Machine learning for large-scale wearable sensor data in Parkinson's disease: Concepts, promises, pitfalls, and futures

A unified approach for Parkinson's disease recognition: imbalance mitigation and grid search optimized boosting with LightGBM

The work elucidates the importance of accurate Parkinson's disease classification within medical diagnostics and introduces a novel framework for achieving this goal. Specifically, the study focuses on enhancing disease identification accuracy utilizing boosting methods. A standout contribution of this work lies in the utilization of a light gradient boosting machine (LGBM) coupled with hyperparameter tuning through grid search optimization (GSO) on the Parkinson's disease dataset derived from speech recording signals. In addition, the Synthetic Minority Over-sampling Technique (SMOTE) has also been employed as a pre-processing technique to balance the dataset, enhancing the robustness and reliability of the analysis. This approach is a novel addition to the study and underscores its potential to enhance disease identification accuracy. The datasets employed in this work include both gender-specific and combined cases, utilizing several distinctive feature subsets including baseline, Mel-frequency cepstral coefficients (MFCC), time-frequency, wavelet transform (WT), vocal fold, and tunable-Q-factor wavelet transform (TQWT). Comparative analyses against state-of-the-art boosting methods, such as AdaBoost and XG-Boost, reveal the superior performance of our proposed approach across diverse datasets and metrics. Notably, on the male cohort dataset, our method achieves exceptional results, demonstrating an accuracy of 0.98, precision of 1.00, sensitivity of 0.97, F1-Score of 0.98, and specificity of 1.00 when utilizing all features with GSO-LGBM. In comparison to AdaBoost and XGBoost, the proposed framework utilizing LGBM demonstrates superior accuracy, achieving an average improvement of 5% in classification accuracy across all feature subsets and datasets. These findings underscore the potential of the proposed methodology to enhance disease identification accuracy and provide valuable insights for further advancements in medical diagnostics.

Motor assessment of X-linked dystonia parkinsonism via machine-learning-based analysis of wearable sensor data

X-linked dystonia parkinsonism (XDP) is a neurogenetic combined movement disorder involving both parkinsonism and dystonia. Complex, overlapping phenotypes result in difficulties in clinical rating scale assessment. We performed wearable sensor-based analyses in XDP participants to quantitatively characterize disease phenomenology as a potential clinical trial endpoint. Wearable sensor data was collected from 10 symptomatic XDP patients and 3 healthy controls during a standardized examination. Disease severity was assessed with the Unified Parkinson's Disease Rating Scale Part 3 (MDS-UPDRS) and Burke-Fahn-Marsden dystonia scale (BFM). We collected sensor data during the performance of specific MDS-UPDRS/BFM upper- and lower-limb motor tasks, and derived data features suitable to estimate clinical scores using machine learning (ML). XDP patients were at varying stages of disease and clinical severity. ML-based algorithms estimated MDS-UPDRS scores (parkinsonism) and dystonia-specific data features with a high degree of accuracy. Gait spatio-temporal parameters had high discriminatory power in differentiating XDP patients with different MDS-UPDRS scores from controls, XDP freezing of gait, and dystonic/non-dystonic gait. These analyses suggest the feasibility of using wearable sensor data for deriving reliable clinical score estimates associated with both parkinsonian and dystonic features in a complex, combined movement disorder and the utility of motion sensors in quantifying clinical examination.

Leveraging ANFIS with Adam and PSO optimizers for Parkinson's disease

Parkinson's disease (PD) is an age-related neurodegenerative disorder characterized by motor deficits, including tremor, rigidity, bradykinesia, and postural instability. According to the World Health Organization, about 1 % of the global population has been diagnosed with PD, and this figure is expected to double by 2040. Early and accurate diagnosis of PD is critical to slowing down the progression of the disease and reducing long-term disability. Due to the complexity of the disease, it is difficult to accurately diagnose it using traditional clinical tests. Therefore, it has become necessary to develop intelligent diagnostic models that can accurately detect PD. This article introduces a novel hybrid approach for accurate prediction of PD using an ANFIS with two optimizers, namely Adam and PSO. ANFIS is a type of fuzzy logic system used for nonlinear function approximation and classification, while Adam optimizer has the ability to adaptively adjust the learning rate of each individual parameter in an ANFIS at each training step, which helps the model find a better solution more quickly. PSO is a metaheuristic approach inspired by the behavior of social animals such as birds. Combining these two methods has potential to provide improved accuracy and robustness in PD diagnosis compared to existing methods. The proposed method utilized the advantages of both optimization techniques and applied them on the developed ANFIS model to maximize its prediction accuracy. This system was developed by using an open access clinical and demographic data. The chosen parameters for the ANFIS were selected through a comparative experimental analysis to optimize the model considering the number of fuzzy membership functions, number of epochs of ANFIS, and number of particles of PSO. The performance of the two ANFIS models: ANFIS (Adam) and ANFIS (PSO) focusing at ANFIS parameters and various evaluation metrics are further analyzed in detail and presented, The experimental results showed that the proposed ANFIS (PSO) shows better results in terms of loss and precision, whereas, the ANFIS (Adam) showed the better results in terms of accuracy, f1-score and recall. Thus, this adaptive neural-fuzzy algorithm provides a promising strategy for the diagnosis of PD, and show that the proposed models show their suitability for many other practical applications.

A proof of concept: digital diary using 24-hour monitoring using wearable device for patients with Parkinson's disease in nursing homes

Introduction

In the advanced stages of Parkinson's disease (PD), motor complications such as wearing-off and dyskinesia are problematic and vary daily. These symptoms need to be monitored precisely to provide adequate care for patients with advanced PD.

Methods

This study used wearable devices to explore biomarkers for motor complications by measuring multiple biomarkers in patients with PD residing in facilities and combining them with lifestyle and clinical assessments. Data on the pulse rate and activity index (metabolic equivalents) were collected from 12 patients over 30 days.

Results

The pulse rate and activity index during the off- and on-periods and dyskinesia were analyzed for two participants; the pulse rate and activity index did not show any particular trend in each participant; however, the pulse rate/activity index was significantly greater in the off-state compared to that in the dyskinesia and on-states, and this index in the dyskinesia state was significantly greater than that in the on-state in both participants.

Conclusion

These results suggest the pulse rate and activity index combination would be a useful indicator of wearing-off and dyskinesia and that biometric information from wearable devices may function as a digital diary. Accumulating more cases and collecting additional data are necessary to verify our findings.

Kinematic Analysis of Human Gait in Healthy Young Adults Using IMU Sensors: Exploring Relevant Machine Learning Features for Clinical Applications

BACKGROUND

Gait is the manner or style of walking, involving motor control and coordination to adapt to the surrounding environment. Knowing the kinesthetic markers of normal gait is essential for the diagnosis of certain pathologies or the generation of intelligent ortho-prostheses for the treatment or prevention of gait disorders. The aim of the present study was to identify the key features of normal human gait using inertial unit (IMU) recordings in a walking test.

