular deficits and 15 age-matched controls) participated in a single-session gait study during which they performed seven gait tasks while donning a full-body set of IMUs. Classification performance was reported in terms of area under the receiver operating characteristic curve (AUROC) scores for Random Forest models trained on data from each IMU placement for each gait task.

RESULTS

Several models were able to classify vestibular gait better than random (AUROC > 0.5), but their performance varied according to IMU placement and gait task selection. Results indicated that a single IMU placed on the left arm when walking with eyes closed resulted in the highest AUROC score for a single IMU (AUROC = 0.88 [0.84, 0.89]). Feature permutation results indicated that participants with vestibular deficits reduced their arm swing compared to age-matched controls while they walked with eyes closed.

CONCLUSIONS

These findings highlighted differences in upper extremity kinematics during walking with eyes closed that were characteristic of vestibular deficits and showed evidence of the discriminative ability of IMU-based automated screening for vestibular deficits. Further research should explore the mechanisms driving arm swing differences in the vestibular population.

Single- and dual-task gait performance and their diagnostic value in early-stage Parkinson's disease

Background

Gait parameters are considered potential diagnostic markers of Parkinson's disease (PD). We aimed to 1) assess the gait impairment in early-stage PD and its related factors in the single-task (ST) and dual-task (DT) walking tests and 2) evaluate and compare the diagnostic value of gait parameters for early-stage PD under ST and DT conditions.

Methods

A total of 97 early-stage PD patients and 41 healthy controls (HC) were enrolled at Hwa Mei hospital. Gait parameters were gathered and compared between the two groups in the ST and DT walking test, controlling for covariates. Utilizing the receiver operating characteristic curve, diagnostic parameters were investigated.

Results

In the ST walking test, significantly altered gait patterns could be observed in early-stage PD patients in all domains of gait, except for asymmetry (P < 0.05). Compared to the ST walking test, the early-stage PD group performed poorly in the DT walking test in the pace, rhythm, variability and postural control domain (P < 0.05). Older, heavier subjects, as well as those with lower height, lower level of education and lower gait velocity, were found to have a poorer gait performance (P < 0.05). Stride length (AUC = 0.823, sensitivity, 68.0%; specificity, 85.4%; P < 0.001) and heel strike angle (AUC = 0.796, sensitivity, 71.1%; specificity, 80.5%; P < 0.001) could distinguish early-stage PD patients from HCs with moderate accuracy, independent of covariates. The diagnostic accuracy of gait parameters under ST conditions were statistically noninferior to those under DT conditions(P>0.05). Combining all gait parameters with diagnostic values under ST and DT walking test, the predictive power significantly increased with an AUC of 0.924 (sensitivity, 85.4%; specificity, 92.7%; P < 0.001).

Conclusion

Gait patterns altered in patients with early-stage PD but the gait symmetry remained preserved. Stride length and heel strike angle were the two most prominent gait parameters of altered gait in early-stage of PD that could serve as diagnostic markers of early-stage PD. Our findings are helpful to understand the gait pattern of early-stage PD and its related factors and can be conducive to the development of new diagnostic tools for early-stage PD.

Machine learning models for Parkinson's disease detection and stage classification based on spatial-temporal gait parameters

BACKGROUND

Parkinson's disease (PD) is a chronic and progressive neurodegenerative disease with no cure, presenting a challenging diagnosis and management. However, despite a significant number of criteria and guidelines have been proposed to improve the diagnosis of PD and to determine the PD stage, the gold standard for diagnosis and symptoms monitoring of PD is still mainly based on clinical evaluation, which includes several subjective factors. The use of machine learning (ML) algorithms in spatial-temporal gait parameters is an interesting advance with easy interpretation and objective factors that may assist in PD diagnostic and follow up.

RESEARCH QUESTION

This article studies ML algorithms for: i) distinguish people with PD vs. matched-healthy individuals; and ii) to discriminate PD stages, based on selected spatial-temporal parameters, including variability and asymmetry.

METHODS

Gait data acquired from 63 people with PD with different levels of PD motor symptoms severity, and 63 matched-control group individuals, during self-selected walking speed, was study in the experiments.

RESULTS

In the PD diagnosis, a classification accuracy of 84.6 %, with a precision of 0.923 and a recall of 0.800, was achieved by the Naïve Bayes algorithm. We found four significant gait features in PD diagnosis: step length, velocity and width, and step width variability. As to the PD stage identification, the Random Forest outperformed the other studied ML algorithms, by reaching an Area Under the ROC curve of 0.786. We found two relevant gait features in identifying the PD stage: stride width variability and step double support time variability.

SIGNIFICANCE

The results showed that the studied ML algorithms have potential both to PD diagnosis and stage identification by analysing gait parameters.

