A Supervised Machine Learning Approach to Detect the On/Off State in Parkinson's Disease Using Wearable Based Gait Signals

A review of machine learning and deep learning algorithms for Parkinson's disease detection using handwriting and voice datasets

Parkinson's Disease (PD) is a prevalent neurodegenerative disorder with significant clinical implications. Early and accurate diagnosis of PD is crucial for timely intervention and personalized treatment. In recent years, Machine Learning (ML) and Deep Learning (DL) techniques have emerged as promis-ing tools for improving PD diagnosis. This review paper presents a detailed analysis of the current state of ML and DL-based PD diagnosis, focusing on voice, handwriting, and wave spiral datasets. The study also evaluates the effectiveness of various ML and DL algorithms, including classifiers, on these datasets and highlights their potential in enhancing diagnostic accuracy and aiding clinical decision-making. Additionally, the paper explores the identifi-cation of biomarkers using these techniques, offering insights into improving the diagnostic process. The discussion encompasses different data formats and commonly employed ML and DL methods in PD diagnosis, providing a comprehensive overview of the field. This review serves as a roadmap for future research, guiding the development of ML and DL-based tools for PD detection. It is expected to benefit both the scientific community and medical practitioners by advancing our understanding of PD diagnosis and ultimately improving patient outcomes.

A Multimodal Deep Learning Approach to Predicting Systemic Diseases from Oral Conditions

Background: It is known that oral diseases such as periodontal (gum) disease are closely linked to various systemic diseases and disorders. Deep learning advances have the potential to make major contributions to healthcare, particularly in the domains that rely on medical imaging. Incorporating non-imaging information based on clinical and laboratory data may allow clinicians to make more comprehensive and accurate decisions. Methods: Here, we developed a multimodal deep learning method to predict systemic diseases and disorders from oral health conditions. A dual-loss autoencoder was used in the first phase to extract periodontal disease-related features from 1188 panoramic radiographs. Then, in the second phase, we fused the image features with the demographic data and clinical information taken from electronic health records (EHR) to predict systemic diseases. We used receiver operation characteristics (ROC) and accuracy to evaluate our model. The model was further validated by an unseen test dataset. Findings: According to our findings, the top three most accurately predicted chapters, in order, are the Chapters III, VI and IX. The results indicated that the proposed model could predict systemic diseases belonging to Chapters III, VI and IX, with AUC values of 0.92 (95% CI, 0.90-94), 0.87 (95% CI, 0.84-89) and 0.78 (95% CI, 0.75-81), respectively. To assess the robustness of the models, we performed the evaluation on the unseen test dataset for these chapters and the results showed an accuracy of 0.88, 0.82 and 0.72 for Chapters III, VI and IX, respectively. Interpretation: The present study shows that the combination of panoramic radiograph and clinical oral features could be considered to train a fusion deep learning model for predicting systemic diseases and disorders.

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.

Detection of Parkinson's Disease Using Wrist Accelerometer Data and Passive Monitoring

Parkinson's disease is a neurodegenerative disorder impacting patients' movement, causing a variety of movement abnormalities. It has been the focus of research studies for early detection based on wearable technologies. The benefit of wearable technologies in the domain rises by continuous monitoring of this population's movement patterns over time. The ubiquity of wrist-worn accelerometry and the fact that the wrist is the most common and acceptable body location to wear the accelerometer for continuous monitoring suggests that wrist-worn accelerometers are the best choice for early detection of the disease and also tracking the severity of it over time. In this study, we use a dataset consisting of one-week wrist-worn accelerometry data collected from individuals with Parkinson's disease and healthy elderlies for early detection of the disease. Two feature engineering methods, including epoch-based statistical feature engineering and the document-of-words method, were used. Using various machine learning classifiers, the impact of different windowing strategies, using the document-of-words method versus the statistical method, and the amount of data in terms of number of days were investigated. Based on our results, PD was detected with the highest average accuracy value (85% ± 15%) across 100 runs of SVM classifier using a set of features containing features from every and all windowing strategies. We also found that the document-of-words method significantly improves the classification performance compared to the statistical feature engineering model. Although the best performance of the classification task between PD and healthy elderlies was obtained using seven days of data collection, the results indicated that with three days of data collection, we can reach a classification performance that is not significantly different from a model built using seven days of data collection.