METHODS

Gait analysis was conducted on 32 healthy participants (age range 19-29 years) at speeds of 2 km/h and 4 km/h using a treadmill. Dynamic data were obtained using a microcontroller (Arduino Nano 33 BLE Sense Rev2) with IMU sensors (BMI270). The collected data were processed and analyzed using a custom script (MATLAB 2022b), including the labeling of the four relevant gait phases and events (Stance, Toe-Off, Swing, and Heel Strike), computation of statistical features (64 features), and application of machine learning techniques for classification (8 classifiers).

RESULTS

Spider plot analysis revealed significant differences in the four events created by the most relevant statistical features. Among the different classifiers tested, the Support Vector Machine (SVM) model using a Cubic kernel achieved an accuracy rate of 92.4% when differentiating between gait events using the computed statistical features.

CONCLUSIONS

This study identifies the optimal features of acceleration and gyroscope data during normal gait. The findings suggest potential applications for injury prevention and performance optimization in individuals engaged in activities involving normal gait. The creation of spider plots is proposed to obtain a personalised fingerprint of each patient's gait fingerprint that could be used as a diagnostic tool. A deviation from a normal gait pattern can be used to identify human gait disorders. Moving forward, this information has potential for use in clinical applications in the diagnosis of gait-related disorders and developing novel orthoses and prosthetics to prevent falls and ankle sprains.

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.

Frontiers of Wearable Biosensors for Human Health Monitoring

Wearable biosensors offer noninvasive, real-time, and continuous monitoring of diverse human health data, making them invaluable for remote patient tracking, early diagnosis, and personalized medicine [...].

Gait video-based prediction of unified Parkinson's disease rating scale score: a retrospective study

BACKGROUND

The diagnosis of Parkinson's disease (PD) and evaluation of its symptoms require in-person clinical examination. Remote evaluation of PD symptoms is desirable, especially during a pandemic such as the coronavirus disease 2019 pandemic. One potential method to remotely evaluate PD motor impairments is video-based analysis. In this study, we aimed to assess the feasibility of predicting the Unified Parkinson's Disease Rating Scale (UPDRS) score from gait videos using a convolutional neural network (CNN) model.

METHODS

We retrospectively obtained 737 consecutive gait videos of 74 patients with PD and their corresponding neurologist-rated UPDRS scores. We utilized a CNN model for predicting the total UPDRS part III score and four subscores of axial symptoms (items 27, 28, 29, and 30), bradykinesia (items 23, 24, 25, 26, and 31), rigidity (item 22) and tremor (items 20 and 21). We trained the model on 80% of the gait videos and used 10% of the videos as a validation dataset. We evaluated the predictive performance of the trained model by comparing the model-predicted score with the neurologist-rated score for the remaining 10% of videos (test dataset). We calculated the coefficient of determination (R2) between those scores to evaluate the model's goodness of fit.

RESULTS

In the test dataset, the R2 values between the model-predicted and neurologist-rated values for the total UPDRS part III score and subscores of axial symptoms, bradykinesia, rigidity, and tremor were 0.59, 0.77, 0.56, 0.46, and 0.0, respectively. The performance was relatively low for videos from patients with severe symptoms.

CONCLUSIONS

Despite the low predictive performance of the model for the total UPDRS part III score, it demonstrated relatively high performance in predicting subscores of axial symptoms. The model approximately predicted the total UPDRS part III scores of patients with moderate symptoms, but the performance was low for patients with severe symptoms owing to limited data. A larger dataset is needed to improve the model's performance in clinical settings.

Machine learning models for diagnosis and prognosis of Parkinson's disease using brain imaging: general overview, main challenges, and future directions

Parkinson's disease (PD) is a progressive and complex neurodegenerative disorder associated with age that affects motor and cognitive functions. As there is currently no cure, early diagnosis and accurate prognosis are essential to increase the effectiveness of treatment and control its symptoms. Medical imaging, specifically magnetic resonance imaging (MRI), has emerged as a valuable tool for developing support systems to assist in diagnosis and prognosis. The current literature aims to improve understanding of the disease's structural and functional manifestations in the brain. By applying artificial intelligence to neuroimaging, such as deep learning (DL) and other machine learning (ML) techniques, previously unknown relationships and patterns can be revealed in this high-dimensional data. However, several issues must be addressed before these solutions can be safely integrated into clinical practice. This review provides a comprehensive overview of recent ML techniques analyzed for the automatic diagnosis and prognosis of PD in brain MRI. The main challenges in applying ML to medical diagnosis and its implications for PD are also addressed, including current limitations for safe translation into hospitals. These challenges are analyzed at three levels: disease-specific, task-specific, and technology-specific. Finally, potential future directions for each challenge and future perspectives are discussed.

Multiscale Entropy Algorithms to Analyze Complexity and Variability of Trunk Accelerations Time Series in Subjects with Parkinson's Disease

The aim of this study was to assess the ability of multiscale sample entropy (MSE), refined composite multiscale entropy (RCMSE), and complexity index (CI) to characterize gait complexity through trunk acceleration patterns in subjects with Parkinson's disease (swPD) and healthy subjects, regardless of age or gait speed. The trunk acceleration patterns of 51 swPD and 50 healthy subjects (HS) were acquired using a lumbar-mounted magneto-inertial measurement unit during their walking. MSE, RCMSE, and CI were calculated on 2000 data points, using scale factors (τ) 1-6. Differences between swPD and HS were calculated at each τ, and the area under the receiver operating characteristics, optimal cutoff points, post-test probabilities, and diagnostic odds ratios were calculated. MSE, RCMSE, and CIs showed to differentiate swPD from HS. MSE in the anteroposterior direction at τ4 and τ5, and MSE in the ML direction at τ4 showed to characterize the gait disorders of swPD with the best trade-off between positive and negative posttest probabilities and correlated with the motor disability, pelvic kinematics, and stance phase. Using a time series of 2000 data points, a scale factor of 4 or 5 in the MSE procedure can yield the best trade-off in terms of post-test probabilities when compared to other scale factors for detecting gait variability and complexity in swPD.

The Classification of Movement in Infants for the Autonomous Monitoring of Neurological Development

Neurodevelopmental delay following extremely preterm birth or birth asphyxia is common but diagnosis is often delayed as early milder signs are not recognised by parents or clinicians. Early interventions have been shown to improve outcomes. Automation of diagnosis and monitoring of neurological disorders using non-invasive, cost effective methods within a patient's home could improve accessibility to testing. Furthermore, said testing could be conducted over a longer period, enabling greater confidence in diagnoses, due to increased data availability. This work proposes a new method to assess the movements in children. Twelve parent and infant participants were recruited (children aged between 3 and 12 months). Approximately 25 min 2D video recordings of the infants organically playing with toys were captured. A combination of deep learning and 2D pose estimation algorithms were used to classify the movements in relation to the children's dexterity and position when interacting with a toy. The results demonstrate the possibility of capturing and classifying children's complexity of movements when interacting with toys as well as their posture. Such classifications and the movement features could assist practitioners to accurately diagnose impaired or delayed movement development in a timely fashion as well as facilitating treatment monitoring.

