Upper limb motor pre-clinical assessment in Parkinson's disease using machine learning

Deep Learning for hand tracking in Parkinson's Disease video-based assessment: Current and future perspectives

BACKGROUND

Parkinson's Disease (PD) demands early diagnosis and frequent assessment of symptoms. In particular, analysing hand movements is pivotal to understand disease progression. Advancements in hand tracking using Deep Learning (DL) allow for the automatic and objective disease evaluation from video recordings of standardised motor tasks, which are the foundation of neurological examinations. In view of this scenario, this narrative review aims to describe the state of the art and the future perspective of DL frameworks for hand tracking in video-based PD assessment.

METHODS

A rigorous search of PubMed, Web of Science, IEEE Explorer, and Scopus until October 2023 using primary keywords such as parkinson, hand tracking, and deep learning was performed to select eligible by focusing on video-based PD assessment through DL-driven hand tracking frameworks RESULTS:: After accurate screening, 23 publications met the selection criteria. These studies used various solutions, from well-established pose estimation frameworks, like OpenPose and MediaPipe, to custom deep architectures designed to accurately track hand and finger movements and extract relevant disease features. Estimated hand tracking data were then used to differentiate PD patients from healthy individuals, characterise symptoms such as tremors and bradykinesia, or regress the Movement Disorder Society-Unified Parkinson's Disease Rating Scale (MDS-UPDRS) by automatically assessing clinical tasks such as finger tapping, hand movements, and pronation-supination.

CONCLUSIONS

DL-driven hand tracking holds promise for PD assessment, offering precise, objective measurements for early diagnosis and monitoring, especially in a telemedicine scenario. However, to ensure clinical acceptance, standardisation and validation are crucial. Future research should prioritise large open datasets, rigorous validation on patients, and the investigation of new frontiers such as tracking hand-hand and hand-object interactions for daily-life tasks assessment.

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.

Clinical Management of Movement Disorders

Movement disorders include a wide and heterogeneous variety of signs and syndromes, which are classified as hyperkinetic [...].

From Recognition to Remedy: The Significance of Biomarkers in Neurodegenerative Disease Pathology

With the inexorable aging of the global populace, neurodegenerative diseases (NDs) like Alzheimer's disease (AD), Parkinson's disease (PD), and amyotrophic lateral sclerosis (ALS) pose escalating challenges, which are underscored by their socioeconomic repercussions. A pivotal aspect in addressing these challenges lies in the elucidation and application of biomarkers for timely diagnosis, vigilant monitoring, and effective treatment modalities. This review delineates the quintessence of biomarkers in the realm of NDs, elucidating various classifications and their indispensable roles. Particularly, the quest for novel biomarkers in AD, transcending traditional markers in PD, and the frontier of biomarker research in ALS are scrutinized. Emergent susceptibility and trait markers herald a new era of personalized medicine, promising enhanced treatment initiation especially in cases of SOD1-ALS. The discourse extends to diagnostic and state markers, revolutionizing early detection and monitoring, alongside progression markers that unveil the trajectory of NDs, propelling forward the potential for tailored interventions. The synergy between burgeoning technologies and innovative techniques like -omics, histologic assessments, and imaging is spotlighted, underscoring their pivotal roles in biomarker discovery. Reflecting on the progress hitherto, the review underscores the exigent need for multidisciplinary collaborations to surmount the challenges ahead, accelerate biomarker discovery, and herald a new epoch of understanding and managing NDs. Through a panoramic lens, this article endeavors to provide a comprehensive insight into the burgeoning field of biomarkers in NDs, spotlighting the promise they hold in transforming the diagnostic landscape, enhancing disease management, and illuminating the pathway toward efficacious therapeutic interventions.

Clinical assessment of upper limb impairments and functional capacity in Parkinson's disease: a systematic review

BACKGROUND

 Parkinson's disease (PD) may progressively reduce the upper limb's functionality. Currently, there is no standardized upper limb functional capacity assessment in PD in the rehabilitation field.

OBJECTIVE

 To identify specific outcome measurements to assess upper limbs in PD and access functional capacity.

METHODS

 We systematically reviewed and analyzed the literature in English published from August/2012 to August/2022 according to PRISMA. The following keywords were used in our search: "upper limbs" OR "upper extremity" and "Parkinson's disease." Two researchers searched independently, including studies accordingly to our inclusion and exclusion criteria. Registered at PROSPERO CRD42021254486.

RESULTS

 We found 797 studies, and 50 were included in this review (n = 2.239 participants in H&Y stage 1-4). The most common upper limbs outcome measures found in the studies were: (i) UPDRS-III and MDS-UPDRS to assess the severity and progression of PD motor symptoms (tremor, bradykinesia, and rigidity) (ii) Nine Hole Peg Test and Purdue Pegboard Test to assess manual dexterity; (iii) Spiral test and Funnel test to provoke and assess freezing of upper limbs; (iv) Technology assessment such as wearables sensors, apps, and other device were also found.

CONCLUSION

 We found evidence to support upper limb impairments assessments in PD. However, there is still a large shortage of specific tests to assess the functional capacity of the upper limbs. The upper limbs' functional capacity is insufficiently investigated during the clinical and rehabilitation examination due to a lack of specific outcome measures to assess functionality.

Mild cognitive impairment identification based on motor and cognitive dual-task pooled indices

OBJECTIVE

This study investigates the possibility of adopting motor and cognitive dual-task (MCDT) approaches to identify subjects with mild cognitive impairment (MCI) and subjective cognitive impairment (SCI).

METHODS

The upper and lower motor performances of 44 older adults were assessed using the SensHand and SensFoot wearable system during three MCDTs: forefinger tapping (FTAP), toe-tapping heel pin (TTHP), and walking 10 m (GAIT). We developed five pooled indices (PIs) based on these MCDTs, and we included them, along with demographic data (age) and clinical scores (Frontal Assessment Battery (FAB) scores), in five logistic regression models.

