Deep neural networks for wearable sensor-based activity recognition in Parkinson's disease: investigating generalizability and model complexity.

BACKGROUND: The research gap addressed in this study is the applicability of deep neural network (NN) models on wearable sensor data to recognize different activities performed by patients with Parkinson's Disease (PwPD) and the generalizability of these models to PwPD using labeled healthy data. METHODS: The experiments were carried out utilizing three datasets containing wearable motion sensor readings on common activities of daily living. The collected readings were from two accelerometer sensors. PAMAP2 and MHEALTH are publicly available datasets collected from 10 and 9 healthy, young subjects, respectively. A private dataset of a similar nature collected from 14 PwPD patients was utilized as well. Deep NN models were implemented with varying levels of complexity to investigate the impact of data augmentation, manual axis reorientation, model complexity, and domain adaptation on activity recognition performance. RESULTS: A moderately complex model trained on the augmented PAMAP2 dataset and adapted to the Parkinson domain using domain adaptation achieved the best activity recognition performance with an accuracy of 73.02%, which was significantly higher than the accuracy of 63% reported in previous studies. The model's F1 score of 49.79% significantly improved compared to the best cross-testing of 33.66% F1 score with only data augmentation and 2.88% F1 score without data augmentation or domain adaptation. CONCLUSION: These findings suggest that deep NN models originating on healthy data have the potential to recognize activities performed by PwPD accurately and that data augmentation and domain adaptation can improve the generalizability of models in the healthy-to-PwPD transfer scenario. The simple/moderately complex architectures tested in this study could generalize better to the PwPD domain when trained on a healthy dataset compared to the most complex architectures used. The findings of this study could contribute to the development of accurate wearable-based activity monitoring solutions for PwPD, improving clinical decision-making and patient outcomes based on patient activity levels.

Use of Sensors for Fall Prediction in Older Persons: A Scoping Review.

The application of technological advances and clear articulation of how they improve patient outcomes are not always well described in the literature. Our research team investigated the numerous ways to measure conditions and behaviors that precede patient events and could signal an important change in health through a scoping review. We searched for evidence of technology use in fall prediction in the population of older adults in any setting. The research question was described in the population-concept-context format: "What types of sensors are being used in the prediction of falls in older persons?" The purpose was to examine the numerous ways to obtain continuous measurement of conditions and behaviors that precede falls. This area of interest may be termed emerging knowledge . Implications for research include increased attention to human-centered design, need for robust research trials that clearly articulate study design and outcomes, larger sample sizes and randomization of subjects, consistent oversight of institutional review board processes, and elucidation of the human costs and benefits to health and science.

Biological Signal Processing and Analysis for Healthcare Monitoring.

Nowadays, portable and wireless wearable sensors have been commonly incorporated into the signal acquisition modules of healthcare monitoring systems [...].

Ensemble deep model for continuous estimation of Unified Parkinson's Disease Rating Scale III.

BACKGROUND: Unified Parkinson Disease Rating Scale-part III (UPDRS III) is part of the standard clinical examination performed to track the severity of Parkinson's disease (PD) motor complications. Wearable technologies could be used to reduce the need for on-site clinical examinations of people with Parkinson's disease (PwP) and provide a reliable and continuous estimation of the severity of PD at home. The reported estimation can be used to successfully adjust the dose and interval of PD medications. METHODS: We developed a novel algorithm for unobtrusive and continuous UPDRS-III estimation at home using two wearable inertial sensors mounted on the wrist and ankle. We used the ensemble of three deep-learning models to detect UPDRS-III-related patterns from a combination of hand-crafted features, raw temporal signals, and their time-frequency representation. Specifically, we used a dual-channel, Long Short-Term Memory (LSTM) for hand-crafted features, 1D Convolutional Neural Network (CNN)-LSTM for raw signals, and 2D CNN-LSTM for time-frequency data. We utilized transfer learning from activity recognition data and proposed a two-stage training for the CNN-LSTM networks to cope with the limited amount of data. RESULTS: The algorithm was evaluated on gyroscope data from 24 PwP as they performed different daily living activities. The estimated UPDRS-III scores had a correlation of [Formula: see text] and a mean absolute error of 5.95 with the clinical examination scores without requiring the patients to perform any specific tasks. CONCLUSION: Our analysis demonstrates the potential of our algorithm for estimating PD severity scores unobtrusively at home. Such an algorithm could provide the required motor-complication measurements without unnecessary clinical visits and help the treating physician provide effective management of the disease.