Improved Parkinsonian tremor quantification based on automatic label modification and SVM with RBF kernel

Objective. The quantitative assessment of Parkinsonian tremor, e.g. (0, 1, 2, 3, 4) according to the Movement Disorder Society-Unified Parkinson's Disease Rating Scale, is crucial for treating Parkinson's disease. However, the tremor amplitude constantly fluctuates due to environmental and psychological effects on the patient. In clinical practice, clinicians assess the tremor severity for a short duration, whereas manual tremor labeling relies on the clinician's physician experience. Therefore, automatic tremor quantification based on wearable inertial sensors and machine learning algorithms is affected by the manual labels of clinicians. In this study, an automatic modification method for the labels judged by clinicians is presented to improve Parkinsonian tremor quantitation.Approach. For the severe overlapping of dynamic feature range between different severities, an outlier modification algorithm (PCA-IQR) based on the combination of principal component analysis and interquartile range statistic rule is proposed to learn the blurred borders between different severity scores, thereby optimizing the labels. Afterward, according to the modified feature vectors, a support vector machine (SVM) with a radial basis function (RBF) kernel is proposed to classify the tremor severity. The classifier models of SVM with RBF kernel,k-nearest neighbors, and SVM with the linear kernel are compared.Main results. Experimental results show that the proposed method has high classification performance and excellent model generalization ability for tremor quantitation (accuracy: 97.93%, precision: 97.96%, sensitivity: 97.93%, F1-score: 97.94%).Significance. The proposed method may not only provide valuable assistance for clinicians to assess the tremor severity accurately, but also provides self-monitoring for patients at home and improve the assessment skills of clinicians.

A Computerized Analysis with Machine Learning Techniques for the Diagnosis of Parkinson's Disease: Past Studies and Future Perspectives

According to the World Health Organization (WHO), Parkinson's disease (PD) is a neurodegenerative disease of the brain that causes motor symptoms including slower movement, rigidity, tremor, and imbalance in addition to other problems like Alzheimer's disease (AD), psychiatric problems, insomnia, anxiety, and sensory abnormalities. Techniques including artificial intelligence (AI), machine learning (ML), and deep learning (DL) have been established for the classification of PD and normal controls (NC) with similar therapeutic appearances in order to address these problems and improve the diagnostic procedure for PD. In this article, we examine a literature survey of research articles published up to September 2022 in order to present an in-depth analysis of the use of datasets, various modalities, experimental setups, and architectures that have been applied in the diagnosis of subjective disease. This analysis includes a total of 217 research publications with a list of the various datasets, methodologies, and features. These findings suggest that ML/DL methods and novel biomarkers hold promising results for application in medical decision-making, leading to a more methodical and thorough detection of PD. Finally, we highlight the challenges and provide appropriate recommendations on selecting approaches that might be used for subgrouping and connection analysis with structural magnetic resonance imaging (sMRI), DaTSCAN, and single-photon emission computerized tomography (SPECT) data for future Parkinson's research.

Towards a Visualizable, De-identified Synthetic Biomarker of Human Movement Disorders

Human motion analysis has been a common thread across modern and early medicine. While medicine evolves, analysis of movement disorders is mostly based on clinical presentation and trained observers making subjective assessments using clinical rating scales. Currently, the field of computer vision has seen exponential growth and successful medical applications. While this has been the case, neurology, for the most part, has not embraced digital movement analysis. There are many reasons for this including: the limited size of labeled datasets, accuracy and nontransparent nature of neural networks, and potential legal and ethical concerns. We hypothesize that a number of opportunities are made available by advancements in computer vision that will enable digitization of human form, movements, and will represent them synthetically in 3D. Representing human movements within synthetic body models will potentially pave the way towards objective standardized digital movement disorder diagnosis and building sharable open-source datasets from such processed videos. We provide a perspective of this emerging field and describe how clinicians and computer scientists can navigate this new space. Such digital movement capturing methods will be important for both machine learning-based diagnosis and computer vision-aided clinical assessment. It would also supplement face-to-face clinical visits and be used for longitudinal monitoring and remote diagnosis.

Integrated biosensor platform based on graphene transistor arrays for real-time high-accuracy ion sensing

Two-dimensional materials such as graphene have shown great promise as biosensors, but suffer from large device-to-device variation due to non-uniform material synthesis and device fabrication technologies. Here, we develop a robust bioelectronic sensing platform  composed of  more than 200 integrated sensing units, custom-built high-speed readout electronics, and machine learning inference that overcomes these challenges to achieve rapid, portable, and reliable measurements. The platform demonstrates reconfigurable multi-ion electrolyte sensing capability and provides highly sensitive, reversible, and real-time response for potassium, sodium, and calcium ions in complex solutions despite variations in device performance. A calibration method leveraging the sensor redundancy and device-to-device variation is also proposed, while a machine learning model trained with multi-dimensional information collected through the multiplexed sensor array is used to enhance the sensing system’s functionality and accuracy in ion classification.

The potential of 2D materials for biosensing applications is often limited by large device-to-device variation. Here, the authors report a calibration method and a machine learning approach leveraging the redundancy of a sensing platform based on 256 integrated graphene transistors to enhance the system accuracy in real-time ion classification.

Motor Signatures in Digitized Cognitive and Memory Tests Enhances Characterization of Parkinson's Disease

Although interest in using wearable sensors to characterize movement disorders is growing, there is a lack of methodology for developing clinically interpretable biomarkers. Such digital biomarkers would provide a more objective diagnosis, capturing finer degrees of motor deficits, while retaining the information of traditional clinical tests. We aim at digitizing traditional tests of cognitive and memory performance to derive motor biometrics of pen-strokes and voice, thereby complementing clinical tests with objective criteria, while enhancing the overall characterization of Parkinson's disease (PD). 35 participants including patients with PD, healthy young and age-matched controls performed a series of drawing and memory tasks, while their pen movement and voice were digitized. We examined the moment-to-moment variability of time series reflecting the pen speed and voice amplitude. The stochastic signatures of the fluctuations in pen drawing speed and voice amplitude of patients with PD show a higher signal-to-noise ratio compared to those of neurotypical controls. It appears that contact motions of the pen strokes on a tablet evoke sensory feedback for more immediate and predictable control in PD, while voice amplitude loses its neurotypical richness. We offer new standardized data types and analytics to discover the hidden motor aspects within the cognitive and memory clinical assays.

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.

Estimating longitudinal depressive symptoms from smartphone data in a transdiagnostic cohort

BACKGROUND

Passive measures collected using smartphones have been suggested to represent efficient proxies for depression severity, but the performance of such measures across diagnoses has not been studied.

METHODS

We enrolled a cohort of 45 individuals (11 with major depressive disorder, 11 with bipolar disorder, 11 with schizophrenia or schizoaffective disorder, and 12 individuals with no axis I psychiatric disorder). During the 8-week study period, participants were evaluated with a rater-administered Montgomery-Åsberg Depression Rating Scale (MADRS) biweekly, completed self-report PHQ-8 measures weekly on their smartphone, and consented to collection of smartphone-based GPS and accelerometer data in order to learn about their behaviors. We utilized linear mixed models to predict depression severity on the basis of phone-based PHQ-8 and passive measures.

RESULTS

Among the 45 individuals, 38 (84%) completed the 8-week study. The average root-mean-squared error (RMSE) in predicting the MADRS score (scale 0-60) was 4.72 using passive data alone, 4.27 using self-report measures alone, and 4.30 using both.