RESULTS

Models which consider cognitively normal adult (CNA) vs MCI subjects have accuracies that range from 67% to 78%. The addition of clinical scores stabilised the accuracies, which ranged from 85% to 89%. For models which consider CNA vs SCI vs MCI subjects, there are great benefits to considering all three regressors (age, FAB score, and PIs); the overall accuracies of the three-class models range between 50% and 59% when just PIs and age are considered, whereas the overall accuracy increases by 18% when all three regressors are utilised.

CONCLUSION

Logistic regression models that consider MCDT PIs and age have been effective in distinguishing between CNA and MCI subjects. The inclusion of clinical scores increased the models' accuracy. Particularly high performances in distinguishing among CNA, SCI, and MCI subjects were obtained by the TTHP PI. This study suggests that a broader framework for MCDTs, which should encompass a greater selection of motor tasks, could provide clinicians with new appropriate tools.

Levodopa-Induced Dyskinesias in Parkinson's Disease: An Overview on Pathophysiology, Clinical Manifestations, Therapy Management Strategies and Future Directions

Since its first introduction, levodopa has become the cornerstone for the treatment of Parkinson's disease and remains the leading therapeutic choice for motor control therapy so far. Unfortunately, the subsequent appearance of abnormal involuntary movements, known as dyskinesias, is a frequent drawback. Despite the deep knowledge of this complication, in terms of clinical phenomenology and the temporal relationship during a levodopa regimen, less is clear about the pathophysiological mechanisms underpinning it. As the disease progresses, specific oscillatory activities of both motor cortical and basal ganglia neurons and variation in levodopa metabolism, in terms of the dopamine receptor stimulation pattern and turnover rate, underlie dyskinesia onset. This review aims to provide a global overview on levodopa-induced dyskinesias, focusing on pathophysiology, clinical manifestations, therapy management strategies and future directions.

Explainable machine learning models based on multimodal time-series data for the early detection of Parkinson's disease

BACKGROUND AND OBJECTIVES

Parkinson's Disease (PD) is a devastating chronic neurological condition. Machine learning (ML) techniques have been used in the early prediction of PD progression. Fusion of heterogeneous data modalities proved its capability to improve the performance of ML models. Time series data fusion supports the tracking of the disease over time. In addition, the trustworthiness of the resulting models is improved by adding model explainability features. The literature on PD has not sufficiently explored these three points.

METHODS

In this work, we proposed an ML pipeline for predicting the progression of PD that is both accurate and explainable. We explore the fusion of different combinations of five time series modalities from the Parkinson's Progression Markers Initiative (PPMI) real-world dataset, including patient characteristics, biosamples, medication history, motor, and non-motor function data. Each patient has six visits. The problem has been formulated in two ways: ❶ a three-class based progression prediction with 953 patients in each time series modality, and ❷ a four-class based progression prediction with 1,060 patients in each time series modality. The statistical features of these six visits were calculated from each modality and diverse feature selection methods were applied to select the most informative feature sets. The extracted features were used to train a set of well-known ML models including Support vector machines (SVM), random forests (RF), extra tree classifier (ETC), light gradient boosting machines (LGBM), and stochastic gradient descent (SGD). We examined a number of data-balancing strategies in the pipeline with different combinations of modalities. ML models have been optimized using the Bayesian optimizer. A comprehensive evaluation of various ML methods has been conducted, and the best models have been extended to provide different explainability features.

RESULTS

We compare the performance of ML models before and after optimization and using and without using feature selection. In the three-class experiment and with various modality fusions, the LGBM model produced the most accurate results with a 10-fold cross-validation (10-CV) accuracy of 90.73% using non-motor function modality. RF produced the best results in the four-class experiment with various modality fusions with a 10-CV accuracy of 94.57% using non-motor modality. With the fused dataset of non-motor and motor function modalities, the LGBM model outperformed the other ML models in both the 3-class and 4-class experiments (i.e., 10-CV accuracy of 94.89% and 93.73%, respectively). Using the Shapely Additive Explanations (SHAP) framework, we employed global and instance-based explanations to explain the behavior of each ML classifier. Moreover, we extended the explainability by implementing the LIME and SHAPASH local explainers. The consistency of these explainers has been explored. The resultant classifiers were accurate, explainable, and thus medically more relevant and applicable.

CONCLUSIONS

The select modalities and feature sets were confirmed by the literature and medical experts. The various explainers suggest that the bradykinesia (NP3BRADY) feature was the most dominant and consistent. By providing thorough insights into the influence of multiple modalities on the disease risk, the suggested approach is expected to help improve the clinical knowledge of PD progression processes.

A Computer Method for Pronation-Supination Assessment in Parkinson's Disease Based on Latent Space Representations of Biomechanical Indicators

One problem in the quantitative assessment of biomechanical impairments in Parkinson's disease patients is the need for scalable and adaptable computing systems. This work presents a computational method that can be used for motor evaluations of pronation-supination hand movements, as described in item 3.6 of the Unified Parkinson's Disease Rating Scale (MDS-UPDRS). The presented method can quickly adapt to new expert knowledge and includes new features that use a self-supervised training approach. The work uses wearable sensors for biomechanical measurements. We tested a machine-learning model on a dataset of 228 records with 20 indicators from 57 PD patients and eight healthy control subjects. The test dataset's experimental results show that the method's precision rates for the pronation and supination classification task achieved up to 89% accuracy, and the F1-scores were higher than 88% in most categories. The scores present a root mean squared error of 0.28 when compared to expert clinician scores. The paper provides detailed results for pronation-supination hand movement evaluations using a new analysis method when compared to the other methods mentioned in the literature. Furthermore, the proposal consists of a scalable and adaptable model that includes expert knowledge and affectations not covered in the MDS-UPDRS for a more in-depth evaluation.