Detection and assessment of Parkinson's disease based on gait analysis: A survey

Neurological disorders represent one of the leading causes of disability and mortality in the world. Parkinson's Disease (PD), for example, affecting millions of people worldwide is often manifested as impaired posture and gait. These impairments have been used as a clinical sign for the early detection of PD, as well as an objective index for pervasive monitoring of the PD patients in daily life. This review presents the evidence that demonstrates the relationship between human gait and PD, and illustrates the role of different gait analysis systems based on vision or wearable sensors. It also provides a comprehensive overview of the available automatic recognition systems for the detection and management of PD. The intervening measures for improving gait performance are summarized, in which the smart devices for gait intervention are emphasized. Finally, this review highlights some of the new opportunities in detecting, monitoring, and treating of PD based on gait, which could facilitate the development of objective gait-based biomarkers for personalized support and treatment of PD.

A comparison of an implanted accelerometer with a wearable accelerometer for closed-loop DBS

Sensing technology, as well as cloud communication, is enabling the development of closed-loop deep brain stimulation (DBS) for Parkinson's disease. The accelerometer is a practical sensor that can provide information about the disease/health state of the patient as well as physical activity levels, all of which in the long-term can provide feedback information to an adaptive closed-loop control algorithm for more effective and personalized DBS therapy. In this paper, we present for the first time, acceleration streamed from Medtronic's RC+S device in patients with Parkinson's disease while at home, and compare it to accel-eration acquired concurrently from the patient's Apple Watch. We examined correlation between the accelerometer signals at varying time scales. We also compared the spectral band power obtained from the two accelerometers. While there was an average correlation of 0.37 for subject 1 and 0.50 for subject 2 between the two acceleration signals on a time scale of 10 minutes, the correlation was lower for shorter time scales on the order of seconds. There was greater spectral power in the Parkinsonian tremor band of 4-7 Hz for the externally worn accelerometer than the internal accelerometer, but the internal accelerometer showed greater relative power distributed in the higher frequencies (7-30 Hz). Thus, based on this preliminary analysis, we expect that the internal accelerometer may be used to assess patient activity and state for closed loop DBS but tremor detection may require more sophisticated signal processing. Furthermore, the internal accelerometer may contain information in higher frequency bands that reveal information about the patient state. Clinical relevance - Closed-loop DBS is expected to improve patient outcomes for the tens of thousands of Parkinson's disease patients using DBS [1], [2]. Eliminating an additional external device in order to implement closed-loop adaptive deep brain stimulation would benefit DBS patients however an understanding of what information is lost by doing so is needed to justify the ultimate design of closed-loop DBS.

IMU-Based Monitoring for Assistive Diagnosis and Management of IoHT: A Review

With the rapid development of Internet of Things (IoT) technologies, traditional disease diagnoses carried out in medical institutions can now be performed remotely at home or even ambient environments, yielding the concept of the Internet of Health Things (IoHT). Among the diverse IoHT applications, inertial measurement unit (IMU)-based systems play a significant role in the detection of diseases in many fields, such as neurological, musculoskeletal, and mental. However, traditional numerical interpretation methods have proven to be challenging to provide satisfying detection accuracies owing to the low quality of raw data, especially under strong electromagnetic interference (EMI). To address this issue, in recent years, machine learning (ML)-based techniques have been proposed to smartly map IMU-captured data on disease detection and progress. After a decade of development, the combination of IMUs and ML algorithms for assistive disease diagnosis has become a hot topic, with an increasing number of studies reported yearly. A systematic search was conducted in four databases covering the aforementioned topic for articles published in the past six years. Eighty-one articles were included and discussed concerning two aspects: different ML techniques and application scenarios. This review yielded the conclusion that, with the help of ML technology, IMUs can serve as a crucial element in disease diagnosis, severity assessment, characteristic estimation, and monitoring during the rehabilitation process. Furthermore, it summarizes the state-of-the-art, analyzes challenges, and provides foreseeable future trends for developing IMU-ML systems for IoHT.

An Efficient Rotation Forest-Based Ensemble Approach for Predicting Severity of Parkinson’s Disease

Parkinson's disease (PD) is a neurodegenerative nervous system disorder that mainly affects body movement, and it is one of the most common diseases, particularly in elderly individuals. This paper proposes a new machine learning approach to predict Parkinson's disease severity using UCI's Parkinson's telemonitoring voice dataset. The proposed method analyses the patient's voice data and classifies them into “severe” and “nonsevere” classes. At first, a subset of features was selected, then a novel approach with a combination of Rotation Forest and Random Forest was applied on selected features to determine each patient's disease severity. Analysis of the experimental results shows that the proposed approach can detect the severity of PD patients in the early stages. Moreover, the proposed model is compared with several algorithms, and the results indicate that the model is highly successful in classifying records and outperformed the other methods concerning classification accuracy and F1-measure rate.