CONCLUSIONS

While passive measures did not improve MADRS score prediction in our cross-disorder study, they may capture behavioral phenotypes that cannot be measured objectively, granularly, or over long-term via self-report.

A Sensor-Based Perspective in Early-Stage Parkinson's Disease: Current State and the Need for Machine Learning Processes

Parkinson's disease (PD) is a progressive neurodegenerative disorder associated with dysfunction of dopaminergic neurons in the brain, lack of dopamine and the formation of abnormal Lewy body protein particles. PD is an idiopathic disease of the nervous system, characterized by motor and nonmotor manifestations without a discrete onset of symptoms until a substantial loss of neurons has already occurred, enabling early diagnosis very challenging. Sensor-based platforms have gained much attention in clinical practice screening various biological signals simultaneously and allowing researchers to quickly receive a huge number of biomarkers for diagnostic and prognostic purposes. The integration of machine learning into medical systems provides the potential for optimization of data collection, disease prediction through classification of symptoms and can strongly support data-driven clinical decisions. This work attempts to examine some of the facts and current situation of sensor-based approaches in PD diagnosis and discusses ensemble techniques using sensor-based data for developing machine learning models for personalized risk prediction. Additionally, a biosensing platform combined with clinical data processing and appropriate software is proposed in order to implement a complete diagnostic system for PD monitoring.

Predicting Axial Impairment in Parkinson's Disease through a Single Inertial Sensor

Background: Current telemedicine approaches lack standardised procedures for the remote assessment of axial impairment in Parkinson’s disease (PD). Unobtrusive wearable sensors may be a feasible tool to provide clinicians with practical medical indices reflecting axial dysfunction in PD. This study aims to predict the postural instability/gait difficulty (PIGD) score in PD patients by monitoring gait through a single inertial measurement unit (IMU) and machine-learning algorithms. Methods: Thirty-one PD patients underwent a 7-m timed-up-and-go test while monitored through an IMU placed on the thigh, both under (ON) and not under (OFF) dopaminergic therapy. After pre-processing procedures and feature selection, a support vector regression model was implemented to predict PIGD scores and to investigate the impact of L-Dopa and freezing of gait (FOG) on regression models. Results: Specific time- and frequency-domain features correlated with PIGD scores. After optimizing the dimensionality reduction methods and the model parameters, regression algorithms demonstrated different performance in the PIGD prediction in patients OFF and ON therapy (r = 0.79 and 0.75 and RMSE = 0.19 and 0.20, respectively). Similarly, regression models showed different performances in the PIGD prediction, in patients with FOG, ON and OFF therapy (r = 0.71 and RMSE = 0.27; r = 0.83 and RMSE = 0.22, respectively) and in those without FOG, ON and OFF therapy (r = 0.85 and RMSE = 0.19; r = 0.79 and RMSE = 0.21, respectively). Conclusions: Optimized support vector regression models have high feasibility in predicting PIGD scores in PD. L-Dopa and FOG affect regression model performances. Overall, a single inertial sensor may help to remotely assess axial motor impairment in PD patients.

Potential applications and performance of machine learning techniques and algorithms in clinical practice: A systematic review

PURPOSE

The advent of clinically adapted machine learning algorithms can solve numerous problems ranging from disease diagnosis and prognosis to therapy recommendations. This systematic review examines the performance of machine learning (ML) algorithms and evaluates the progress made to date towards their implementation in clinical practice.

METHODS

Systematic searching of databases (PubMed, MEDLINE, Scopus, Google Scholar, Cochrane Library and WHO Covid-19 database) to identify original articles published between January 2011 and October 2021. Studies reporting ML techniques in clinical practice involving humans and ML algorithms with a performance metric were considered.

RESULTS

Of 873 unique articles identified, 36 studies were eligible for inclusion. The XGBoost (extreme gradient boosting) algorithm showed the highest potential for clinical applications (n = 7 studies); this was followed jointly by random forest algorithm, logistic regression, and the support vector machine, respectively (n = 5 studies). Prediction of outcomes (n = 33), in particular Inflammatory diseases (n = 7) received the most attention followed by cancer and neuropsychiatric disorders (n = 5 for each) and Covid-19 (n = 4). Thirty-three out of the thirty-six included studies passed more than 50% of the selected quality assessment criteria in the TRIPOD checklist. In contrast, none of the studies could achieve an ideal overall bias rating of 'low' based on the PROBAST checklist. In contrast, only three studies showed evidence of the deployment of ML algorithm(s) in clinical practice.

CONCLUSIONS

ML is potentially a reliable tool for clinical decision support. Although advocated widely in clinical practice, work is still in progress to validate clinically adapted ML algorithms. Improving quality standards, transparency, and interpretability of ML models will further lower the barriers to acceptability.

Technology-Based Neurorehabilitation in Parkinson’s Disease—A Narrative Review

This narrative review provides a brief overview of the current literature on technology-based interventions for the neurorehabilitation of persons with Parkinson’s disease (PD). The role of brain–computer interfaces, exergaming/virtual-reality-based exercises, robot-assisted therapies and wearables is discussed. It is expected that technology-based neurorehabilitation will gain importance in the management of PD patients, although it is often not clear yet whether this approach is superior to conventional therapies. High-intensity technology-based neurorehabilitation may hold promise with respect to neuroprotective or neurorestorative actions in PD. Overall, more research is required in order to obtain more data on the feasibility, efficacy and safety of technology-based neurorehabilitation in persons with PD.

Detecting Parkinson Disease Using a Web-Based Speech Task: Observational Study

Background

Access to neurological care for Parkinson disease (PD) is a rare privilege for millions of people worldwide, especially in resource-limited countries. In 2013, there were just 1200 neurologists in India for a population of 1.3 billion people; in Africa, the average population per neurologist exceeds 3.3 million people. In contrast, 60,000 people receive a diagnosis of PD every year in the United States alone, and similar patterns of rising PD cases—fueled mostly by environmental pollution and an aging population—can be seen worldwide. The current projection of more than 12 million patients with PD worldwide by 2040 is only part of the picture given that more than 20% of patients with PD remain undiagnosed. Timely diagnosis and frequent assessment are key to ensure timely and appropriate medical intervention, thus improving the quality of life of patients with PD.

Objective

In this paper, we propose a web-based framework that can help anyone anywhere around the world record a short speech task and analyze the recorded data to screen for PD.

Methods

We collected data from 726 unique participants (PD: 262/726, 36.1% were women; non-PD: 464/726, 63.9% were women; average age 61 years) from all over the United States and beyond. A small portion of the data (approximately 54/726, 7.4%) was collected in a laboratory setting to compare the performance of the models trained with noisy home environment data against high-quality laboratory-environment data. The participants were instructed to utter a popular pangram containing all the letters in the English alphabet, “the quick brown fox jumps over the lazy dog.” We extracted both standard acoustic features (mel-frequency cepstral coefficients and jitter and shimmer variants) and deep learning–based embedding features from the speech data. Using these features, we trained several machine learning algorithms. We also applied model interpretation techniques such as Shapley additive explanations to ascertain the importance of each feature in determining the model’s output.

