Using AI to measure Parkinson's disease severity at home

Feasibility of computerized motor, cognitive and speech tests in the home: Analysis of TAS Test in 2,300 older adults

BACKGROUND

Early detection of Alzheimer's disease (AD) risk is crucial for dementia prevention. Tasmanian Test (TAS Test) is a novel, unsupervised, computerized assessment of motor, cognitive, and speech function designed to detect AD risk.

OBJECTIVES

To evaluate the feasibility, usability, and acceptability of TAS Test.

DESIGN AND SETTING

TAS Test was administered remotely at home and/or in a research facility, using personal computers.

PARTICIPANTS

2,351 adults aged 50-89 years (mean 65.35), 71.76 % female, from Tasmania, Australia.

MEASUREMENTS

Completion rates, ease-of-use, distraction, test duration, and enjoyment scores. Demographics, computer literacy, cognition, and mood were analyzed.

RESULTS

Over 80 % completed motor and cognitive components with 92.8 % completing speech tests. 89.81 % found the duration acceptable. 80.90 % of remote and 83.46 % of onsite participants enjoyed the procedure. High usability and acceptability were reported, with age, gender, education, computer literacy, cognition and mood having minimal or no impact.

CONCLUSIONS

TAS Test demonstrated high completion rates and user satisfaction across a large community sample, supporting its feasibility as an unsupervised computerized assessment tool. Future research should address demographic representation and technical refinements.

AI and Neurology

BACKGROUND

Artificial Intelligence is influencing medicine on all levels. Neurology, one of the most complex and progressive medical disciplines, is no exception. No longer limited to neuroimaging, where data-driven approaches were initiated, machine and deep learning methodologies are taking neurologic diagnostics, prognostication, predictions, decision making and even therapy to very promising potentials.

MAIN BODY

In this review, the basic principles of different types of Artificial Intelligence and the options to apply them to neurology are summarized. Examples of noteworthy studies on such applications are presented from the fields of acute and intensive care neurology, stroke, epilepsy, and movement disorders. Finally, these potentials are matched with risks and challenges jeopardizing ethics, safety and equality, that need to be heeded by neurologists welcoming Artificial Intelligence to their field of expertise.

CONCLUSION

Artificial intelligence is and will be changing neurology. Studies need to be taken to the prospective level and algorithms undergo federated learning to reach generalizability. Neurologists need to master not only the benefits but also the risks in safety, ethics and equity of such data-driven form of medicine.

Improving reliability of movement assessment in Parkinson's disease using computer vision-based automated severity estimation

BACKGROUND

Clinical assessments of motor symptoms rely on observations and subjective judgments against standardized scales, leading to variability due to confounders. Improving inter-rater agreement is essential for effective disease management.

OBJECTIVE

We developed an objective rating system for Parkinson's disease (PD) that integrates computer vision (CV) and machine learning to correct potential discrepancies among raters while providing the basis for model performance to gain professional acceptance.

METHODS

A prospective PD cohort (n = 128) were recruited from multi-centers. Motor examination videos were recorded using an android tablet with CV-based software following the MDS-UPDRS Part-III instructions. Videos included facial, upper- and lower-limb movements, arising from a chair, standing, and walking. Fifteen certified clinicians were recruited from multi-centers. For each video, five clinicians were randomly selected to independently rate the severity of motor symptoms, validate the videos and movement variables (MovVars). Machine learning algorithms were applied for automated rating and feature importance analysis. Inter-rater agreement among human raters and the agreement between artificial intelligence (AI)-generated ratings and expert consensus were calculated.

RESULTS

For all validated videos (n = 1024), AI-based ratings showed an average absolute accuracy of 69.63% and an average acceptable accuracy of 98.78% against the clinician consensus. The mean absolute error between the AI-based scores and clinician consensus was 0.32, outperforming the inter-rater variability (0.65), potentially due to the combined utilization of diverse MovVars.

CONCLUSIONS

The algorithm enabled accurate video-based evaluation of mild motor symptom severity. AI-assisted assessment improved the inter-rater agreement, demonstrating the practical value of CV-based tools in screening, diagnosing, and treating movement disorders.