Atrial fibrillation source area probability mapping using electrogram patterns of multipole catheters.

BACKGROUND: Catheter ablation therapy involving isolation of pulmonary veins (PVs) from the left atrium is performed to terminate atrial fibrillation (AF). Unfortunately, standalone PV isolation procedure has shown to be a suboptimal success with AF continuation or recurrence. One reason, especially in patients with persistent or high-burden paroxysmal AF, is known to be due to the formation of repeating-pattern AF sources with a meandering core inside the atria. However, there is a need for accurate mapping and localization of these sources during catheter ablation. METHODS: A novel AF source area probability (ASAP) mapping algorithm was developed and evaluated in 2D and 3D atrial simulated tissues with various arrhythmia scenarios and a retrospective study with three cases of clinical human AF. The ASAP mapping analyzes the electrograms collected from a multipole diagnostic catheter that is commonly used during catheter ablation procedure to intelligently sample the atria and delineate the trajectory path of a meandering repeating-pattern AF source. ASAP starts by placing the diagnostic catheter at an arbitrary location in the atria. It analyzes the recorded bipolar electrograms to build an ASAP map over the atrium anatomy and suggests an optimal location for the subsequent catheter location. ASAP then determines from the constructed ASAP map if an AF source has been delineated. If so, the catheter navigation is stopped and the algorithm provides the area of the AF source. Otherwise, the catheter is navigated to the suggested location, and the process is continued until an AF-source area is delineated. RESULTS: ASAP delineated the AF source in over 95% of the simulated human AF cases within less than eight catheter placements regardless of the initial catheter placement. The success of ASAP in the clinical AF was confirmed by the ablation outcomes and the electrogram patterns at the delineated area. CONCLUSION: Our analysis indicates the potential of the ASAP mapping to provide accurate information about the area of the meandering repeating-pattern AF sources as AF ablation targets for effective AF termination. Our algorithm could improve the success of AF catheter ablation therapy by locating and subsequently targeting patient-specific and repeating-pattern AF sources inside the atria.

Iterative navigation of multipole diagnostic catheters to locate repeating-pattern atrial fibrillation drivers.

INTRODUCTION: Targeting repeating-pattern atrial fibrillation (AF) sources (reentry or focal drivers) can help in patient-specific ablation therapy for AF; however, the development of reliable and accurate tools for locating such sources remains a major challenge. We describe iterative catheter navigation (ICAN) algorithm to locate AF drivers using a conventional circular Lasso catheter. METHODS AND RESULTS: At each step, the algorithm analyzes 10 bipolar electrograms recoded at a given catheter location and the history of previous catheter movements to determine if the source is inside the catheter loop. If not, it calculates new coordinates and selects a new position for the catheter. The process continues until a source is located. The algorithm was evaluated in a computer model of atrial tissue with various degrees of fibrosis under a broad range of arrhythmia scenarios. The latter included slow and fast reentry, macroreentry, figure-of-eight reentry, and fibrillatory conduction. Depending on the initial distance of the catheter from the source and scenario, it took about 3 to 16 steps to localize an AF source. In 94% of cases, the identified location was within 4 mm from the source, independently of the initial position of the catheter. The algorithm worked equally well in the presence of patchy fibrosis, low-voltage areas, fragmented electrograms, and dominant-frequency gradients. CONCLUSIONS: AF repeating-pattern sources can be localized using circular catheters without the need to map the entire tissue. The proposed algorithm has the potential to become a useful tool for patient-specific ablation of AF sources located outside the pulmonary veins.

Wearable Sensors for Estimation of Parkinsonian Tremor Severity during Free Body Movements.

Tremor is one of the main symptoms of Parkinson's Disease (PD) that reduces the quality of life. Tremor is measured as part of the Unified Parkinson Disease Rating Scale (UPDRS) part III. However, the assessment is based on onsite physical examinations and does not fully represent the patients' tremor experience in their day-to-day life. Our objective in this paper was to develop algorithms that, combined with wearable sensors, can estimate total Parkinsonian tremor as the patients performed a variety of free body movements. We developed two methods: an ensemble model based on gradient tree boosting and a deep learning model based on long short-term memory (LSTM) networks. The developed methods were assessed on gyroscope sensor data from 24 PD subjects. Our analysis demonstrated that the method based on gradient tree boosting provided a high correlation (r = 0.96 using held-out testing and r = 0.93 using subject-based, leave-one-out cross-validation) between the estimated and clinically assessed tremor subscores in comparison to the LSTM-based method with a moderate correlation (r = 0.84 using held-out testing and r = 0.77 using subject-based, leave-one-out cross-validation). These results indicate that our approach holds great promise in providing a full spectrum of the patients' tremor from continuous monitoring of the subjects' movement in their natural environment.