Results

We achieved an area under the curve of 0.753 for determining the presence of self-reported PD by modeling the standard acoustic features through the XGBoost—a gradient-boosted decision tree model. Further analysis revealed that the widely used mel-frequency cepstral coefficient features and a subset of previously validated dysphonia features designed for detecting PD from a verbal phonation task (pronouncing “ahh”) influence the model’s decision the most.

Conclusions

Our model performed equally well on data collected in a controlled laboratory environment and in the wild across different gender and age groups. Using this tool, we can collect data from almost anyone anywhere with an audio-enabled device and help the participants screen for PD remotely, contributing to equity and access in neurological care.

A systematic review of smartphone-based human activity recognition methods for health research

Smartphones are now nearly ubiquitous; their numerous built-in sensors enable continuous measurement of activities of daily living, making them especially well-suited for health research. Researchers have proposed various human activity recognition (HAR) systems aimed at translating measurements from smartphones into various types of physical activity. In this review, we summarized the existing approaches to smartphone-based HAR. For this purpose, we systematically searched Scopus, PubMed, and Web of Science for peer-reviewed articles published up to December 2020 on the use of smartphones for HAR. We extracted information on smartphone body location, sensors, and physical activity types studied and the data transformation techniques and classification schemes used for activity recognition. Consequently, we identified 108 articles and described the various approaches used for data acquisition, data preprocessing, feature extraction, and activity classification, identifying the most common practices, and their alternatives. We conclude that smartphones are well-suited for HAR research in the health sciences. For population-level impact, future studies should focus on improving the quality of collected data, address missing data, incorporate more diverse participants and activities, relax requirements about phone placement, provide more complete documentation on study participants, and share the source code of the implemented methods and algorithms.

A Comparative Study of Time Frequency Representation Techniques for Freeze of Gait Detection and Prediction

Freezing of Gait (FOG) is an impairment that affects the majority of patients in the advanced stages of Parkinson's Disease (PD). FOG can lead to sudden falls and injuries, negatively impacting the quality of life for the patients and their families. Rhythmic Auditory Stimulation (RAS) can be used to help patients recover from FOG and resume normal gait. RAS might be ineffective due to the latency between the start of a FOG event, its detection and initialization of RAS. We propose a system capable of both FOG prediction and detection using signals from tri-axial accelerometer sensors that will be useful in initializing RAS with minimal latency. We compared the performance of several time frequency analysis techniques, including moving windows extracted from the signals, handcrafted features, Recurrence Plots (RP), Short Time Fourier Transform (STFT), Discreet Wavelet Transform (DWT) and Pseudo Wigner Ville Distribution (PWVD) with Deep Learning (DL) based Long Short Term Memory (LSTM) and Convolutional Neural Networks (CNN). We also propose three Ensemble Network Architectures that combine all the time frequency representations and DL architectures. Experimental results show that our ensemble architectures significantly improve the performance compared with existing techniques. We also present the results of applying our method trained on a publicly available dataset to data collected from patients using wearable sensors in collaboration with A.T. Still University.

Discrimination of idiopathic Parkinson's disease and vascular parkinsonism based on gait time series and the levodopa effect

Idiopathic Parkinson's disease (IPD) and vascular parkinsonism (VaP) present highly overlapping phenotypes, making it challenging to distinguish between these two parkinsonian syndromes. Recent evidence suggests that gait assessment and response to levodopa medication may assist in the objective evaluation of clinical differences. In this paper, we propose a new approach for gait pattern differentiation that uses convolutional neural networks (CNNs) based on gait time series with and without the influence of levodopa medication. Wearable sensors positioned on both feet were used to acquire gait data from 14 VaP patients, 15 IPD patients, and 34 healthy subjects. An individual's gait features are affected by physical characteristics, including age, height, weight, sex, and walking speed or stride length. Therefore, to reduce bias due to intersubject variations, a multiple regression normalization approach was used to obtain gait data. Recursive feature elimination using the linear support vector machine, lasso, and random forest were applied to infer the optimal feature subset that led to the best results. CNNs were implemented by means of various hyperparameters and feature subsets. The best CNN classifiers achieved accuracies of 79.33%±6.46, 82.33%±10.62, and 86.00%±7.12 without (off state), with (on state), and with the simultaneous consideration of the effect of levodopa medication (off/on state), respectively. The response to levodopa medication improved classification performance. Based on gait time series and response to medication, the proposed approach differentiates between IPD and VaP gait patterns and reveals a high accuracy rate, which might prove useful when distinguishing other diseases related to movement disorders.

Artificial intelligence in neurodegenerative diseases: A review of available tools with a focus on machine learning techniques

Neurodegenerative diseases have shown an increasing incidence in the older population in recent years. A significant amount of research has been conducted to characterize these diseases. Computational methods, and particularly machine learning techniques, are now very useful tools in helping and improving the diagnosis as well as the disease monitoring process. In this paper, we provide an in-depth review on existing computational approaches used in the whole neurodegenerative spectrum, namely for Alzheimer's, Parkinson's, and Huntington's Diseases, Amyotrophic Lateral Sclerosis, and Multiple System Atrophy. We propose a taxonomy of the specific clinical features, and of the existing computational methods. We provide a detailed analysis of the various modalities and decision systems employed for each disease. We identify and present the sleep disorders which are present in various diseases and which represent an important asset for onset detection. We overview the existing data set resources and evaluation metrics. Finally, we identify current remaining open challenges and discuss future perspectives.

Validation of Inertial Sensing-Based Wearable Device for Tremor and Bradykinesia Quantification

Neurologists judge the severity of Parkinsonian motor symptoms according to clinical scales, and their judgments exist inconsistent because of differences in clinical experience. Correspondingly, inertial sensing-based wearable devices (ISWDs) produce objective and standardized quantifications. However, ISWDs indirectly quantify symptoms by parametric modeling of angular velocities and linear accelerations nd trained by the judgments of several neurologists through supervised learning algorithms. Hence, the ISWD outputs are biased along with the scores provided by neurologists. To investigate the effectiveness ISWDs for Parkinsonian symptoms quantification, technical verification and clinical validation of both tremor and bradykinesia quantification methods were carried out. A total of 45 Parkinson's disease patients and 30 healthy controls performed the tremor and finger-tapping tasks, which were tracked simultaneously by an ISWD and a 6-axis high-precision electromagnetic tracking system (EMTS). The Unified Parkinson's Disease Rating Scale (UPDRS) prescribed parameters obtained from the EMTS, which directly provides linear and rotational displacements, were compared with the scores provided by both the ISWD and seven neurologists. EMTS-based parameters were regarded as the ground truth and were employed to train several common machine learning (ML) algorithms, i.e., support vector machine (SVM), k-nearest neighbors (KNN), and random forest (RF) algorithms. Inconsistency among the scores provided by the neurologists was proven. Besides, the quantification performance (sensitivity, specificity, and accuracy) of the ISWD employed with ML algorithms were better than that of the neurologists. Furthermore, EMTS can be utilized to both modify the quantification algorithms of ISWDs and improve the assessment skills of young neurologists.