Quantitative High Density EEG Brain Connectivity Evaluation in Parkinson's Disease: The Phase Locking Value (PLV)

INTRODUCTION

The present study explores brain connectivity in Parkinson's disease (PD) and in age matched healthy controls (HC), using quantitative EEG analysis, at rest and during a motor tasks. We also evaluated the diagnostic performance of the phase locking value (PLV), a measure of functional connectivity, in differentiating PD patients from HCs.

METHODS

High-density, 64-channels, EEG data from 26 PD patients and 13 HC were analyzed. EEG signals were recorded at rest and during a motor task. Phase locking value (PLV), as a measure of functional connectivity, was evaluated for each group in a resting state and during a motor task for the following frequency bands: (i) delta: 2-4 Hz; (ii) theta: 5-7 Hz; (iii) alpha: 8-12 Hz; beta: 13-29 Hz; and gamma: 30-60 Hz. The diagnostic performance in PD vs. HC discrimination was evaluated.

RESULTS

Results showed no significant differences in PLV connectivity between the two groups during the resting state, but a higher PLV connectivity in the delta band during the motor task, in HC compared to PD. Comparing the resting state versus the motor task for each group, only HCs showed a higher PLV connectivity in the delta band during motor task. A ROC curve analysis for HC vs. PD discrimination, showed an area under the ROC curve (AUC) of 0.75, a sensitivity of 100%, and a negative predictive value (NPV) of 100%.

CONCLUSIONS

The present study evaluated the brain connectivity through quantitative EEG analysis in Parkinson's disease versus healthy controls, showing a higher PLV connectivity in the delta band during the motor task, in HC compared to PD. This neurophysiology biomarkers showed the potentiality to be explored in future studies as a potential screening biomarker for PD patients.

Assessment of movement disorders using wearable sensors during upper limb tasks: A scoping review

Background: Studies aiming to objectively quantify movement disorders during upper limb tasks using wearable sensors have recently increased, but there is a wide variety in described measurement and analyzing methods, hampering standardization of methods in research and clinics. Therefore, the primary objective of this review was to provide an overview of sensor set-up and type, included tasks, sensor features and methods used to quantify movement disorders during upper limb tasks in multiple pathological populations. The secondary objective was to identify the most sensitive sensor features for the detection and quantification of movement disorders on the one hand and to describe the clinical application of the proposed methods on the other hand. Methods: A literature search using Scopus, Web of Science, and PubMed was performed. Articles needed to meet following criteria: 1) participants were adults/children with a neurological disease, 2) (at least) one sensor was placed on the upper limb for evaluation of movement disorders during upper limb tasks, 3) comparisons between: groups with/without movement disorders, sensor features before/after intervention, or sensor features with a clinical scale for assessment of the movement disorder. 4) Outcome measures included sensor features from acceleration/angular velocity signals. Results: A total of 101 articles were included, of which 56 researched Parkinson's Disease. Wrist(s), hand(s) and index finger(s) were the most popular sensor locations. Most frequent tasks were: finger tapping, wrist pro/supination, keeping the arms extended in front of the body and finger-to-nose. Most frequently calculated sensor features were mean, standard deviation, root-mean-square, ranges, skewness, kurtosis/entropy of acceleration and/or angular velocity, in combination with dominant frequencies/power of acceleration signals. Examples of clinical applications were automatization of a clinical scale or discrimination between a patient/control group or different patient groups. Conclusion: Current overview can support clinicians and researchers in selecting the most sensitive pathology-dependent sensor features and methodologies for detection and quantification of upper limb movement disorders and objective evaluations of treatment effects. Insights from Parkinson's Disease studies can accelerate the development of wearable sensors protocols in the remaining pathologies, provided that there is sufficient attention for the standardisation of protocols, tasks, feasibility and data analysis methods.

Long Short-Term Memory-Based Deep Learning Models for Screening Parkinson's Disease Using Sequential Diagnostic Codes

BACKGROUND AND PURPOSE

It is challenging to detect Parkinson's disease (PD) in its early stages, which has prompted researchers to develop techniques based on machine learning methods for detecting PD. However, previous studies did not fully incorporate the slow progression of PD over a long period of time nor consider that its symptoms occur in a time-sequential manner. Contributing to the literature on PD, which has relied heavily on cross-sectional data, this study aimed to develop a method for detecting PD early that can process time-series information using the long short-term memory (LSTM) algorithm.

METHODS

We sampled 926 patients with PD and 9,260 subjects without PD using medical-claims data. The LSTM algorithm was tested using diagnostic histories, which contained the diagnostic codes and their respective time information. We compared the prediction power of the 12-month diagnostic codes under two different settings over the 4 years prior to the first PD diagnosis.

RESULTS

The model that was trained using the most-recent 12-month diagnostic codes had the best performance, with an accuracy of 94.25%, a sensitivity of 82.91%, and a specificity of 95.26%. The other three models (12-month codes from 2, 3, and 4 years prior) were found to have comparable performances, with accuracies of 92.27%, 91.86%, and 91.81%, respectively. The areas under the curve from our data settings ranged from 0.839 to 0.923.

CONCLUSIONS

We explored the possibility that PD specialists could benefit from our proposed machine learning method as an early detection method for PD.

Digital Devices for Assessing Motor Functions in Mobility-Impaired and Healthy Populations: Systematic Literature Review

Background

With the advent of smart sensing technology, mobile and wearable devices can provide continuous and objective monitoring and assessment of motor function outcomes.

Objective

We aimed to describe the existing scientific literature on wearable and mobile technologies that are being used or tested for assessing motor functions in mobility-impaired and healthy adults and to evaluate the degree to which these devices provide clinically valid measures of motor function in these populations.