The Effect of Submaximal Exercise on Jugular Venous Pulse Assessed by a Wearable Cervical Plethysmography System

The jugular venous pulse (JVP) is a one of the crucial parameters of efficient cardiovascular function. Nowadays, limited data are available regarding the response of JVP to exercise because of its complex and/or invasive assessment procedure. The aim of the present work is to test the feasibility of a non-invasive JVP plethysmography system to monitor different submaximal exercise condition. Twenty (20) healthy subjects (13M/7F mean age 25 ± 3, BMI 21 ± 2) underwent cervical strain-gauge plethysmography, acquired synchronously with the electrocardiogram, while they were carrying out different activities: stand supine, upright, and during the execution of aerobic exercise (2 km walking test) and leg-press machine exercise (submaximal 6 RM test). Peaks a and x of the JVP waveform were investigated since they reflect the volume of cardiac filling. To this aim, the Δax parameter was introduced, representing the amplitude differences between a and x peaks. Significant differences in the values of a, x, and Δax were found between static and exercise conditions (p < 0.0001, p < 0.0001, p < 0.0001), respectively. Particularly, the Δax value for the leg press was approximately three times higher than the supine, and during walking was even nine times higher. The exercise monitoring by means of the novel JVP plethysmography system is feasible during submaximal exercise, and it provides additional parameters on cardiac filling and cerebral venous drainage to the widely used heartbeat rate value.

A Vision-Based System for Stage Classification of Parkinsonian Gait Using Machine Learning and Synthetic Data

Parkinson's disease is characterized by abnormal gait, which worsens as the condition progresses. Although several methods have been able to classify this feature through pose-estimation algorithms and machine-learning classifiers, few studies have been able to analyze its progression to perform stage classification of the disease. Moreover, despite the increasing popularity of these systems for gait analysis, the amount of available gait-related data can often be limited, thereby, hindering the progress of the implementation of this technology in the medical field. As such, creating a quantitative prognosis method that can identify the severity levels of a Parkinsonian gait with little data could help facilitate the study of the Parkinsonian gait for rehabilitation. In this contribution, we propose a vision-based system to analyze the Parkinsonian gait at various stages using linear interpolation of Parkinsonian gait models. We present a comparison between the performance of a k-nearest neighbors algorithm (KNN), support-vector machine (SVM) and gradient boosting (GB) algorithms in classifying well-established gait features. Our results show that the proposed system achieved 96-99% accuracy in evaluating the prognosis of Parkinsonian gaits.

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.

Cardiovascular/Stroke Risk Stratification in Parkinson's Disease Patients Using Atherosclerosis Pathway and Artificial Intelligence Paradigm: A Systematic Review

Parkinson’s disease (PD) is a severe, incurable, and costly condition leading to heart failure. The link between PD and cardiovascular disease (CVD) is not available, leading to controversies and poor prognosis. Artificial Intelligence (AI) has already shown promise for CVD/stroke risk stratification. However, due to a lack of sample size, comorbidity, insufficient validation, clinical examination, and a lack of big data configuration, there have been no well-explained bias-free AI investigations to establish the CVD/Stroke risk stratification in the PD framework. The study has two objectives: (i) to establish a solid link between PD and CVD/stroke; and (ii) to use the AI paradigm to examine a well-defined CVD/stroke risk stratification in the PD framework. The PRISMA search strategy selected 223 studies for CVD/stroke risk, of which 54 and 44 studies were related to the link between PD-CVD, and PD-stroke, respectively, 59 studies for joint PD-CVD-Stroke framework, and 66 studies were only for the early PD diagnosis without CVD/stroke link. Sequential biological links were used for establishing the hypothesis. For AI design, PD risk factors as covariates along with CVD/stroke as the gold standard were used for predicting the CVD/stroke risk. The most fundamental cause of CVD/stroke damage due to PD is cardiac autonomic dysfunction due to neurodegeneration that leads to heart failure and its edema, and this validated our hypothesis. Finally, we present the novel AI solutions for CVD/stroke risk prediction in the PD framework. The study also recommends strategies for removing the bias in AI for CVD/stroke risk prediction using the PD framework.