Generalizability of deep learning models for predicting outdoor irregular walking surfaces

Observations from laboratory-based gait analysis are difficult to extrapolate to real-world environments where gait behavior is modulated in response to complex environmental conditions and surface profiles. Inertial measurement units (IMUs) permit real-world gait analysis; however, automatic detection of surfaces encountered remains largely unexplored. The aims of this study are to quantify for machine learning models the effect of (1) random and subject-wise data splitting and (2) sensor location and count on surface classification performance. Thirty participants walked on nine surface conditions (flat-even, slope-up, slope-down, stairs-up, stairs-down, cobblestone, grass, banked-left, banked-right) wearing IMUs (wrist, trunk, bilateral thighs, bilateral shanks). Data were separated into gait cycles, normalized to 101 samples, and spilt into train and test sets (85 and 15%, respectively). For random splitting, trials were randomly assigned to the train or test set. In subject-wise splitting, all trials from 4 random participants were selected for testing. Linear discriminant analysis extracted features from the IMUs. Features were delivered to a neural network. F1-score evaluated model performance. Models achieved F1 scores of 0.96 and 0.78 using random and subject-wise splitting, respectively. Random splitting performance was mainly invariant to sensor location/count; however, subject-wise splitting showed best performance using lower-limb sensors. In general, stairs and sloped surfaces were easily predicted (F1 > 0.85) while banked surfaces were challenging, especially for subject-wise models (F1 ≈ 0.6). Neural networks can detect surfaces based on subtle changes in walking behavior captured by IMUs. Data splitting approaches and sensor location/count (subject-wise) have a non-negligible effect on model performance.

Measurement, Evaluation, and Control of Active Intelligent Gait Training Systems—Analysis of the Current State of the Art

Gait recognition and rehabilitation has been a research hotspot in recent years due to its importance to medical care and elderly care. Active intelligent rehabilitation and assistance systems for lower limbs integrates mechanical design, sensing technology, intelligent control, and robotics technology, and is one of the effective ways to resolve the above problems. In this review, crucial technologies and typical prototypes of active intelligent rehabilitation and assistance systems for gait training are introduced. The limitations, challenges, and future directions in terms of gait measurement and intention recognition, gait rehabilitation evaluation, and gait training control strategies are discussed. To address the core problems of the sensing, evaluation and control technology of the active intelligent gait training systems, the possible future research directions are proposed. Firstly, different sensing methods need to be proposed for the decoding of human movement intention. Secondly, the human walking ability evaluation models will be developed by integrating the clinical knowledge and lower limb movement data. Lastly, the personalized gait training strategy for collaborative control of human–machine systems needs to be implemented in the clinical applications.

Machine Learning Classifiers to Evaluate Data From Gait Analysis With Depth Cameras in Patients With Parkinson’s Disease

Introduction

The assessments of the motor symptoms in Parkinson’s disease (PD) are usually limited to clinical rating scales (MDS UPDRS III), and it depends on the clinician’s experience. This study aims to propose a machine learning technique algorithm using the variables from upper and lower limbs, to classify people with PD from healthy people, using data from a portable low-cost device (RGB-D camera). And can be used to support the diagnosis and follow-up of patients in developing countries and remote areas.

Methods

We used Kinect®eMotion system to capture the spatiotemporal gait data from 30 patients with PD and 30 healthy age-matched controls in three walking trials. First, a correlation matrix was made using the variables of upper and lower limbs. After this, we applied a backward feature selection model using R and Python to determine the most relevant variables. Three further analyses were done using variables selected from backward feature selection model (Dataset A), movement disorders specialist (Dataset B), and all the variables from the dataset (Dataset C). We ran seven machine learning models for each model. Dataset was divided 80% for algorithm training and 20% for evaluation. Finally, a causal inference model (CIM) using the DoWhy library was performed on Dataset B due to its accuracy and simplicity.

Results

The Random Forest model is the most accurate for all three variable Datasets (Dataset A: 81.8%; Dataset B: 83.6%; Dataset C: 84.5%) followed by the support vector machine. The CIM shows a relation between leg variables and the arms swing asymmetry (ASA) and a proportional relationship between ASA and the diagnosis of PD with a robust estimator (1,537).

Conclusions

Machine learning techniques based on objective measures using portable low-cost devices (Kinect®eMotion) are useful and accurate to classify patients with Parkinson’s disease. This method can be used to evaluate patients remotely and help clinicians make decisions regarding follow-up and treatment.