Methods

A systematic literature review was conducted by searching Embase, MEDLINE, CENTRAL (January 1, 2015, to June 24, 2020), the United States and European Union clinical trial registries, and the United States Food and Drug Administration website using predefined study selection criteria. Study selection, data extraction, and quality assessment were performed by 2 independent reviewers.

Results

A total of 91 publications representing 87 unique studies were included. The most represented clinical conditions were Parkinson disease (n=51 studies), followed by stroke (n=5), Huntington disease (n=5), and multiple sclerosis (n=2). A total of 42 motion-detecting devices were identified, and the majority (n=27, 64%) were created for the purpose of health care–related data collection, although approximately 25% were personal electronic devices (eg, smartphones and watches) and 11% were entertainment consoles (eg, Microsoft Kinect or Xbox and Nintendo Wii). The primary motion outcomes were related to gait (n=30), gross motor movements (n=25), and fine motor movements (n=23). As a group, sensor-derived motion data showed a mean sensitivity of 0.83 (SD 7.27), a mean specificity of 0.84 (SD 15.40), a mean accuracy of 0.90 (SD 5.87) in discriminating between diseased individuals and healthy controls, and a mean Pearson r validity coefficient of 0.52 (SD 0.22) relative to clinical measures. We did not find significant differences in the degree of validity between in-laboratory and at-home sensor-based assessments nor between device class (ie, health care–related device, personal electronic devices, and entertainment consoles).

Conclusions

Sensor-derived motion data can be leveraged to classify and quantify disease status for a variety of neurological conditions. However, most of the recent research on digital clinical measures is derived from proof-of-concept studies with considerable variation in methodological approaches, and much of the reviewed literature has focused on clinical validation, with less than one-quarter of the studies performing analytical validation. Overall, future research is crucially needed to further consolidate that sensor-derived motion data may lead to the development of robust and transformative digital measurements intended to predict, diagnose, and quantify neurological disease state and its longitudinal change.

Deep Clinical Phenotyping of Parkinson's Disease: Towards a New Era of Research and Clinical Care

Despite recent advances in technology, clinical phenotyping of Parkinson's disease (PD) has remained relatively limited as current assessments are mainly based on empirical observation and subjective categorical judgment at the clinic. A lack of comprehensive, objective, and quantifiable clinical phenotyping data has hindered our capacity to diagnose, assess patients' conditions, discover pathogenesis, identify preclinical stages and clinical subtypes, and evaluate new therapies. Therefore, deep clinical phenotyping of PD patients is a necessary step towards understanding PD pathology and improving clinical care. In this review, we present a growing community consensus and perspective on how to clinically phenotype this disease, that is, to phenotype the entire course of disease progression by integrating capacity, performance, and perception approaches with state-of-the-art technology. We also explore the most studied aspects of PD deep clinical phenotypes, namely, bradykinesia, tremor, dyskinesia and motor fluctuation, gait impairment, speech impairment, and non-motor phenotypes.

An Auxiliary Diagnostic System for Parkinson's Disease Based on Wearable Sensors and Genetic Algorithm Optimized Random Forest

Parkinson's disease (PD) is a neurodegenerative disorder characterized mainly by motor-related impairment, an accurate, quantitative, and objective diagnosis is an effective way to slow the disease deterioration process. In this paper, a user-friendly auxiliary diagnostic system for PD is constructed based on the upper limb movement conditions of 100 subjects consisting of 50 PD patients and 50 healthy subjects. This system includes wearable sensors that collect upper limb movement data, host computer for data processing and classification, and graphic user interface (GUI). The genetic algorithm optimized random forest classifier is introduced to classify PD and normal states based on the selected optimal features, and the 50 trials leave-one-out cross-validation is used to evaluate the performance of the classifier, with the highest accuracy of 94.4%. The classification accuracy among different upper limb movement tasks and with the different number of sensors are compared, results show that the task with only alternation hand movement also has satisfactory classification accuracy, and sensors on both wrists performance better than one sensor on a single wrist. The utility of the proposed system is illustrated by neurologists with a deployed GUI during the clinical inquiry, opening the possibility for a wide range of applications in the auxiliary diagnosis of PD.

Outcome Assessment in Parkinson Disease Prevention Trials: Utility of Clinical and Digital Measures

BACKGROUND AND OBJECTIVES

The prodromal phase of Parkinson disease (PD) is accompanied by subtle clinical signs that are not sufficient for diagnosis but could potentially be measured in the context of clinical trials of therapies intended to delay or prevent more definitive clinical features. The objective of this study was to review the available literature on the presence and time course of subtle motor features in prodromal PD in the context of planning for possible clinical trials.

METHODS

We reviewed the available literature based on expert opinion. We considered a range of outcomes including measurement of clinical features, patient-reported outcomes, digital markers, and clinical diagnosis.

RESULTS

We considered these features and measures in the context of patient stratification, intermediate outcomes, and clinically relevant end points, including phenoconversion.

DISCUSSION

Substantial progress has been made in understanding how motor features evolve in the period immediately before a PD diagnosis. Digital measures hold substantial progress for measurement precision and may be additionally relevant because they can be used in naturalistic environments outside the clinic. Future studies should focus on advancing digital sensor technology and analysis and developing methods to implement available methods, particularly determination of a clinical diagnosis of PD, in a clinical trial context.

A Novel Machine Learning Algorithm Predicts Dementia With Lewy Bodies Versus Parkinson's Disease Dementia Based on Clinical and Neuropsychological Scores

OBJECTIVE

Our aim was to develop a machine learning algorithm based only on non-invasively clinic collectable predictors, for the accurate diagnosis of these disorders.

METHODS

This is an ongoing prospective cohort study (ClinicalTrials.gov identifier NCT number NCT04448340) of 78 PDD and 62 DLB subjects whose diagnostic follow-up is available for at least 3 years after the baseline assessment. We used predictors such as clinico-demographic characteristics, 6 neuropsychological tests (mini mental, PD Cognitive Rating Scale, Brief Visuospatial Memory test, Symbol digit written, Wechsler adult intelligence scale, trail making A and B). We investigated logistic regression, K-Nearest Neighbors (K-NNs) Support Vector Machine (SVM), Naïve Bayes classifier, and Ensemble Model for their ability to predict successfully PDD or DLB diagnosis.