Proof of Concept in Artificial-Intelligence-Based Wearable Gait Monitoring for Parkinson's Disease Management Optimization

Parkinson's disease (PD) is the second most common progressive neurodegenerative disorder, affecting 6.2 million patients and causing disability and decreased quality of life. The research is oriented nowadays toward artificial intelligence (AI)-based wearables for early diagnosis and long-term PD monitoring. Our primary objective is the monitoring and assessment of gait in PD patients. We propose a wearable physiograph for qualitative and quantitative gait assessment, which performs bilateral tracking of the foot biomechanics and unilateral tracking of arm balance. Gait patterns are assessed by means of correlation. The surface plot of a correlation coefficient matrix, generated from the recorded signals, is classified using convolutional neural networks into physiological or PD-specific gait. The novelty is given by the proposed AI-based decisional support procedure for gait assessment. A proof of concept of the proposed physiograph is validated in a clinical environment on five patients and five healthy controls, proving to be a feasible solution for ubiquitous gait monitoring and assessment in PD. PD management demonstrates the complexity of the human body. A platform empowering multidisciplinary, AI-evidence-based decision support assessments for optimal dosing between drug and non-drug therapy could lay the foundation for affordable precision medicine.

Co-evolution of machine learning and digital technologies to improve monitoring of Parkinson's disease motor symptoms

Parkinson’s disease (PD) is a neurodegenerative disorder characterized by motor impairments such as tremor, bradykinesia, dyskinesia, and gait abnormalities. Current protocols assess PD symptoms during clinic visits and can be subjective. Patient diaries can help clinicians evaluate at-home symptoms, but can be incomplete or inaccurate. Therefore, researchers have developed in-home automated methods to monitor PD symptoms to enable data-driven PD diagnosis and management. We queried the US National Library of Medicine PubMed database to analyze the progression of the technologies and computational/machine learning methods used to monitor common motor PD symptoms. A sub-set of roughly 12,000 papers was reviewed that best characterized the machine learning and technology timelines that manifested from reviewing the literature. The technology used to monitor PD motor symptoms has advanced significantly in the past five decades. Early monitoring began with in-lab devices such as needle-based EMG, transitioned to in-lab accelerometers/gyroscopes, then to wearable accelerometers/gyroscopes, and finally to phone and mobile & web application-based in-home monitoring. Significant progress has also been made with respect to the use of machine learning algorithms to classify PD patients. Using data from different devices (e.g., video cameras, phone-based accelerometers), researchers have designed neural network and non-neural network-based machine learning algorithms to categorize PD patients across tremor, gait, bradykinesia, and dyskinesia. The five-decade co-evolution of technology and computational techniques used to monitor PD motor symptoms has driven significant progress that is enabling the shift from in-lab/clinic to in-home monitoring of PD symptoms.

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.

Adaptive, personalized closed-loop therapy for Parkinson's disease: biochemical, neurophysiological, and wearable sensing systems

INTRODUCTION

Motor complication management is one of the main unmet needs in Parkinson's disease patients.

AREAS COVERED

Among the most promising emerging approaches for handling motor complications in Parkinson's disease, adaptive deep brain stimulation strategies operating in closed-loop have emerged as pivotal to deliver sustained, near-to-physiological inputs to dysfunctional basal ganglia-cortical circuits over time. Existing sensing systems that can provide feedback signals to close the loop include biochemical-, neurophysiological- or wearable-sensors. Biochemical sensing allows to directly monitor the pharmacokinetic and pharmacodynamic of antiparkinsonian drugs and metabolites. Neurophysiological sensing relies on neurotechnologies to sense cortical or subcortical brain activity and extract real-time correlates of symptom intensity or symptom control during DBS. A more direct representation of the symptom state, particularly the phenomenological differentiation and quantification of motor symptoms, can be realized via wearable sensor technology.