Machine Learning Approach to Support the Detection of Parkinson's Disease in IMU-Based Gait Analysis

The aim of this study was to determine which supervised machine learning (ML) algorithm can most accurately classify people with Parkinson’s disease (pwPD) from speed-matched healthy subjects (HS) based on a selected minimum set of IMU-derived gait features. Twenty-two gait features were extrapolated from the trunk acceleration patterns of 81 pwPD and 80 HS, including spatiotemporal, pelvic kinematics, and acceleration-derived gait stability indexes. After a three-level feature selection procedure, seven gait features were considered for implementing five ML algorithms: support vector machine (SVM), artificial neural network, decision trees (DT), random forest (RF), and K-nearest neighbors. Accuracy, precision, recall, and F1 score were calculated. SVM, DT, and RF showed the best classification performances, with prediction accuracy higher than 80% on the test set. The conceptual model of approaching ML that we proposed could reduce the risk of overrepresenting multicollinear gait features in the model, reducing the risk of overfitting in the test performances while fostering the explainability of the results.

Using a Video Device and a Deep Learning-Based Pose Estimator to Assess Gait Impairment in Neurodegenerative Related Disorders: A Pilot Study

As the world’s population is living longer, age-related neurodegenerative diseases are becoming a more significant global issue. Neurodegenerative diseases cause worsening motor, cognitive and autonomic dysfunction over time and reduce functional abilities required for daily living. Compromised motor performance is one of the first and most evident manifestations. In the case of Parkinson’s disease, these impairments are currently evaluated by experts through the use of rating scales. Although this method is widely used by experts worldwide, it includes subjective and error-prone motor examinations that also fail in the characterization of symptoms’ fluctuations. The aim of this study is to evaluate whether artificial intelligence techniques can be used to objectively assess gait impairment in subjects with Parkinson’s disease. This paper presents the results of a cohort of ten subjects, five with a Parkinson’s disease diagnosis at different degrees of severity. We experimentally demonstrate good effectiveness of the proposed system in extracting the main features concerning people’s gait during the standard tests that clinicians use to assess the burden of disease. This system can offer neurologists, through accurate and objective data, a second opinion or a suggestion to reconsider score assignment. Thanks to its simplicity, tactful and non-intrusive approach and clinical-grade accuracy, it can be adopted on an ongoing basis even in environments where people usually live and work.

Foot Trajectory Features in Gait of Parkinson’s Disease Patients

Parkinson’s disease (PD) is a progressive neurological disorder characterized by movement disorders, such as gait instability. This study investigated whether certain spatial features of foot trajectory are characteristic of patients with PD. The foot trajectory of patients with mild and advanced PD in on-state and healthy older and young individuals was estimated from acceleration and angular velocity measured by inertial measurement units placed on the subject’s shanks, just above the ankles. We selected six spatial variables in the foot trajectory: forward and vertical displacements from heel strike to toe-off, maximum clearance, and change in supporting leg (F1 to F3 and V1 to V3, respectively). Healthy young individuals had the greatest F2 and F3 values, followed by healthy older individuals, and then mild PD patients. Conversely, the vertical displacements of mild PD patients were larger than the healthy older individuals. Still, those of healthy older individuals were smaller than the healthy young individuals except for V3. All six displacements of the advanced PD patients were smaller than the mild PD patients. To investigate features in foot trajectories in detail, a principal components analysis and soft-margin kernel support vector machine was used in machine learning. The accuracy in distinguishing between mild PD patients and healthy older individuals and between mild and advanced PD patients was 96.3 and 84.2%, respectively. The vertical and forward displacements in the foot trajectory was the main contributor. These results reveal that large vertical displacements and small forward ones characterize mild and advanced PD patients, respectively.

Explainable Artificial Intelligence and Wearable Sensor-Based Gait Analysis to Identify Patients with Osteopenia and Sarcopenia in Daily Life

Osteopenia and sarcopenia can cause various senile diseases and are key factors related to the quality of life in old age. There is need for portable tools and methods that can analyze osteopenia and sarcopenia risks during daily life, rather than requiring a specialized hospital setting. Gait is a suitable indicator of musculoskeletal diseases; therefore, we analyzed the gait signal obtained from an inertial-sensor-based wearable gait device as a tool to manage bone loss and muscle loss in daily life. To analyze the inertial-sensor-based gait, the inertial signal was classified into seven gait phases, and descriptive statistical parameters were obtained for each gait phase. Subsequently, explainable artificial intelligence was utilized to analyze the contribution and importance of descriptive statistical parameters on osteopenia and sarcopenia. It was found that XGBoost yielded a high accuracy of 88.69% for osteopenia, whereas the random forest approach showed a high accuracy of 93.75% for sarcopenia. Transfer learning with a ResNet backbone exhibited appropriate performance but showed lower accuracy than the descriptive statistical parameter-based identification result. The proposed gait analysis method confirmed high classification accuracy and the statistical significance of gait factors that can be used for osteopenia and sarcopenia management.