RESULTS

The K-NN classification model had an accuracy 91.2% of overall cases based on 15 best clinical and cognitive scores achieving 96.42% sensitivity and 81% specificity on discriminating between DLB and PDD. The binomial logistic regression classification model achieved an accuracy of 87.5% based on 15 best features, showing 93.93% sensitivity and 87% specificity. The SVM classification model had an accuracy 84.6% of overall cases based on 15 best features achieving 90.62% sensitivity and 78.58% specificity. A model created on Naïve Bayes classification had 82.05% accuracy, 93.10% sensitivity and 74.41% specificity. Finally, an Ensemble model, synthesized by the individual ones, achieved 89.74% accuracy, 93.75% sensitivity and 85.73% specificity.

CONCLUSION

Machine learning method predicted with high accuracy, sensitivity and specificity PDD or DLB diagnosis based on non-invasively and easily in-the-clinic and neuropsychological tests.

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 comparison of prediction approaches for identifying prodromal Parkinson disease

Identifying people with Parkinson disease during the prodromal period, including via algorithms in administrative claims data, is an important research and clinical priority. We sought to improve upon an existing penalized logistic regression model, based on diagnosis and procedure codes, by adding prescription medication data or using machine learning. Using Medicare Part D beneficiaries age 66–90 from a population-based case-control study of incident Parkinson disease, we fit a penalized logistic regression both with and without Part D data. We also built a predictive algorithm using a random forest classifier for comparison. In a combined approach, we introduced the probability of Parkinson disease from the random forest, as a predictor in the penalized regression model. We calculated the receiver operator characteristic area under the curve (AUC) for each model. All models performed well, with AUCs ranging from 0.824 (simplest model) to 0.835 (combined approach). We conclude that medication data and random forests improve Parkinson disease prediction, but are not essential.

Deep learning model for distinguishing novel coronavirus from other chest related infections in X-ray images

Novel Coronavirus is deadly for humans and animals. The ease of its dispersion, coupled with its tremendous capability for ailment and death in infected people, makes it a risk to society. The chest X-ray is conventional but hard to interpret radiographic test for initial diagnosis of coronavirus from other related infections. It bears a considerable amount of information on physiological and anatomical features. To extract relevant information from it can occasionally become challenging even for a professional radiologist. In this regard, deep-learning models can help in swift, accurate and reliable outcomes. Existing datasets are small and suffer from the balance issue. In this paper, we prepare a relatively larger and well-balanced dataset as compared to the available datasets. Furthermore, we analyze deep learning models, namely, AlexNet, SqueezeNet, DenseNet201, MobileNetV2 and InceptionV3 with numerous variations such as training the models from scratch, fine-tuning without pre-trained weights, fine-tuning along with updating pre-trained weights of all layers, and fine-tuning with pre-trained weights along with applying augmentation. Our results show that fine-tuning with augmentation generates best results in pre-trained models. Finally, we have made architectural adjustments in MobileNetV2 and InceptionV3 models to learn more intricate features, which are then merged in our proposed ensemble model. The performance of our model is statistically analyzed against other models using four different performance metrics with paired two-sided t-test on 5 different splits of training and test sets of our dataset. We find that it is statistically better than its competing methods for the four metrics. Thus, the computer-aided classification based on the proposed model can assist radiologists in identifying coronavirus from other related infections in chest X-rays with higher accuracy. This can help in a reliable and speedy diagnosis, thereby saving valuable lives and mitigating the adverse impact on the socioeconomics of our community.

Multimodal Classification of Parkinson's Disease in Home Environments with Resiliency to Missing Modalities

Parkinson’s disease (PD) is a chronic neurodegenerative condition that affects a patient’s everyday life. Authors have proposed that a machine learning and sensor-based approach that continuously monitors patients in naturalistic settings can provide constant evaluation of PD and objectively analyse its progression. In this paper, we make progress toward such PD evaluation by presenting a multimodal deep learning approach for discriminating between people with PD and without PD. Specifically, our proposed architecture, named MCPD-Net, uses two data modalities, acquired from vision and accelerometer sensors in a home environment to train variational autoencoder (VAE) models. These are modality-specific VAEs that predict effective representations of human movements to be fused and given to a classification module. During our end-to-end training, we minimise the difference between the latent spaces corresponding to the two data modalities. This makes our method capable of dealing with missing modalities during inference. We show that our proposed multimodal method outperforms unimodal and other multimodal approaches by an average increase in F1-score of 0.25 and 0.09, respectively, on a data set with real patients. We also show that our method still outperforms other approaches by an average increase in F1-score of 0.17 when a modality is missing during inference, demonstrating the benefit of training on multiple modalities.

Machine Learning for the Diagnosis of Parkinson's Disease: A Review of Literature

Diagnosis of Parkinson's disease (PD) is commonly based on medical observations and assessment of clinical signs, including the characterization of a variety of motor symptoms. However, traditional diagnostic approaches may suffer from subjectivity as they rely on the evaluation of movements that are sometimes subtle to human eyes and therefore difficult to classify, leading to possible misclassification. In the meantime, early non-motor symptoms of PD may be mild and can be caused by many other conditions. Therefore, these symptoms are often overlooked, making diagnosis of PD at an early stage challenging. To address these difficulties and to refine the diagnosis and assessment procedures of PD, machine learning methods have been implemented for the classification of PD and healthy controls or patients with similar clinical presentations (e.g., movement disorders or other Parkinsonian syndromes). To provide a comprehensive overview of data modalities and machine learning methods that have been used in the diagnosis and differential diagnosis of PD, in this study, we conducted a literature review of studies published until February 14, 2020, using the PubMed and IEEE Xplore databases. A total of 209 studies were included, extracted for relevant information and presented in this review, with an investigation of their aims, sources of data, types of data, machine learning methods and associated outcomes. These studies demonstrate a high potential for adaptation of machine learning methods and novel biomarkers in clinical decision making, leading to increasingly systematic, informed diagnosis of PD.