EXPERT OPINION

Biochemical, neurophysiologic, and wearable-based biomarkers are promising technological tools that either individually or in combination could guide adaptive therapy for Parkinson's disease motor symptoms in the future.

Using Machine Learning for Predicting the Best Outcomes With Electrical Muscle Stimulation for Tremors in Parkinson's Disease

Recent studies have identified that peripheral stimulation in Parkinson’s disease (PD) is effective in tremor reduction, indicating that a peripheral feedback loop plays an important role in the tremor reset mechanism. This was an open-label, quasi-experimental, pre- and post-test design, single-blind, single-group study involving 20 tremor-dominant PD patients. The objective of this study is to explore the effect of electrical muscle stimulation (EMS) as an adjunctive treatment for resting tremor during “on” period and to identify the best machine learning model to predict the suitable stimulation level that will yield the longest period of tremor reduction or tremor reset time. In this study, we used a Parkinson’s glove to evaluate, stimulate, and quantify the tremors of PD patients. This adjustable glove incorporates a 3-axis gyroscope to measure tremor signals and an EMS to provide an on-demand muscle stimulation to suppress tremors. Machine learning models were applied to identify the suitable pulse amplitude (stimulation level) in five classes that led to the longest tremor reset time. The study was registered at the www.clinicaltrials.gov under the name “The Study of Rest Tremor Suppression by Using Electrical Muscle Stimulation” (NCT02370108). Twenty tremor-dominant PD patients were recruited. After applying an average pulse amplitude of 6.25 (SD 2.84) mA and stimulation period of 440.7 (SD 560.82) seconds, the total time of tremor reduction, or tremor reset time, was 329.90 (SD 340.91) seconds. A significant reduction in tremor parameters during stimulation was demonstrated by a reduction of Unified Parkinson’s Disease Rating Scale (UPDRS) scores, and objectively, with a reduction of gyroscopic data (p < 0.05, each). None of the subjects reported any serious adverse events. We also compared gyroscopic data with five machine learning techniques: Logistic Regression, Random Forest, Support Vector Machine (SVM), Neural Network (NN), and Long-Short-Term-Memory (LSTM). The machine learning model that gave the highest accuracy was LSTM, which obtained: accuracy = 0.865 and macro-F1 = 0.736. This study confirms the efficacy of EMS in the reduction of resting tremors in PD. LSTM was identified as the most effective model for predicting pulse amplitude that would elicit the longest tremor reset time. Our study provides further insight on the tremor reset mechanism 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.

The Experience of OFF Periods in Parkinson's Disease: Descriptions, Triggers, and Alleviating Factors

Purpose

Wearing off of Parkinson's disease medication is common, but triggers and coping strategies for this transient phenomenon are poorly understood. We aimed to assess the lived experience of OFF periods for people with Parkinson's disease.

Methods

Participants in the longitudinal Fox Insight study who endorsed OFF periods were invited to complete a survey consisting of both multiple-choice and free-text responses. Descriptive statistics were used to summarize multiple-choice responses, and free-text responses were classified into themes through iterative discussion by 3 movement disorders specialists.

Results

A total of 2110 participants (52.4% male) completed the survey. Tremor was the most common description of OFF periods (n=1038, 49.2%), followed by gait changes (n=535, 25.4%) and rigidity (n=430, 20.4%). Of 1498 specific triggers for OFF symptoms, the most common was stress (n=920, 61.4%), followed by anxiety/depression (n=476, 31.8%) and tiredness/fatigue (n=351, 23.4%). Common coping strategies (n=1416 responses) included exercise (n=678, 47.9%), taking a break (n=504, 35.6%), and meditation (n=276, 19.5%).

Conclusions

Although OFF periods are common, the individual experiences of OFF vary. This knowledge could be used to develop new counseling strategies for OFF periods in people with Parkinson's disease.