Hybrid Feature Extraction for Detection of Degree of Motor Fluctuation Severity in Parkinson's Disease Patients.

The success of medication adjustment in Parkinson's disease (PD) patients with motor fluctuation relies on the knowledge about their fluctuation severity. However, because of the temporal and spatial variability in motor fluctuations, a single clinical examination often fails to capture the spectrum of motor impairment experienced in routine daily life. In this study, we developed an algorithm to estimate the degree of motor fluctuation severity from two wearable sensors' data during subjects' free body movements. Specifically, we developed a new hybrid feature extraction method to represent the longitudinal changes of motor function from the sensor data. Next, we developed a classification model based on random forest to learn the changes in the patterns of the sensor data as the severity of the motor function changes. We evaluated our algorithm using data from 24 subjects with idiopathic PD as they performed a variety of daily routine activities. A leave-one-subject-out assessment of the algorithm resulted in 83.33% accuracy, indicating that our approach holds a great promise to passively detect degree of motor fluctuation severity from continuous monitoring of an individual's free body movements. Such a sensor-based assessment system and algorithm combination could provide the objective and comprehensive information about the fluctuation severity that can be used by the treating physician to effectively adjust therapy for PD patients with troublesome motor fluctuation.

Multi-Shared-Task Self-Supervised CNN-LSTM for Monitoring Free-Body Movement UPDRS-III Using Wearable Sensors.

The Unified Parkinson's Disease Rating Scale (UPDRS) is used to recognize patients with Parkinson's disease (PD) and rate its severity. The rating is crucial for disease progression monitoring and treatment adjustment. This study aims to advance the capabilities of PD management by developing an innovative framework that integrates deep learning with wearable sensor technology to enhance the precision of UPDRS assessments. We introduce a series of deep learning models to estimate UPDRS Part III scores, utilizing motion data from wearable sensors. Our approach leverages a novel Multi-shared-task Self-supervised Convolutional Neural Network-Long Short-Term Memory (CNN-LSTM) framework that processes raw gyroscope signals and their spectrogram representations. This technique aims to refine the estimation accuracy of PD severity during naturalistic human activities. Utilizing 526 min of data from 24 PD patients engaged in everyday activities, our methodology demonstrates a strong correlation of 0.89 between estimated and clinically assessed UPDRS-III scores. This model outperforms the benchmark set by single and multichannel CNN, LSTM, and CNN-LSTM models and establishes a new standard in UPDRS-III score estimation for free-body movements compared to recent state-of-the-art methods. These results signify a substantial step forward in bioengineering applications for PD monitoring, providing a robust framework for reliable and continuous assessment of PD symptoms in daily living settings.

Reinforcement Learning-Based Adaptive Classification for Medication State Monitoring in Parkinson's Disease.

Parkinson's Disease (PD) patients frequently transition between the 'ON' state, where medication is effective, and the 'OFF' state, affecting their quality of life. Monitoring these transitions is vital for personalized therapy. We introduced a framework based on Reinforcement Learning (RL) to detect transitions between medication states by learning from continuous movement data. Unlike traditional approaches that typically identify each state based on static data patterns, our approach focuses on understanding the dynamic patterns of change throughout the transitions, providing a more generalizable medication state monitoring method. We integrated a deep Long Short-Term Memory (LSTM) neural network and three one-class unsupervised classifiers to implement an RL-based adaptive classifier. We tested on two PD datasets: Dataset PD1 with 12 subjects (14-minute average recording) and Dataset PD2 with seven subjects (120-minute average recording). Data from wrist and ankle wearables captured transitions during 2 to 4-hour daily activities. The algorithm demonstrated its effectiveness in detecting medication states, achieving an average weighted F1-score of 82.94% when trained and tested on Dataset PD1. It performed well when trained on Dataset PD1 and tested on Dataset PD2, with a weighted F1-score of 76.67%. It surpassed other models, was resilient to severe PD symptoms, and performed well with imbalanced data. Notably, prior work has not addressed the generalizability from one dataset to another, essential for real-world applications with varied sensors. Our innovative framework revolutionizes PD monitoring, setting the stage for advanced therapeutic methods and greatly enhancing the life quality of PD patients.