Cultural bias in motor function patterns: Potential relevance for predictive, preventive, and personalized medicine

Background

Quantification of motor performance has a promising role in personalized medicine by diagnosing and monitoring, e.g. neurodegenerative diseases or health problems related to aging. New motion assessment technologies can evolve into patient-centered eHealth applications on a global scale to support personalized healthcare as well as treatment of disease. However, uncertainty remains on the limits of generalizability of such data, which is relevant specifically for preventive or predictive applications, using normative datasets to screen for incipient disease manifestations or indicators of individual risks.

Objective

This study explored differences between healthy German and Japanese adults in the performance of a short set of six motor tests.

Methods

Six motor tasks related to gait and balance were recorded with a validated 3D camera system. Twenty-five healthy adults from Chiba, Japan, participated in this study and were matched for age, sex, and BMI to a sample of 25 healthy adults from Berlin, Germany. Recordings used the same technical setup and standard instructions and were supervised by the same experienced operator. Differences in motor performance were analyzed using multiple linear regressions models, adjusted for differences in body stature.

Results

From 23 presented parameters, five showed group-related differences after adjustment for height and weight (R ² between .19 and .46, p<.05). Japanese adults transitioned faster between sitting and standing and used a smaller range of hand motion. In stepping-in-place, cadence was similar in both groups, but Japanese adults showed higher knee movement amplitudes. Body height was identified as relevant confounder (standardized beta >.5) for performance of short comfortable and maximum speed walks. For results of posturography, regression models did not reveal effects of group or body stature.

Conclusions

Our results support the existence of a population-specific bias in motor function patterns in young healthy adults. This needs to be considered when motor function is assessed and used for clinical decisions, especially for personalized predictive and preventive medical purposes. The bias affected only the performance of specific items and parameters and is not fully explained by population-specific ethnic differences in body stature. It may be partially explained as cultural bias related to motor habits. Observed effects were small but are expected to be larger in a non-controlled cross-cultural application of motion assessment technologies with relevance for related algorithms that are being developed and used for data processing. In sum, the interpretation of individual data should be related to appropriate population-specific or even better personalized normative values to yield its full potential and avoid misinterpretation.

Supplementary Information

The online version contains supplementary material available at 10.1007/s13167-021-00236-3.

Automatic Resting Tremor Assessment in Parkinson's Disease Using Smartwatches and Multitask Convolutional Neural Networks

Resting tremor in Parkinson's disease (PD) is one of the most distinctive motor symptoms. Appropriate symptom monitoring can help to improve management and medical treatments and improve the patients' quality of life. Currently, tremor is evaluated by physical examinations during clinical appointments; however, this method could be subjective and does not represent the full spectrum of the symptom in the patients' daily lives. In recent years, sensor-based systems have been used to obtain objective information about the disease. However, most of these systems require the use of multiple devices, which makes it difficult to use them in an ambulatory setting. This paper presents a novel approach to evaluate the amplitude and constancy of resting tremor using triaxial accelerometers from consumer smartwatches and multitask classification models. These approaches are used to develop a system for an automated and accurate symptom assessment without interfering with the patients' daily lives. Results show a high agreement between the amplitude and constancy measurements obtained from the smartwatch in comparison with those obtained in a clinical assessment. This indicates that consumer smartwatches in combination with multitask convolutional neural networks are suitable for providing accurate and relevant information about tremor in patients in the early stages of the disease, which can contribute to the improvement of PD clinical evaluation, early detection of the disease, and continuous monitoring.

Modeling and Prediction of Wearable Energy Harvesting Sliding Shoes for Metabolic Cost and Energy Rate Outside of the Lab

The recent explosion of wearable electronics has led to widespread interest in harvesting human movement energy, particularly during walking, for clinical and health applications. However, the amount of energy available to harvest and the required metabolic rate for wearable energy harvesting varies across subjects. In this paper, we utilize custom energy harvesting sliding shoes to develop and evaluate multivariate linear regression models to predict metabolic rate and energy harvesting rate during overground walking outside of the lab. Subjects performed 200 m self-selected normal and fast walking trials on flat ground with custom sliding shoes. Metabolic rate was measured with a portable breathing analysis system and energy harvesting rate was measured directly from the generator on the custom sliding shoes. Model performance was determined by comparing the difference between actual and predicted metabolic and energy harvesting rates. Overall, predictive modeling closely matched the actual values, and there was no statistical difference between actual and predicted average metabolic rate or between actual and predicted average energy harvesting rate. Energy harvesting sliding shoes could potentially be used for a variety of wearable devices to reduce onboard energy storage, and these findings could serve to inform expected energy harvesting rates and associated required metabolic cost for a diverse array of medical and health applications.

Classification of Fatigue Phases in Healthy and Diabetic Adults Using Wearable Sensor

Fatigue is defined as "a loss of force-generating capacity" in a muscle that can intensify tremor. Tremor quantification can facilitate early detection of fatigue onset so that preventative or corrective controls can be taken to minimize work-related injuries and improve the performance of tasks that require high-levels of accuracy. We focused on developing a system that recognizes and classifies voluntary effort and detects phases of fatigue. The experiment was designed to extract and evaluate hand-tremor data during the performance of both rest and effort tasks. The data were collected from the wrist and finger of the participant's dominant hand. To investigate tremor, time, frequency domain features were extracted from the accelerometer signal for segments of 45 and 90 samples/window. Analysis using advanced signal processing and machine-learning techniques such as decision tree, k-nearest neighbor, support vector machine, and ensemble classifiers were applied to discover models to classify rest and effort tasks and the phases of fatigue. Evaluation of the classifier's performance was assessed based on various metrics using 5-fold cross-validation. The recognition of rest and effort tasks using an ensemble classifier based on the random subspace and window length of 45 samples was deemed to be the most accurate (96.1%). The highest accuracy (~98%) that distinguished between early and late fatigue phases was achieved using the same classifier and window length.

A Multi-Sensor Wearable System for the Quantitative Assessment of Parkinson's Disease

The quantitative characterization of movement disorders and their related neurophysiological signals is important for the management of Parkinson’s disease (PD). The aim of this study is to develop a novel wearable system enabling the simultaneous measurement of both motion and other neurophysiological signals in PD patients. We designed a wearable system that consists of five motion sensors and three electrophysiology sensors to measure the motion signals of the body, electroencephalogram, electrocardiogram, and electromyography, respectively. The data captured by the sensors are transferred wirelessly in real time, and the outcomes are analyzed and uploaded to the cloud-based server automatically. We completed pilot studies to (1) test its validity by comparing outcomes to the commercialized systems, and (2) evaluate the deep brain stimulation (DBS) treatment effects in seven PD patients. Our results showed: (1) the motion and neurophysiological signals measured by this wearable system were strongly correlated with those measured by the commercialized systems (r > 0.94, p < 0.001); and (2) by completing the clinical supination and pronation frequency test, the frequency of motion as measured by this system increased when DBS was turned on. The results demonstrated that this multi-sensor wearable system can be utilized to quantitatively characterize and monitor motion and neurophysiological PD.