Internet of Things Technologies and Machine Learning Methods for Parkinson's Disease Diagnosis, Monitoring and Management: A Systematic Review

Parkinson's disease is a chronic neurodegenerative disease that affects a large portion of the population, especially the elderly. It manifests with motor, cognitive and other types of symptoms, decreasing significantly the patients' quality of life. The recent advances in the Internet of Things and Artificial Intelligence fields, including the subdomains of machine learning and deep learning, can support Parkinson's disease patients, their caregivers and clinicians at every stage of the disease, maximizing the treatment effectiveness and minimizing the respective healthcare costs at the same time. In this review, the considered studies propose machine learning models, trained on data acquired via smart devices, wearable or non-wearable sensors and other Internet of Things technologies, to provide predictions or estimations regarding Parkinson's disease aspects. Seven hundred and seventy studies have been retrieved from three dominant academic literature databases. Finally, one hundred and twelve of them have been selected in a systematic way and have been considered in the state-of-the-art systematic review presented in this paper. These studies propose various methods, applied on various sensory data to address different Parkinson's disease-related problems. The most widely deployed sensors, the most commonly addressed problems and the best performing algorithms are highlighted. Finally, some challenges are summarized along with some future considerations and opportunities that arise.

Smart-Sleeve: A Wearable Textile Pressure Sensor Array for Human Activity Recognition

Human activity recognition is becoming increasingly important. As contact with oneself and the environment accompanies almost all human activities, a Smart-Sleeve, made of soft and stretchable textile pressure sensor matrix, is proposed to sense human contact with the surroundings and identify performed activities in this work. Additionally, a dataset including 18 activities, performed by 14 subjects in 10 repetitions, is generated. The Smart-Sleeve is evaluated over six classical machine learning classifiers (support vector machine, k-nearest neighbor, logistic regression, random forest, decision tree and naive Bayes) and a convolutional neural network model. For classical machine learning, a new normalization approach is proposed to overcome signal differences caused by different body sizes and statistical, geometric, and symmetry features are used. All classification techniques are compared in terms of classification accuracy, precision, recall, and F-measure. Average accuracies of 82.02% (support vector machine) and 82.30% (convolutional neural network) can be achieved in 10-fold cross-validation, and 72.66% (support vector machine) and 74.84% (convolutional neural network) in leave-one-subject-out validation, which shows that the Smart-Sleeve and the proposed data processing method are suitable for human activity recognition.

Analysis of Gait Sub-Movements to Estimate Ataxia Severity using Ankle Inertial Data

Objective: Assessment of motor severity in cerebellar ataxia is critical for monitoring disease progression and evaluating the effectiveness of therapeutic interventions. Though wearable sensors have been used to monitor gait tasks in order to enable frequent assessment, existing solutions only estimate gait performance severity rather than comprehensive motor severity. In this study, we propose a new approach that analyzes sub-second movement profiles of the lower-limbs during gait to estimate overall motor severity in cerebellar ataxia. Methods: A total of 37 ataxia subjects and 12 healthy subjects performed a 5 m walk-and-turn task with two ankle-worn inertial sensors. Lower-limb movements were decomposed into one-dimensional sub-movements, namely movement elements. Supervised regression models trained on data features of movement elements estimated the Brief Ataxia Rating Scale (BARS) and its sub-scores evaluated by clinicians. The proposed models were also compared to models trained on widely-accepted spatiotemporal gait features. Results: Estimated total BARS showed strong agreement with clinician-evaluated scores with r² = 0.72 and a root mean square error of 2.6 BARS points. Movement element-based models significantly outperformed conventional, spatiotemporal gait feature-based models. Conclusion: The proposed algorithm accurately assessed overall motor severity in cerebellar ataxia using inertial data collected from bilaterally-placed ankle sensors during a simple walk-and-turn task. Significance: Our work could support fine-grained monitoring of disease progression and patients' responses to medical/clinical interventions.

Classification of Parkinson's disease with freezing of gait based on 360° turning analysis using 36 kinematic features

BACKGROUND

Freezing of gait (FOG) is a sensitive problem, which is caused by motor control deficits and requires greater attention during postural transitions such as turning in people with Parkinson's disease (PD). However, the turning characteristics have not yet been extensively investigated to distinguish between people with PD with and without FOG (freezers and non-freezers) based on full-body kinematic analysis during the turning task. The objectives of this study were to identify the machine learning model that best classifies people with PD and freezers and reveal the associations between clinical characteristics and turning features based on feature selection through stepwise regression.