Development of Neurodegenerative Disease Diagnosis and Monitoring from Traditional to Digital Biomarkers

Monitoring and assessing the progression of symptoms in neurodegenerative diseases, including Alzheimer's and Parkinson's disease, are critical for improving patient outcomes. Traditional biomarkers, such as cerebrospinal fluid analysis and brain imaging, are widely used to investigate the underlying mechanisms of disease and enable early diagnosis. In contrast, digital biomarkers derived from phenotypic changes-such as EEG, eye movement, gait, and speech analysis-offer a noninvasive and accessible alternative. Leveraging portable and widely available devices, such as smartphones and wearable sensors, digital biomarkers are emerging as a promising tool for ND diagnosis and monitoring. This review highlights the comprehensive developments in digital biomarkers, emphasizing their unique advantages and integration potential alongside traditional biomarkers.

Hospitalization prediction from the emergency department using computer vision AI with short patient video clips

In this study, we investigate the performance of computer vision AI algorithms in predicting patient disposition from the emergency department (ED) using short video clips. Clinicians often use "eye-balling" or clinical gestalt to aid in triage, based on brief observations. We hypothesize that AI can similarly use patient appearance for disposition prediction. Data were collected from adult patients at an academic ED, with mobile phone videos capturing patients performing simple tasks. Our AI algorithm, using video alone, showed better performance in predicting hospital admissions (AUROC = 0.693 [95% CI 0.689, 0.696]) compared to models using triage clinical data (AUROC = 0.678 [95% CI 0.668, 0.687]). Combining video and triage data achieved the highest predictive performance (AUROC = 0.714 [95% CI 0.709, 0.719]). This study demonstrates the potential of video AI algorithms to support ED triage and alleviate healthcare capacity strains during periods of high demand.

Integrating Big Data, Artificial Intelligence, and motion analysis for emerging precision medicine applications in Parkinson's Disease

One of the key challenges in Big Data for clinical research and healthcare is how to integrate new sources of data, whose relation to disease processes are often not well understood, with multiple classical clinical measurements that have been used by clinicians for years to describe disease processes and interpret therapeutic outcomes. Without such integration, even the most promising data from emerging technologies may have limited, if any, clinical utility. This paper presents an approach to address this challenge, illustrated through an example in Parkinson's Disease (PD) management. We show how data from various sensing sources can be integrated with traditional clinical measurements used in PD; furthermore, we show how leveraging Big Data frameworks, augmented by Artificial Intelligence (AI) algorithms, can distinctively enrich the data resources available to clinicians. We showcase the potential of this approach in a cohort of 50 PD patients who underwent both evaluations with an Integrated Motion Analysis Suite (IMAS) composed of a battery of multimodal, portable, and wearable sensors and traditional Unified Parkinson's Disease Rating Scale (UPDRS)-III evaluations. Through techniques including Principal Component Analysis (PCA), elastic net regression, and clustering analysis we demonstrate how this combined approach can be used to improve clinical motor assessments and to develop personalized treatments. The scalability of our approach enables systematic data generation and analysis on increasingly larger datasets, confirming the integration potential of IMAS, whose use in PD assessments is validated herein, within Big Data paradigms. Compared to existing approaches, our solution offers a more comprehensive, multi-dimensional view of patient data, enabling deeper clinical insights and greater potential for personalized treatment strategies. Additionally, we show how IMAS can be integrated into established clinical practices, facilitating its adoption in routine care and complementing emerging methods, for instance, non-invasive brain stimulation. Future work will aim to augment our data repositories with additional clinical data, such as imaging and biospecimen data, to further broaden and enhance these foundational methodologies, leveraging the full potential of Big Data and AI.