Innovative motor and cognitive dual-task approaches combining upper and lower limbs may improve dementia early detection

Motor and Cognitive Dual-Task (MCDT) represents an innovative chance to assess Mild Cognitive Impairment (MCI). We compare two novel MCDTs, fore-finger tapping (FTAP), toe-tapping (TTHP), to gold standards for cognitive screening (Mini-Mental State Examination-MMSE), and to a well-established MCDT (GAIT). We administered the aforementioned MCDTs to 44 subjects (MCIs and controls). Motor parameters were extracted, and correlations with MMSE investigated. Logistic regression models were built, and AUC areas computed. Spearman's correlation demonstrated that FTAP and TTHP significantly correlate with MMSE, at each cognitive load. AUC areas computed report similar (FTAP, 0.87), and even higher (TTHP, 0.97) capability to identify MCIs, if compared to GAIT (0.92). We investigated the use of novel MCDT approaches to assess MCI, aiming to enrich the clinical repertoire with objective and non-invasive tools. Our protocol shows good correlations with MMSE, and reaches high performances in identifying MCI, adopting simpler exercises.

An artificial neural network approach to detect presence and severity of Parkinson's disease via gait parameters

Introduction

Gait deficits are debilitating in people with Parkinson’s disease (PwPD), which inevitably deteriorate over time. Gait analysis is a valuable method to assess disease-specific gait patterns and their relationship with the clinical features and progression of the disease.

Objectives

Our study aimed to i) develop an automated diagnostic algorithm based on machine-learning techniques (artificial neural networks [ANNs]) to classify the gait deficits of PwPD according to disease progression in the Hoehn and Yahr (H-Y) staging system, and ii) identify a minimum set of gait classifiers.

Methods

We evaluated 76 PwPD (H-Y stage 1–4) and 67 healthy controls (HCs) by computerized gait analysis. We computed the time-distance parameters and the ranges of angular motion (RoMs) of the hip, knee, ankle, trunk, and pelvis. Principal component analysis was used to define a subset of features including all gait variables. An ANN approach was used to identify gait deficits according to the H-Y stage.

Results

We identified a combination of a small number of features that distinguished PwPDs from HCs (one combination of two features: knee and trunk rotation RoMs) and identified the gait patterns between different H-Y stages (two combinations of four features: walking speed and hip, knee, and ankle RoMs; walking speed and hip, knee, and trunk rotation RoMs).

Conclusion

The ANN approach enabled automated diagnosis of gait deficits in several symptomatic stages of Parkinson’s disease. These results will inspire future studies to test the utility of gait classifiers for the evaluation of treatments that could modify disease progression.

What the Tech? The Management of Neurological Dysfunction Through the Use of Digital Technology

Worldwide, it is estimated that millions of individuals suffer from a neurological disorder which can be the result of head injuries, ischaemic events such as a stroke, or neurodegenerative disorders such as Parkinson's disease (PD) and multiple sclerosis (MS). Problems with mobility and hemiparesis are common for these patients, making daily life, social factors and independence heavily affected. Current therapies aimed at improving such conditions are often tedious in nature, with patients often losing vital motivation and positive outlook towards their rehabilitation. The interest in the use of digital technology in neuro-rehabilitation has skyrocketed in the past decade. To gain insight, a systematic review of the literature in the field was conducting following the Preferred Reporting Items for Systematic Review and Meta-analyses (PRISMA) guidelines for three categories: stroke, Parkinson's disease and multiple sclerosis. It was found that the majority of the literature (84%) was in favour of the use of digital technologies in the management of neurological dysfunction; with some papers taking a "neutral" or "against" standpoint. It was found that the use of technologies such as virtual reality (VR), robotics, wearable sensors and telehealth was highly accepted by patients, helped to improve function, reduced anxiety and make therapy more accessible to patients living in more remote areas. The most successful therapies were those that used a combination of conventional therapies and new digital technologies.

An SBM-based machine learning model for identifying mild cognitive impairment in patients with Parkinson's disease

OBJECTIVE

To identify Parkinson's disease with mild cognitive impairment (PD-MCI) through surface-based morphometry (SBM) based machine learning model.

METHODS

93 patients with parkinson's disease (35 PD with normal cognition, 58 PD-MCI) were examined, obtaining 276 SBM variables per subject. 20 healthy control subjects were used as the reference. After extracting features with statistically significance, support vector machine (SVM) model with grid search method was applied to identify patients with PD-MCI. Accuracy, matthews correlation coefficient (MCC), receiver operating characteristic curve (ROC), precision-recall curve (PR), AUC-ROC, AUC-PR and leave-one-out cross validation (LOOCV) strategy were employed for model evaluation.

RESULTS

PD-MCI is characterized by widespread structural abnormality. SVM model with SBM features achieved an accuracy of 80.00% and area under the ROC of 0.86 for identifying PD-MCI. MCC, AUC-PR, and LOOCV classification accuracy were 0.56, 0.89, and 78.08%, respectively.

CONCLUSION

Automatic identification of PD-MCI could be realized by SBM-based machine learning model.