Wearable Technology to Detect Motor Fluctuations in Parkinson's Disease Patients: Current State and Challenges

Monitoring of motor symptom fluctuations in Parkinson's disease (PD) patients is currently performed through the subjective self-assessment of patients. Clinicians require reliable information about a fluctuation's occurrence to enable a precise treatment rescheduling and dosing adjustment. In this review, we analyzed the utilization of sensors for identifying motor fluctuations in PD patients and the application of machine learning techniques to detect fluctuations. The review process followed the Preferred Reporting Items for Systematic Reviews and Meta-Analyses (PRISMA) guidelines. Ten studies were included between January 2010 and March 2021, and their main characteristics and results were assessed and documented. Five studies utilized daily activities to collect the data, four used concrete scenarios executing specific activities to gather the data, and only one utilized a combination of both situations. The accuracy for classification was 83.56-96.77%. In the studies evaluated, it was not possible to find a standard cleaning protocol for the signal captured, and there is significant heterogeneity in the models utilized and in the different features introduced in the models (using spatiotemporal characteristics, frequential characteristics, or both). The two most influential factors in the good performance of the classification problem are the type of features utilized and the type of model.

Comparison of Laboratory and Daily-Life Gait Speed Assessment during ON and OFF States in Parkinson's Disease

Accurate assessment of Parkinson's disease (PD) ON and OFF states in the usual environment is essential for tailoring optimal treatments. Wearables facilitate measurements of gait in novel and unsupervised environments; however, differences between unsupervised and in-laboratory measures have been reported in PD. We aimed to investigate whether unsupervised gait speed discriminates medication states and which supervised tests most accurately represent home performance. In-lab gait speeds from different gait tasks were compared to home speeds of 27 PD patients at ON and OFF states using inertial sensors. Daily gait speed distribution was expressed in percentiles and walking bout (WB) length. Gait speeds differentiated ON and OFF states in the lab and the home. When comparing lab with home performance, ON assessments in the lab showed moderate-to-high correlations with faster gait speeds in unsupervised environment (r = 0.69; p < 0.001), associated with long WB. OFF gait assessments in the lab showed moderate correlation values with slow gait speeds during OFF state at home (r = 0.56; p = 0.004), associated with short WB. In-lab and daily assessments of gait speed with wearables capture additional integrative aspects of PD, reflecting different aspects of mobility. Unsupervised assessment using wearables adds complementary information to the clinical assessment of motor fluctuations in PD.

Forecast the Exacerbation in Patients of Chronic Obstructive Pulmonary Disease with Clinical Indicators Using Machine Learning Techniques

Preventing exacerbation and seeking to determine the severity of the disease during the hospitalization of chronic obstructive pulmonary disease (COPD) patients is a crucial global initiative for chronic obstructive lung disease (GOLD); this option is available only for stable-phase patients. Recently, the assessment and prediction techniques that are used have been determined to be inadequate for acute exacerbation of chronic obstructive pulmonary disease patients. To magnify the monitoring and treatment of acute exacerbation COPD patients, we need to rely on the AI system, because traditional methods take a long time for the prognosis of the disease. Machine-learning techniques have shown the capacity to be effectively used in crucial healthcare applications. In this paper, we propose a voting ensemble classifier with 24 features to identify the severity of chronic obstructive pulmonary disease patients. In our study, we applied five machine-learning classifiers, namely random forests (RF), support vector machine (SVM), gradient boosting machine (GBM), XGboost (XGB), and K-nearest neighbor (KNN). These classifiers were trained with a set of 24 features. After that, we combined their results with a soft voting ensemble (SVE) method. Consequently, we found performance measures with an accuracy of 91.0849%, a precision of 90.7725%, a recall of 91.3607%, an F-measure of 91.0656%, and an AUC score of 96.8656%, respectively. Our result shows that the SVE classifier with the proposed twenty-four features outperformed regular machine-learning-based methods for chronic obstructive pulmonary disease (COPD) patients. The SVE classifier helps respiratory physicians to estimate the severity of COPD patients in the early stage, consequently guiding the cure strategy and helps the prognosis of COPD patients.