METHODS

The study recruited 77 people with PD (31 freezers and 46 non-freezers) and 34 age-matched older adults. The 360° turning task was performed at the preferred speed for the inner step of the more affected limb. All experiments on the people with PD were performed in the "Off" state of medication. The full-body kinematic features during the turning task were extracted using the three-dimensional motion capture system. These features were selected via stepwise regression.

RESULTS

In feature selection through stepwise regression, five and six features were identified to distinguish between people with PD and controls and between freezers and non-freezers (PD and FOG classification problem), respectively. The machine learning model accuracies revealed that the random forest (RF) model had 98.1% accuracy when using all turning features and 98.0% accuracy when using the five features selected for PD classification. In addition, RF and logistic regression showed accuracies of 79.4% when using all turning features and 72.9% when using the six selected features for FOG classification.

CONCLUSION

We suggest that our study leads to understanding of the turning characteristics of people with PD and freezers during the 360° turning task for the inner step of the more affected limb and may help improve the objective classification and clinical assessment by disease progression using turning features.

Real-Time Limb Motion Tracking with a Single IMU Sensor for Physical Therapy Exercises

Limb exercises are common in physical therapy to improve range of motion (RoM), strength, and flexibility of the arm/leg. To improve therapy outcomes and reduce cost, motion tracking systems have been used to monitor the user's movements when performing the exercises and provide guidance. Traditional motion tracking systems are based on either cameras or inertial measurement unit (IMU) sensors. Camera-based systems face problems caused by occlusion and lighting. Traditional IMU-based systems require at least two IMU sensors to track the motion of the entire limb, which is not convenient for use. In this paper, we propose a novel limb motion tracking system that uses a single 9-axis IMU sensor that is worn on the distal end joint of the limb (i.e., wrist for the arm or ankle for the leg). Limb motion tracking using a single IMU sensor is a challenging problem because 1) the noisy IMU data will cause drift problem when estimating position from the acceleration data, 2) the single IMU sensor measures the motion of only one joint but the limb motion consists of motion from multiple joints. To solve these problems, we propose a recurrent neural network (RNN) model to estimate the 3D positions of the distal end joint as well as the other joints of the limb (e.g., elbow or knee) from the noisy IMU data in real time. Our proposed approach achieves high accuracy with a median error of 7.2/7.1 cm for the wrist/elbow joint in leave-one-subject-out cross validation when tracking the arm motion, outperforming the state-of-the-art approach by more than 10%. In addition, the proposed model is lightweight, enabling real-time applications on mobile devices.Clinical relevance- This work has great potential to improve limb exercises monitoring and RoM measurement in home-based physical therapy. It is also cost effective and can be made available widely for immediate application.

Gait-based Human Identification through Minimum Gait-phases and Sensors

The incredible pace at which the world's elderly population is growing will put severe burdens on current healthcare systems and resources. To alleviate this concern the health care systems must rely on the transformation of eldercare and old homes to use Ambient Assisted Living (AAL). Human identification is one of the most common and critical tasks for condition monitoring, human-machine interaction, and providing assistive services in such environments. Recently, human gait has gained new attention as a biometric for identification to achieve contactless identification from a distance robust to physical appearances. However, an important aspect of gait identification through wearables and image-based systems alike is accurate identification when limited information is available for example, when only a fraction of the whole gait cycle or only a part of the subject's body is visible. In this paper, we present a gait identification technique based on temporal and descriptive statistic parameters of different gait phases as the features and we investigate the performance of using only single gait phases for the identification task using a minimum number of sensors. Gait data were collected from 60 individuals through pelvis and foot sensors. Six different machine learning algorithms were used for identification. It was shown that it is possible to achieve high accuracy of over 95.5% by monitoring a single phase of the whole gait cycle through only a single sensor. It was also shown that the proposed methodology could be used to achieve 100% identification accuracy when the whole gait cycle was monitored through pelvis and foot sensors combined. The ANN was found to be more robust to less number of data features compared to SVM and was concluded as the best machine algorithm for the purpose.

A pathophysiological model of gait captures the details of the impairment of pace/rhythm, variability and asymmetry in Parkinsonian patients at distinct stages of the disease