Detection of mild cognitive impairment using various types of gait tests and machine learning.

Introduction: Alzheimer's disease and related disorders (ADRD) progressively impair cognitive function, prompting the need for early detection to mitigate its impact. Mild Cognitive Impairment (MCI) may signal an early cognitive decline due to ADRD. Thus, developing an accessible, non-invasive method for detecting MCI is vital for initiating early interventions to prevent severe cognitive deterioration. Methods: This study explores the utility of analyzing gait patterns, a fundamental aspect of human motor behavior, on straight and oval paths for diagnosing MCI. Using a Kinect v.2 camera, we recorded the movements of 25 body joints from 25 individuals with MCI and 30 healthy older adults (HC). Signal processing, descriptive statistical analysis, and machine learning techniques were employed to analyze the skeletal gait data in both walking conditions. Results and discussion: The study demonstrated that both straight and oval walking patterns provide valuable insights for MCI detection, with a notable increase in identifiable gait features in the more complex oval walking test. The Random Forest model excelled among various algorithms, achieving an 85.50% accuracy and an 83.9% F-score in detecting MCI during oval walking tests. This research introduces a cost-effective, Kinect-based method that integrates gait analysis-a key behavioral pattern-with machine learning, offering a practical tool for MCI screening in both clinical and home environments.

Curve Walking Reveals More Gait Impairments in Older Adults with Mild Cognitive Impairment than Straight Walking: A Kinect Camera-Based Study.

Background: Mild cognitive impairment (MCI) can be an early sign of Alzheimer's disease and other types of dementia detectable through gait analysis. Curve walking, which demands greater cognitive and motor skills, may be more sensitive in MCI detection than straight walking. However, few studies have compared gait performance in older adults with and without MCI in these conditions. Objective: To compare the capability of curve and straight walking tests for the detection of MCI among older adults. Methods: We employed a Kinect v.2 camera to record the gait of 55 older adults (30 healthy controls, 25 with MCI) during single-task straight and curve walking tests. We examined 50 gait markers and conducted statistical analyses to compare groups and conditions. The trail was approved with protocol No. IR.SEMUMS.REC.1398.237 by the ethics committee of Semnan University of Medical Sciences in Iran. Results: Older adults with MCI exhibited more compromised gait performance, particularly during curve walking. Curve walking outperformed straight walking in MCI detection, with several gait markers showing significant differences between healthy controls and MCI patients. These markers encompass average velocity, cadence, temporal markers (e.g., gait cycle subphase durations), spatial markers (e.g., foot position changes during gait subphases), and spatiotemporal markers (e.g., step and stride velocities). Conclusions: Our study suggests curve walking as a more informative and challenging test for MCI detection among older adults, facilitating early diagnosis using non-invasive, cost-effective tools like the Kinect v.2 camera, complementing cognitive assessments in early diagnosis, and tracking MCI progression to dementia.

Objective estimation of m-CTSIB balance test scores using wearable sensors and machine learning.

Accurate balance assessment is important in healthcare for identifying and managing conditions affecting stability and coordination. It plays a key role in preventing falls, understanding movement disorders, and designing appropriate therapeutic interventions across various age groups and medical conditions. However, traditional balance assessment methods often suffer from subjectivity, lack of comprehensive balance assessments and remote assessment capabilities, and reliance on specialized equipment and expert analysis. In response to these challenges, our study introduces an innovative approach for estimating scores on the Modified Clinical Test of Sensory Interaction on Balance (m-CTSIB). Utilizing wearable sensors and advanced machine learning algorithms, we offer an objective, accessible, and efficient method for balance assessment. We collected comprehensive movement data from 34 participants under four different sensory conditions using an array of inertial measurement unit (IMU) sensors coupled with a specialized system to evaluate ground truth m-CTSIB balance scores for our analysis. This data was then preprocessed, and an extensive array of features was extracted for analysis. To estimate the m-CTSIB scores, we applied Multiple Linear Regression (MLR), Support Vector Regression (SVR), and XGBOOST algorithms. Our subject-wise Leave-One-Out and 5-Fold cross-validation analysis demonstrated high accuracy and a strong correlation with ground truth balance scores, validating the effectiveness and reliability of our approach. Key insights were gained regarding the significance of specific movements, feature selection, and sensor placement in balance estimation. Notably, the XGBOOST model, utilizing the lumbar sensor data, achieved outstanding results in both methods, with Leave-One-Out cross-validation showing a correlation of 0.96 and a Mean Absolute Error (MAE) of 0.23 and 5-fold cross-validation showing comparable results with a correlation of 0.92 and an MAE of 0.23, confirming the model's consistent performance. This finding underlines the potential of our method to revolutionize balance assessment practices, particularly in settings where traditional methods are impractical or inaccessible.