Biomechanical parameters assessment for the classification of Parkinson Disease using Bidirectional Long Short-Term Memory

Nowadays objective and efficient assessment of Parkinson Disease (PD) with machine learning techniques is a major focus for clinical management. This work presents a novel approach for classification of patients with PD (PwPD) and healthy controls (HC) using Bidirectional Long Short-Term Neural Network (BLSTM). In this paper, the SensHand and the SensFoot inertial wearable sensors for upper and lower limbs motion analysis were used to acquire motion data in thirteen tasks derived from the MDS-UPDRS III. Sixty-four PwPD and fifty HC were involved in this study. One hundred ninety extracted spatiotemporal and frequency parameters were applied as a single input against each subject to develop a recurrent BLSTM to discriminate the two groups. The maximum achieved accuracy was 82.4%, with the sensitivity of 92.3% and specificity of 76.2%. The obtained results suggest that the use of the extracted parameters for the development of the BLSTM contributed significantly to the classification of PwPD and HC.

Data-Driven Models for Objective Grading Improvement of Parkinson's Disease

Parkinson's disease (PD) is a progressive disorder of the central nervous system that causes motor dysfunctions in affected patients. Objective assessment of symptoms can support neurologists in fine evaluations, improving patients' quality of care. Herein, this study aimed to develop data-driven models based on regression algorithms to investigate the potential of kinematic features to predict PD severity levels. Sixty-four patients with PD (PwPD) and 50 healthy subjects of control (HC) were asked to perform 13 motor tasks from the MDS-UPDRS III while wearing wearable inertial sensors. Simultaneously, the clinician provided the evaluation of the tasks based on the MDS-UPDRS scores. One hundred-ninety kinematic features were extracted from the inertial motor data. Data processing and statistical analysis identified a set of parameters able to distinguish between HC and PwPD. Then, multiple feature selection methods allowed selecting the best subset of parameters for obtaining the greatest accuracy when used as input for several predicting regression algorithms. The maximum correlation coefficient, equal to 0.814, was obtained with the adaptive neuro-fuzzy inference system (ANFIS). Therefore, this predictive model could be useful as a decision support system for a reliable objective assessment of PD severity levels based on motion performance, improving patients monitoring over time.

Instrumental analysis of finger tapping reveals a novel early biomarker of parkinsonism in idiopathic rapid eye movement sleep behaviour disorder

BACKGROUND

Idiopathic rapid eye movement sleep behaviour (iRBD) is considered as a risk factor for Parkinson's disease (PD) development. Evaluation of repetitive movements with finger tapping, which serves as a principal task to measure the extent of bradykinesia in PD, may undercover potential PD patients. The aim of this study was to explore whether finger tapping abnormalities, evaluated with a 3D motion capture system, are already present in RBD patients.

METHODS

Finger tapping data was acquired using a contactless 3D motion capture system from 40 RBD subjects and compared to 25 de-novo PD patients and 25 healthy controls. Objective assessment of amplitude decrement, maximum opening velocity and their combination representing finger tapping decrement was performed in the sequence of the first ten tapping movements. The association between instrumental finger tapping data and semi-quantitative clinical evaluation was analyzed.

RESULTS

While significant differences between PD and controls were found for all investigated finger tapping measures (p < 0.002), RBD differed from controls in finger tapping amplitude (p = 0.004) and velocity (p = 0.007) decrement but not in maximal opening velocity. A significant relationship between the motor score from the Movement Disorders Society - Unified Parkinson's Disease Rating Scale and finger tapping decrement was shown for both patient groups, ie RBD (r = 0.36, p = 0.02) and PD (r = 0.60, p = 0.002).

CONCLUSIONS

In our group of RBD patients we demonstrated amplitude decrement of repetitive movements, which may correspond with prodromal bradykinesia. Our findings suggest instrumental analysis of finger tapping abnormalities as a potential novel clinical marker reflecting subclinical motor disturbances in RBD.

Wearable Sensors for Prodromal Motor Assessment of Parkinson's Disease using Supervised Learning

Parkinson's disease (PD) is a common neurodegenerative disorder characterized by disabling motor and non-motor symptoms. Idiopathic hyposmia (IH), a reduced olfactory sensitivity, is a preclinical marker for the pathology and affects >95% of PD patients. In this paper, SensHand V1 and SensFoot V2, two inertial wearable sensors for upper and lower limbs, were developed to acquire motion data in ten tasks of the MDS-UPDRS III. Fifteen healthy subjects of control, 15 IH people, and 15 PD patients were enrolled. Seventy-one parameters per side were computed by spatiotemporal and frequency data analysis, and the most significant were selected to distinguish among the different classes. Performances of supervised learning algorithms (i.e., Support Vector Machine (SVM), and Random Forest (RF)) were compared on two-group and three-group classification and considering upper and lower limbs separately or together as a full system. Excellent results were obtained for healthy vs. patients classification (accuracy 1.00 for RF, and 0.97 for SVM), and good results were achieved by including IH subjects (0.92 F-measure with RF) within a three-group classification. Overall, the best performances were obtained using the full system with an RF classifier. The system is, thus, suitable to support an objective PD diagnosis. Furthermore, combining motion analysis with a validated olfactory screening test, people at risk for PD can be appropriately analyzed, and subtle changes in motor performance that characterize the prodromal phase and the early PD onset can be identified.

Smartphone-Based Evaluation of Postural Stability in Parkinson’s Disease Patients During Quiet Stance

Background: Postural instability is one of the most troublesome motor symptoms of Parkinson’s Disease (PD). It impairs patients’ quality of life and results in high risk of falls. The aim of this study is to provide a reliable tool for the automated assessment of postural instability. Methods: Data acquisition was performed on 42 PD patients and 7 young healthy subjects. They were asked to keep a quiet stance position for at least 30 s while wearing a waist-mounted smartphone. A total number of 414 features was extracted from both time and frequency domain, selected based on Pearson’s correlation, and fed to an optimized Support Vector Machine. Results: The implemented model was able to differentiate patients with mild postural instability from those with severe postural instability and from healthy controls, with 100% accuracy. Conclusion: This study demonstrated the feasibility of using inertial sensors embedded in commercial smartphones and proposed a simple protocol for accurate postural instability scoring. This tool can be used for early detection of PD motor signs, disease follow-up and fall prevention.