Locomotion in people with Parkinson' disease (pwPD) worsens with the progression of disease, affecting independence and quality of life. At present, clinical practice guidelines recommend a basic evaluation of gait, even though the variables (gait speed, cadence, step length) may not be satisfactory for assessing the evolution of locomotion over the course of the disease. Collecting variables into factors of a conceptual model enhances the clinical assessment of disease severity. Our aim is to evaluate if factors highlight gait differences between pwPD and healthy subjects (HS) and do it at earlier stages of disease compared to single variables. Gait characteristics of 298 pwPD and 84 HS able to walk without assistance were assessed using a baropodometric walkway (GAITRite®). According to the structure of a model previously validated in pwPD, eight spatiotemporal variables were grouped in three factors: pace/rhythm, variability and asymmetry. The model, created from the combination of three factor scores, proved to outperform the single variables or the factors in discriminating pwPD from HS. When considering the pwPD split into the different Hoehn and Yahr (H&Y) stages, the spatiotemporal variables, factor scores and the model showed that multiple impairments of gait appear at H&Y stage 2.5, with the greatest difference from HS at stage 4. A contrasting behavior was found for the asymmetry variables and factor, which showed differences from the HS already in the early stages of PD. Our findings support the use of factor scores and of the model with respect to the single variables in gait staging in PD.

A Systematic Review of Machine Learning Based Gait characteristics in Parkinson's disease

OBJECTIVE

Parkinson's disease is a pervasive neuro disorder that affects people's quality of life throughout the world. The unsatisfactory results of clinical rating scales open the door for more research. PD treatment using current biomarkers seems a difficult task. So automatic evaluation at an early stage may enhance the quality and time-period of life.

METHODS

Grading of Recommendations Assessment, Development, and Evaluation (GRADE) and Population, intervention, comparison, and outcome (PICO) search methodology schemes are followed to search the data and eligible studies for this survey. Approximate 1500 articles were extracted using related search strings. After the stepwise mapping and elimination of studies, 94 papers are found suitable for the present review.

RESULTS

After the quality assessment of extracted studies, nine inhibitors are identified to analyze people's gait with Parkinson's disease, where four are critical. This review also differentiates the various machine learning classification techniques with their PD analysis characteristics in previous studies. The extracted research gaps are described as future perspectives. Results can help practitioners understand the PD gait as a valuable biomarker for detection, quantification, and classification.

CONCLUSION

Due to less cost and easy recording of gait, gait-based techniques are becoming popular in PD detection. By encapsulating the gait-based studies, it gives an in-depth knowledge of PD, different measures that affect gait detection and classification.

A Clinically Interpretable Computer-Vision Based Method for Quantifying Gait in Parkinson's Disease

Gait is a core motor function and is impaired in numerous neurological diseases, including Parkinson's disease (PD). Treatment changes in PD are frequently driven by gait assessments in the clinic, commonly rated as part of the Movement Disorder Society (MDS) Unified PD Rating Scale (UPDRS) assessment (item 3.10). We proposed and evaluated a novel approach for estimating severity of gait impairment in Parkinson's disease using a computer vision-based methodology. The system we developed can be used to obtain an estimate for a rating to catch potential errors, or to gain an initial rating in the absence of a trained clinician-for example, during remote home assessments. Videos (n=729) were collected as part of routine MDS-UPDRS gait assessments of Parkinson's patients, and a deep learning library was used to extract body key-point coordinates for each frame. Data were recorded at five clinical sites using commercially available mobile phones or tablets, and had an associated severity rating from a trained clinician. Six features were calculated from time-series signals of the extracted key-points. These features characterized key aspects of the movement including speed (step frequency, estimated using a novel Gamma-Poisson Bayesian model), arm swing, postural control and smoothness (or roughness) of movement. An ordinal random forest classification model (with one class for each of the possible ratings) was trained and evaluated using 10-fold cross validation. Step frequency point estimates from the Bayesian model were highly correlated with manually labelled step frequencies of 606 video clips showing patients walking towards or away from the camera (Pearson's r=0.80, p<0.001). Our classifier achieved a balanced accuracy of 50% (chance = 25%). Estimated UPDRS ratings were within one of the clinicians' ratings in 95% of cases. There was a significant correlation between clinician labels and model estimates (Spearman's ρ=0.52, p<0.001). We show how the interpretability of the feature values could be used by clinicians to support their decision-making and provide insight into the model's objective UPDRS rating estimation. The severity of gait impairment in Parkinson's disease can be estimated using a single patient video, recorded using a consumer mobile device and within standard clinical settings; i.e., videos were recorded in various hospital hallways and offices rather than gait laboratories. This approach can support clinicians during routine assessments by providing an objective rating (or second opinion), and has the potential to be used for remote home assessments, which would allow for more frequent monitoring.