Parkinson's Disease Tremor Detection in the Wild Using Wearable Accelerometers

Continuous in-home monitoring of Parkinson's Disease (PD) symptoms might allow improvements in assessment of disease progression and treatment effects. As a first step towards this goal, we evaluate the feasibility of a wrist-worn wearable accelerometer system to detect PD tremor in the wild (uncontrolled scenarios). We evaluate the performance of several feature sets and classification algorithms for robust PD tremor detection in laboratory and wild settings. We report results for both laboratory data with accurate labels and wild data with weak labels. The best performance was obtained using a combination of a pre-processing module to extract information from the tremor spectrum (based on non-negative factorization) and a deep neural network for learning relevant features and detecting tremor segments. We show how the proposed method is able to predict patient self-report measures, and we propose a new metric for monitoring PD tremor (i.e., percentage of tremor over long periods of time), which may be easier to estimate the start and end time points of each tremor event while still providing clinically useful information.

Comparing laboratory and in-the-wild data for continuous Parkinson's Disease tremor detection

Passive, continuous monitoring of Parkinson's Disease (PD) symptoms in the wild (i.e., in home environments) could improve disease management, thereby improving a patient's quality of life. We envision a system that uses machine learning to automatically detect PD symptoms from accelerometer data collected in the wild. Building such systems, however, is challenging because it is difficult to obtain labels of symptom occurrences in the wild. Many researchers therefore train machine learning algorithms on laboratory data with the assumption that findings will translate to the wild. This paper assesses how well laboratory data represents wild data by comparing PD symptom (tremor) detection performance of three models on both lab and wild data. Findings indicate that, for this application, laboratory data is not a good representation of wild data. Results also show that training on wild data, even though labels are less precise, leads to better performance on wild data than training on accurate labels from laboratory data.

Fit-for-Purpose Biometric Monitoring Technologies: Leveraging the Laboratory Biomarker Experience

Biometric monitoring technologies (BioMeTs) are becoming increasingly common to aid data collection in clinical trials and practice. The state of BioMeTs, and associated digitally measured biomarkers, is highly reminiscent of the field of laboratory biomarkers 2 decades ago. In this review, we have summarized and leveraged historical perspectives, and lessons learned from laboratory biomarkers as they apply to BioMeTs. Both categories share common features, including goals and roles in biomedical research, definitions, and many elements of the biomarker qualification framework. They can also be classified based on the underlying technology, each with distinct features and performance characteristics, which require bench and human experimentation testing phases. In contrast to laboratory biomarkers, digitally measured biomarkers require prospective data collection for purposes of analytical validation in human subjects, lack well‐established and widely accepted performance characteristics, require human factor testing, and, for many applications, access to raw (sample‐level) data. Novel methods to handle large volumes of data, as well as security and data rights requirements add to the complexity of this emerging field. Our review highlights the need for a common framework with appropriate vocabulary and standardized approaches to evaluate digitally measured biomarkers, including defining performance characteristics and acceptance criteria. Additionally, the need for human factor testing drives early patient engagement during technology development. Finally, use of BioMeTs requires a relatively high degree of technology literacy among both study participants and healthcare professionals. Transparency of data generation and the need for novel analytical and statistical tools creates opportunities for precompetitive collaborations.

New Sensor and Wearable Technologies to Aid in the Diagnosis and Treatment Monitoring of Parkinson's Disease

Parkinson's disease (PD) is a degenerative disorder of the brain characterized by the impairment of the nigrostriatal system. This impairment leads to specific motor manifestations (i.e., bradykinesia, tremor, and rigidity) that are assessed through clinical examination, scales, and patient-reported outcomes. New sensor-based and wearable technologies are progressively revolutionizing PD care by objectively measuring these manifestations and improving PD diagnosis and treatment monitoring. However, their use is still limited in clinical practice, perhaps because of the absence of external validation and standards for their continuous use at home. In the near future, these systems will progressively complement traditional tools and revolutionize the way we diagnose and monitor patients with PD.

Topological Descriptors for Parkinson's Disease Classification and Regression Analysis

At present, the vast majority of human subjects with neurological disease are still diagnosed through in-person assessments and qualitative analysis of patient data. In this paper, we propose to use Topological Data Analysis (TDA) together with machine learning tools to automate the process of Parkinson's disease classification and severity assessment. An automated, stable, and accurate method to evaluate Parkinson's would be significant in streamlining diagnoses of patients and providing families more time for corrective measures. We propose a methodology which incorporates TDA into analyzing Parkinson's disease postural shifts data through the representation of persistence images. Studying the topology of a system has proven to be invariant to small changes in data and has been shown to perform well in discrimination tasks. The contributions of the paper are twofold. We propose a method to 1) classify healthy patients from those afflicted by disease and 2) diagnose the severity of disease. We explore the use of the proposed method in an application involving a Parkinson's disease dataset comprised of healthy-elderly, healthy-young and Parkinson's disease patients. Our code is available at https://github.com/itsmeafra/Sublevel-Set-TDA.

Empirical assessment of bias in machine learning diagnostic test accuracy studies

OBJECTIVE

Machine learning (ML) diagnostic tools have significant potential to improve health care. However, methodological pitfalls may affect diagnostic test accuracy studies used to appraise such tools. We aimed to evaluate the prevalence and reporting of design characteristics within the literature. Further, we sought to empirically assess whether design features may be associated with different estimates of diagnostic accuracy.

MATERIALS AND METHODS

We systematically retrieved 2 × 2 tables (n = 281) describing the performance of ML diagnostic tools, derived from 114 publications in 38 meta-analyses, from PubMed. Data extracted included test performance, sample sizes, and design features. A mixed-effects metaregression was run to quantify the association between design features and diagnostic accuracy.

RESULTS

Participant ethnicity and blinding in test interpretation was unreported in 90% and 60% of studies, respectively. Reporting was occasionally lacking for rudimentary characteristics such as study design (28% unreported). Internal validation without appropriate safeguards was used in 44% of studies. Several design features were associated with larger estimates of accuracy, including having unreported (relative diagnostic odds ratio [RDOR], 2.11; 95% confidence interval [CI], 1.43-3.1) or case-control study designs (RDOR, 1.27; 95% CI, 0.97-1.66), and recruiting participants for the index test (RDOR, 1.67; 95% CI, 1.08-2.59).

DISCUSSION

Significant underreporting of experimental details was present. Study design features may affect estimates of diagnostic performance in the ML diagnostic test accuracy literature.

CONCLUSIONS

The present study identifies pitfalls that threaten the validity, generalizability, and clinical value of ML diagnostic tools and provides recommendations for improvement.

Fifteen Years of Wireless Sensors for Balance Assessment in Neurological Disorders

Balance impairment is a major mechanism behind falling along with environmental hazards. Under physiological conditions, ageing leads to a progressive decline in balance control per se. Moreover, various neurological disorders further increase the risk of falls by deteriorating specific nervous system functions contributing to balance. Over the last 15 years, significant advancements in technology have provided wearable solutions for balance evaluation and the management of postural instability in patients with neurological disorders. This narrative review aims to address the topic of balance and wireless sensors in several neurological disorders, including Alzheimer’s disease, Parkinson’s disease, multiple sclerosis, stroke, and other neurodegenerative and acute clinical syndromes. The review discusses the physiological and pathophysiological bases of balance in neurological disorders as well as the traditional and innovative instruments currently available for balance assessment. The technical and clinical perspectives of wearable technologies, as well as current challenges in the field of teleneurology, are also examined.