Exploring the feasibility of tensor decomposition for analysis of fNIRS signals: a comparative study with grand averaging method.

The analysis of functional near-infrared spectroscopy (fNIRS) signals has not kept pace with the increased use of fNIRS in the behavioral and brain sciences. The popular grand averaging method collapses the oxygenated hemoglobin data within a predefined time of interest window and across multiple channels within a region of interest, potentially leading to a loss of important temporal and spatial information. On the other hand, the tensor decomposition method can reveal patterns in the data without making prior assumptions of the hemodynamic response and without losing temporal and spatial information. The aim of the current study was to examine whether the tensor decomposition method could identify significant effects and novel patterns compared to the commonly used grand averaging method for fNIRS signal analysis. We used two infant fNIRS datasets and applied tensor decomposition (i.e., canonical polyadic and Tucker decompositions) to analyze the significant differences in the hemodynamic response patterns across conditions. The codes are publicly available on GitHub. Bayesian analyses were performed to understand interaction effects. The results from the tensor decomposition method replicated the findings from the grand averaging method and uncovered additional patterns not detected by the grand averaging method. Our findings demonstrate that tensor decomposition is a feasible alternative method for analyzing fNIRS signals, offering a more comprehensive understanding of the data and its underlying patterns.

Pathological speech signal analysis using time-frequency approaches.

Acoustical measures of vocal function are important in the assessments of disordered voice, and for monitoring patients' progress over the course of voice therapy. In the last 2 decades, a variety of techniques for automatic pathological voice detection have been proposed, ranging from traditional temporal or spectral approaches to advanced time-frequency techniques. However, comparison of these methods is a difficult task because of the diversity of approaches. In this article, we explain a framework that holds the existing methods. In the light of this framework, the methodologic principles of disordered voice analysis schemes are compared and discussed. In addition, this article presents a comprehensive review to demonstrate the advantages of time-frequency approaches in analyzing and extracting pathological structures from speech signals. This information may have an important role in the development of new approaches to this problem.

Computational Methods for Physiological Signal Processing and Data Analysis.

Biomedical signal processing and data analysis play pivotal roles in the advanced medical expert system solutions. Signal processing tools are able to diminish the potential artifact effects and improve the anticipative signal quality. Data analysis techniques can assist in reducing redundant data dimensions and extracting dominant features associated with pathological status. Recent computational methods have greatly improved the effectiveness of signal processing and data analysis, to support the efficient point-of-care diagnosis and accurate medical decision-making. This editorial article highlights the research works published in the special issue of Computational Methods for Physiological Signal Processing and Data Analysis. The context introduces three deep learning applications in epileptic seizure detection, human exercise intensity analysis, and lung nodule CT image segmentation, respectively. The article also summarizes the research works on detection of event-related potential in the single-trial electroencephalogram (EEG) signals during the auditory tests, along with the methodology on estimating the generalized exponential distribution parameters using the simulated and real data produced under the Type I generalized progressive hybrid censoring schemes. The article concludes with perspectives and discussions on future trends in biomedical signal processing and data analysis technologies.

Dyskinesia Estimation of Imbalanced Data Using a Deep-Learning Model.

The collection of Parkinson's Disease (PD) time-series data usually results in imbalanced and incomplete datasets due to the geometric distribution of PD complications' sever-ity scores. Consequently, when training deep convolutional models on these datasets, the models suffer from overfitting and lack generalizability to unseen data. In this paper, we investigated a new framework of Conditional Generative Ad-versarial Netuwoks (cGANs) as a solution to improve the extrapolation and generalizability of the regression models in such datasets. We used a real-world PD dataset to esti-mate Dyskinesia severity in patients with PD. The developed cGAN demonstrated significantly better generalizability to unseen data samples than a traditional Convolutional Neural Network with an improvement of 34%. This solution can be applied in similar imbalanced time-series data, especially in the healthcare domain, where balanced and uniformly distributed data samples are not readily available.