Atypical Gait Cycles in Parkinson's Disease

It is important to find objective biomarkers for evaluating gait in Parkinson's Disease (PD), especially related to the foot and lower leg segments. Foot-switch signals, analyzed through Statistical Gait Analysis (SGA), allow the foot-floor contact sequence to be characterized during a walking session lasting five-minutes, which includes turnings. Gait parameters were compared between 20 PD patients and 20 age-matched controls. PDs showed similar straight-line speed, cadence, and double-support compared to controls, as well as typical gait-phase durations, except for a small decrease in the flat-foot contact duration (-4% of the gait cycle, p = 0.04). However, they showed a significant increase in atypical gait cycles (+42%, p = 0.006), during both walking straight and turning. A forefoot strike, instead of a "normal" heel strike, characterized the large majority of PD's atypical cycles, whose total percentage was 25.4% on the most-affected and 15.5% on the least-affected side. Moreover, we found a strong correlation between the atypical cycles and the motor clinical score UPDRS-III (r = 0.91, p = 0.002), in the subset of PD patients showing an abnormal number of atypical cycles, while we found a moderate correlation (r = 0.60, p = 0.005), considering the whole PD population. Atypical cycles have proved to be a valid biomarker to quantify subtle gait dysfunctions in PD patients.

GaborPDNet: Gabor Transformation and Deep Neural Network for Parkinson’s Disease Detection Using EEG Signals

Parkinson’s disease (PD) is globally the most common neurodegenerative movement disorder. It is characterized by a loss of dopaminergic neurons in the substantia nigra of the brain. However, current methods to diagnose PD on the basis of clinical features of Parkinsonism may lead to misdiagnoses. Hence, noninvasive methods such as electroencephalographic (EEG) recordings of PD patients can be an alternative biomarker. In this study, a deep-learning model is proposed for automated PD diagnosis. EEG recordings of 16 healthy controls and 15 PD patients were used for analysis. Using Gabor transform, EEG recordings were converted into spectrograms, which were used to train the proposed two-dimensional convolutional neural network (2D-CNN) model. As a result, the proposed model achieved high classification accuracy of 99.46% (±0.73) for 3-class classification (healthy controls, and PD patients with and without medication) using tenfold cross-validation. This indicates the potential of proposed model to simultaneously automatically detect PD patients and their medication status. The proposed model is ready to be validated with a larger database before implementation as a computer-aided diagnostic (CAD) tool for clinical-decision support.

Validity Evaluation of an Inertial Measurement Unit (IMU) in Gait Analysis Using Statistical Parametric Mapping (SPM)

Inertial measurement units (IMUs) are possible alternatives to motion-capture systems (Mocap) for gait analysis. However, IMU-based system performance must be validated before widespread clinical use. Therefore, this study evaluated the validity of IMUs using statistical parametric mapping (SPM) for gait analysis. Ten healthy males (age, 30.10 ± 3.28 years; height, 175.90 ± 5.17 cm; weight: 82.80 ± 17.15 kg) participated in this study; they were asked to walk normally on a treadmill. Data were collected during walking at the self-selected speeds (preferred speed, 1.34 ± 0.10 m/s) using both Mocap and an IMU. Calibration was performed directly before each gait measurement to minimize the IMU drift error over time. The lower-extremity joint angles of the hip, knee, and ankle were calculated and compared with IMUs and Mocap; the hip-joint angle did not differ significantly between IMUs and Mocap. There were significant differences in the discrete (max, min, and range of motion) and continuous variables (waveform: 0–100%) of the knee and ankle joints between IMUs and Mocap, particularly on the swing phase (p < 0.05). Our results suggest that IMU-based data can be used confidently during the stance phase but needs evaluation regarding the swing phase in gait analysis.

Electromyography-informed modeling for estimating muscle activation and force alterations in Parkinson's disease

Electromyography (EMG)-driven neuromusculoskeletal modeling (NMSM) enables simulating the mechanical function of multiple muscle-tendon units as controlled by nervous system in the generation of complex movements. In the context of clinical assessment this may enable understanding biomechanical factor contributing to gait disorders such as one induced by Parkinson's disease (PD). In spite of the challenges in the development of patient-specific models, this preliminary study aimed at establishing a feasible and noninvasive experimental and modeling pipeline to be adopted in clinics to detect PD-induced gait alterations. Four different NMSM have been implemented for three healthy controls using CEINMS, an OpenSim-compatible toolbox. Models differed in the EMG-normalization methods used for calibration purposes (i.e. walking trial normalization and maximum voluntary contraction normalization) and in the set of experimental EMGs used for the musculotendon-unit mapping (i.e. 4 channels vs. 15 channels). Model accuracy assessment showed no statistically significant differences between the more complete model (non-clinically viable) and the proposed reduced one (clinically viable). The clinically viable reduced model was systematically applied on a dataset including ten PD's and thirteen healthy controls. Results showed significant differences in the neuromuscular control strategy of the PD group in term of muscle forces and joint torques. Indeed, PD patients displayed a significantly lower magnitude on force production and revealed a higher amount of force variability with the respect of the healthy controls. The estimated variables could become a measurable biomechanical outcome to assess and track both disease progression and its impact on gait in PD subjects.