Wearable Solutions for Patients with Parkinson's Disease and Neurocognitive Disorder: A Systematic Review

Prevalence of neurocognitive diseases in adult patients demands the use of wearable devices to transform the future of mental health. Recent development in wearable technology proclaimed its use in diagnosis, rehabilitation, assessment, and monitoring. This systematic review presents the state of the art of wearables used by Parkinson’s disease (PD) patients or the patients who are going through a neurocognitive disorder. This article is based on PRISMA guidelines, and the literature is searched between January 2009 to January 2020 analyzing four databases: PubMed, IEEE Xplorer, Elsevier, and ISI Web of Science. For further validity of articles, a new PEDro-inspired technique is implemented. In PEDro, five statistical indicators were set to classify relevant articles and later the citations were also considered to make strong assessment of relevant articles. This led to 46 articles that met inclusion criteria. Based on them, this systematic review examines different types of wearable devices, essential in improving early diagnose and monitoring, emphasizing their role in improving the quality of life, differentiating the various fitness and gait wearable-based exercises and their impact on the regression of disease and on the motor diagnosis tests and finally addressing the available wearable insoles and their role in rehabilitation. The research findings proved that sensor based wearable devices, and specially instrumented insoles, help not only in monitoring and diagnosis but also in tracking numerous exercises and their positive impact towards the improvement of quality of life among different Parkinson and neurocognitive patients.

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.

Role of data measurement characteristics in the accurate detection of Parkinson's disease symptoms using wearable sensors

Background

Parkinson’s disease (PD) is a progressive neurological disease, with characteristic motor symptoms such as tremor and bradykinesia. There is a growing interest to continuously monitor these and other symptoms through body-worn sensor technology. However, limited battery life and memory capacity hinder the potential for continuous, long-term monitoring with these devices. There is little information available on the relative value of adding sensors, increasing sampling rate, or computing complex signal features, all of which may improve accuracy of symptom detection at the expense of computational resources. Here we build on a previous study to investigate the relationship between data measurement characteristics and accuracy when using wearable sensor data to classify tremor and bradykinesia in patients with PD.

Methods

Thirteen individuals with PD wore a flexible, skin-mounted sensor (collecting tri-axial accelerometer and gyroscope data) and a commercial smart watch (collecting tri-axial accelerometer data) on their predominantly affected hand. The participants performed a series of standardized motor tasks, during which a clinician scored the severity of tremor and bradykinesia in that limb. Machine learning models were trained on scored data to classify tremor and bradykinesia. Model performance was compared when using different types of sensors (accelerometer and/or gyroscope), different data sampling rates (up to 62.5 Hz), and different categories of pre-engineered features (up to 148 features). Performance was also compared between the flexible sensor and smart watch for each analysis.

Results

First, there was no effect of device type for classifying tremor symptoms (p > 0.34), but bradykinesia models incorporating gyroscope data performed slightly better (up to 0.05 AUROC) than other models (p = 0.01). Second, model performance decreased with sampling frequency (p < 0.001) for tremor, but not bradykinesia (p > 0.47). Finally, model performance for both symptoms was maintained after substantially reducing the feature set.

Conclusions

Our findings demonstrate the ability to simplify measurement characteristics from body-worn sensors while maintaining performance in PD symptom detection. Understanding the trade-off between model performance and data resolution is crucial to design efficient, accurate wearable sensing systems. This approach may improve the feasibility of long-term, continuous, and real-time monitoring of PD symptoms by reducing computational burden on wearable devices.

Improving mobile health apps usage: a quantitative study on mPower data of Parkinson's disease

Purpose

The emergence of mobile health (mHealth) products has created a capability of monitoring and managing the health of patients with chronic diseases. These mHealth technologies would not be beneficial unless they are adopted and used by their target users. This study identifies key factors affecting the usage of mHealth apps based on user usage data collected from an mHealth app.

Design/methodology/approach

Using a dataset collected from an mHealth app named mPower, developed for patients with Parkinson's disease (PD), this paper investigated the effects of disease diagnosis, disease progression and mHealth app difficulty level on app usage, while controlling for user information. App usage is measured by five different activity counts of the app.

Findings

The results across five measures of mHealth app usage vary slightly. On average, previous professional diagnosis and high user performance scores encourage user participation and engagement, while disease progression hinders app usage.

Research limitations/implications

The findings potentially provide insights into better design and promotion of mHealth products and improve the capability of health management of patients with chronic diseases.

Originality/value

Studies on the mHealth app usage are critical but sparse because large-scale and reliable mHealth app usage data are limited. Unlike earlier works based solely on survey data, this research used a large user usage data collected from an mHealth app to study key factors affecting app usage. The methods presented in this study can serve as a pioneering work for the design and promotion of mHealth technologies.

High-Resolution Motor State Detection in Parkinson's Disease Using Convolutional Neural Networks

Patients with advanced Parkinson's disease regularly experience unstable motor states. Objective and reliable monitoring of these fluctuations is an unmet need. We used deep learning to classify motion data from a single wrist-worn IMU sensor recording in unscripted environments. For validation purposes, patients were accompanied by a movement disorder expert, and their motor state was passively evaluated every minute. We acquired a dataset of 8,661 minutes of IMU data from 30 patients, with annotations about the motor state (OFF,ON, DYSKINETIC) based on MDS-UPDRS global bradykinesia item and the AIMS upper limb dyskinesia item. Using a 1-minute window size as an input for a convolutional neural network trained on data from a subset of patients, we achieved a three-class balanced accuracy of 0.654 on data from previously unseen subjects. This corresponds to detecting the OFF, ON, or DYSKINETIC motor state at a sensitivity/specificity of 0.64/0.89, 0.67/0.67 and 0.64/0.89, respectively. On average, the model outputs were highly correlated with the annotation on a per subject scale (r = 0.83/0.84; p < 0.0001), and sustained so for the highly resolved time windows of 1 minute (r = 0.64/0.70; p < 0.0001). Thus, we demonstrate the feasibility of long-term motor-state detection in a free-living setting with deep learning using motion data from a single IMU.

Deep Learning Approaches for Detecting Freezing of Gait in Parkinson's Disease Patients through On-Body Acceleration Sensors

Freezing of gait (FOG) is one of the most incapacitating motor symptoms in Parkinson's disease (PD). The occurrence of FOG reduces the patients' quality of live and leads to falls. FOG assessment has usually been made through questionnaires, however, this method can be subjective and could not provide an accurate representation of the severity of this symptom. The use of sensor-based systems can provide accurate and objective information to track the symptoms' evolution to optimize PD management and treatments. Several authors have proposed specific methods based on wearables and the analysis of inertial signals to detect FOG in laboratory conditions, however, its performance is usually lower when being used at patients' homes. This study presents a new approach based on a recurrent neural network (RNN) and a single waist-worn triaxial accelerometer to enhance the FOG detection performance to be used in real home-environments. Also, several machine and deep learning approaches for FOG detection are evaluated using a leave-one-subject-out (LOSO) cross-validation. Results show that modeling spectral information of adjacent windows through an RNN can bring a significant improvement in the performance of FOG detection without increasing the length of the analysis window (required to using it as a cue-system).