A Wearable System to Objectify Assessment of Motor Tasks for Supporting Parkinson's Disease Diagnosis

Objective assessment of the motor evaluation test for Parkinson’s disease (PD) diagnosis is an open issue both for clinical and technical experts since it could improve current clinical practice with benefits both for patients and healthcare systems. In this work, a wearable system composed of four inertial devices (two SensHand and two SensFoot), and related processing algorithms for extracting parameters from limbs motion was tested on 40 healthy subjects and 40 PD patients. Seventy-eight and 96 kinematic parameters were measured from lower and upper limbs, respectively. Statistical and correlation analysis allowed to define four datasets that were used to train and test five supervised learning classifiers. Excellent discrimination between the two groups was obtained with all the classifiers (average accuracy ranging from 0.936 to 0.960) and all the datasets (average accuracy ranging from 0.953 to 0.966), over three conditions that included parameters derived from lower, upper or all limbs. The best performances (accuracy = 1.00) were obtained when classifying all the limbs with linear support vector machine (SVM) or gaussian SVM. Even if further studies should be done, the current results are strongly promising to improve this system as a support tool for clinicians in objectifying PD diagnosis and monitoring.

Early diagnosis of Parkinson's disease using machine learning algorithms

Parkinson's disease is caused by the disruption of the brain cells that produce substance to allow brain cells to communicate with each other, called dopamine. The cells that produce dopamine in the brain are responsible for the control, adaptation and fluency of movements. When 60-80%of these cells are lost, then enough dopamine is not produced and Parkinson's motor symptoms appear. It is thought that the disease begins many years before the motor (movement related) symptoms and therefore, researchers are looking for ways to recognize the non-motor symptoms that appear early in the disease as early as possible, thereby halting the progression of the disease. In this paper, machine learning based diagnosis of Parkinson's disease is presented. The proposed diagnosis method consists of feature selection and classification processes. Feature Importance and Recursive Feature Elimination methods were considered for feature selection task. Classification and Regression Trees, Artificial Neural Networks, and Support Vector Machines were used for the classification of Parkinson's patients in the experiments. Support Vector Machines with Recursive Feature Elimination was shown to perform better than the other methods. 93.84% accuracy was achieved with the least number of voice features for Parkinson's diagnosis.

A low-cost vision system based on the analysis of motor features for recognition and severity rating of Parkinson's Disease

Background

Assessment and rating of Parkinson’s Disease (PD) are commonly based on the medical observation of several clinical manifestations, including the analysis of motor activities. In particular, medical specialists refer to the MDS-UPDRS (Movement Disorder Society – sponsored revision of Unified Parkinson’s Disease Rating Scale) that is the most widely used clinical scale for PD rating. However, clinical scales rely on the observation of some subtle motor phenomena that are either difficult to capture with human eyes or could be misclassified. This limitation motivated several researchers to develop intelligent systems based on machine learning algorithms able to automatically recognize the PD. Nevertheless, most of the previous studies investigated the classification between healthy subjects and PD patients without considering the automatic rating of different levels of severity.

Methods

In this context, we implemented a simple and low-cost clinical tool that can extract postural and kinematic features with the Microsoft Kinect v2 sensor in order to classify and rate PD. Thirty participants were enrolled for the purpose of the present study: sixteen PD patients rated according to MDS-UPDRS and fourteen healthy paired subjects. In order to investigate the motor abilities of the upper and lower body, we acquired and analyzed three main motor tasks: (1) gait, (2) finger tapping, and (3) foot tapping. After preliminary feature selection, different classifiers based on Support Vector Machine (SVM) and Artificial Neural Networks (ANN) were trained and evaluated for the best solution.

Results

Concerning the gait analysis, results showed that the ANN classifier performed the best by reaching 89.4% of accuracy with only nine features in diagnosis PD and 95.0% of accuracy with only six features in rating PD severity. Regarding the finger and foot tapping analysis, results showed that an SVM using the extracted features was able to classify healthy subjects versus PD patients with great performances by reaching 87.1% of accuracy. The results of the classification between mild and moderate PD patients indicated that the foot tapping features were the most representative ones to discriminate (81.0% of accuracy).

Conclusions

The results of this study have shown how a low-cost vision-based system can automatically detect subtle phenomena featuring the PD. Our findings suggest that the proposed tool can support medical specialists in the assessment and rating of PD patients in a real clinical scenario.

Support Vector Machine-Based Classifier for the Assessment of Finger Movement of Stroke Patients Undergoing Rehabilitation

Purpose

Traditionally, clinical evaluation of motor paralysis following stroke has been of value to physicians and therapists because it allows for immediate pathophysiological assessment without the need for specialized tools. However, current clinical methods do not provide objective quantification of movement; therefore, they are of limited use to physicians and therapists when assessing responses to rehabilitation. The present study aimed to create a support vector machine (SVM)-based classifier to analyze and validate finger kinematics using the leap motion controller. Results were compared with those of 24 stroke patients assessed by therapists.

Methods

A non-linear SVM was used to classify data according to the Brunnstrom recovery stages of finger movements by focusing on peak angle and peak velocity patterns during finger flexion and extension. One thousand bootstrap data values were generated by randomly drawing a series of sample data from the actual normalized kinematics-related data. Bootstrap data values were randomly classified into training (940) and testing (60) datasets. After establishing an SVM classification model by training with the normalized kinematics-related parameters of peak angle and peak velocity, the testing dataset was assigned to predict classification of paralytic movements.

Results

High separation accuracy was obtained (mean 0.863; 95% confidence interval 0.857–0.869; p = 0.006).

Conclusion

This study highlights the ability of artificial intelligence to assist physicians and therapists evaluating hand movement recovery of stroke patients.