Activity Recognition in Parkinson's Patients from Motion Data Using a CNN Model Trained by Healthy Subjects.

Physical activity recognition in patients with Parkinson's Disease (PwPD) is challenging due to the lack of large-enough and good quality motion data for PwPD. A common approach to this obstacle involves the use of models trained on better quality data from healthy patients. Models can struggle to generalize across these domains due to motor complications affecting the movement patterns in PwPD and differences in sensor axes orientations between data. In this paper, we investigated the generalizability of a deep convolutional neural network (CNN) model trained on a young, healthy population to PD, and the role of data augmentation on alleviating sensor position variability. We used two publicly available healthy datasets - PAMAP2 and MHEALTH. Both datasets had sensor placements on the chest, wrist, and ankle with 9 and 10 subjects, respectively. A private PD dataset was utilized as well. The proposed CNN model was trained on PAMAP2 in k-fold cross-validation based on the number of subjects, with and without data augmentation, and tested directly on MHEALTH and PD data. Without data augmentation, the trained model resulted in 48.16% accuracy on MHEALTH and 0% on the PD data when directly applied with no model adaptation techniques. With data augmentation, the accuracies improved to 87.43% and 44.78%, respectively, indicating that the method compensated for the potential sensor placement variations between data. Clinical Relevance- Wearable sensors and machine learning can provide important information about the activity level of PwPD. This information can be used by the treating physician to make appropriate clinical interventions such as rehabilitation to improve quality of life.

Alzheimer's Disease Detection Using Comprehensive Analysis of Timed Up and Go Test via Kinect V.2 Camera and Machine Learning.

Alzheimer's disease (AD) is a progressive neurodegenerative disease affecting cognitive and functional abilities. However, many patients presume lower cognitive or functional abilities because of aging and do not undergo clinical assessments until the symptoms become too advanced. Developing a low-cost and easy-to-use AD detection tool, which can be used in any clinical or non-clinical setting, can enable widespread AD assessments and diagnosis. This paper investigated the feasibility of developing such a tool to detect AD vs. healthy control (HC) from a simple balance and walking assessment called the Timed Up and Go (TUG) test. We collected joint position data of 47 HC and 38 AD subjects as they performed TUG in front of a Kinect V.2 camera. Our signal processing and statistical analyses provided a comprehensive analysis of balance and gait with 12 significant features for discriminating AD from HC after adjusting for age and the Geriatric Depression Scale. Using these features and a support vector machine classifier, our model classified the two groups with an average accuracy of 97.75% and an F-score of 97.67% for five-fold cross-validation and 98.68% and 98.67% for leave-one-subject out cross-validation. These results demonstrate the potential of our approach as a new quantitative complementary tool for detecting AD among older adults. Our work is novel as it presents the first application of Kinect V.2 camera and machine learning to provide a comprehensive and quantitative analysis of the TUG test to detect AD patients from HC. This study supports the feasibility of developing a low-cost and convenient AD assessment tool that can be used during routine checkups or even at home; however, future investigations could confirm its clinical diagnostic value in a larger cohort.

Dyskinesia estimation during activities of daily living using wearable motion sensors and deep recurrent networks.

Levodopa-induced dyskinesias are abnormal involuntary movements experienced by the majority of persons with Parkinson's disease (PwP) at some point over the course of the disease. Choreiform as the most common phenomenology of levodopa-induced dyskinesias can be managed by adjusting the dose/frequency of PD medication(s) based on a PwP's motor fluctuations over a typical day. We developed a sensor-based assessment system to provide such information. We used movement data collected from the upper and lower extremities of 15 PwPs along with a deep recurrent model to estimate dyskinesia severity as they perform different activities of daily living (ADL). Subjects performed a variety of ADLs during a 4-h period while their dyskinesia severity was rated by the movement disorder experts. The estimated dyskinesia severity scores from our model correlated highly with the expert-rated scores (r = 0.87 (p < 0.001)), which was higher than the performance of linear regression that is commonly used for dyskinesia estimation (r = 0.81 (p < 0.001)). Our model provided consistent performance at different ADLs with minimum r = 0.70 (during walking) to maximum r = 0.84 (drinking) in comparison to linear regression with r = 0.00 (walking) to r = 0.76 (cutting food). These findings suggest that when our model is applied to at-home sensor data, it can provide an accurate picture of changes of dyskinesia severity facilitating effective medication adjustments.