Machine learning explains response variability of deep brain stimulation on Parkinson's disease quality of life

Improving health-related quality of life (QoL) is crucial for managing Parkinson's disease. However, QoL outcomes after deep brain stimulation (DBS) of the subthalamic nucleus (STN) vary considerably. Current approaches lack integration of demographic, patient-reported, neuroimaging, and neurophysiological data to understand this variability. This study used explainable machine learning to analyze multimodal factors affecting QoL changes, measured by the Parkinson's Disease Questionnaire (PDQ-39) in 63 patients, and quantified each variable's contribution. Results showed that preoperative PDQ-39 scores and upper beta band activity (>20 Hz) in the left STN were key predictors of QoL changes. Lower initial QoL burden predicted worsening, while improvement was associated with higher beta activity. Additionally, electrode positions along the superior-inferior axis, especially relative to the z = -7 coordinate in standard space, influenced outcomes, with improved and worsened QoL above and below this marker. This study emphasizes a tailored, data-informed approach to optimize DBS treatment and improve patient QoL.

Analyzing Wav2Vec 1.0 Embeddings for Cross-Database Parkinson's Disease Detection and Speech Features Extraction

Advancements in deep learning speech representations have facilitated the effective use of extensive unlabeled speech datasets for Parkinson's disease (PD) modeling with minimal annotated data. This study employs the non-fine-tuned wav2vec 1.0 architecture to develop machine learning models for PD speech diagnosis tasks, such as cross-database classification and regression to predict demographic and articulation characteristics. The primary aim is to analyze overlapping components within the embeddings on both classification and regression tasks, investigating whether latent speech representations in PD are shared across models, particularly for related tasks. Firstly, evaluation using three multi-language PD datasets showed that wav2vec accurately detected PD based on speech, outperforming feature extraction using mel-frequency cepstral coefficients in the proposed cross-database classification scenarios. In cross-database scenarios using Italian and English-read texts, wav2vec demonstrated performance comparable to intra-dataset evaluations. We also compared our cross-database findings against those of other related studies. Secondly, wav2vec proved effective in regression, modeling various quantitative speech characteristics related to articulation and aging. Ultimately, subsequent analysis of important features examined the presence of significant overlaps between classification and regression models. The feature importance experiments discovered shared features across trained models, with increased sharing for related tasks, further suggesting that wav2vec contributes to improved generalizability. The study proposes wav2vec embeddings as a next promising step toward a speech-based universal model to assist in the evaluation of PD.

Enhancing Model Generalizability In Parkinson's Disease Automatic Assessment: A Semi-Supervised Approach Across Independent Experiments

Machine learning in Parkinson's disease assessment uses data from clinically-coded movements, such as finger tapping, to objectively measure motor impairment. Video-based models showed promise in several experiments, but the lack of a unified test benchmark hinders proving generalizability. Additionally, new telemedicine systems may easily collect large amounts of unsupervised data, while obtaining ground truth labels for supervised learning remains time-consuming and requires specialized clinicians. This study explores semi-supervised learning to enhance the generalizability of a Light Gradient Boosting model for video-based finger tapping staging, while reducing its need for supervised data labelling. Specifically, this work employs the Self-training schema in two trials using openly-available finger tapping datasets from three independent experiments. This method significantly improves model performance across various metrics, achieving notable accuracy gains (e.g., from 87.62% to 92.05%) when tested on unseen data from a different experiment. Semi-supervision proves valuable when limited labelled data (less than 10%) from the test distribution are available during training.

Characterizing Disease Progression in Parkinson's Disease from Videos of the Finger Tapping Test

INTRODUCTION

Parkinson's disease (PD) is characterized by motor symptoms whose progression is typically assessed using clinical scales, namely the Movement Disorder Society-Unified Parkinson's Disease Rating Scale (MDS-UPDRS). Despite its reliability, the scale is bounded by a 5-point scale that limits its ability to track subtle changes in disease progression and is prone to subjective interpretations. We aimed to develop an automated system to objectively quantify motor symptoms in PD using Machine Learning (ML) algorithms to analyze videos and capture nuanced features of disease progression.

METHODS

We analyzed videos of the Finger Tapping test, a component of the MDS-UPDRS, from 24 healthy controls and 66 PD patients using ML algorithms for hand pose estimation. We computed multiple movement features related to bradykinesia from videos and employed a novel tiered classification approach to predict disease severity that employed different features according to severity. We compared our video-based disease severity prediction approach against other approaches recently introduced in the literature.

RESULTS

Traditional kinematics features such as amplitude and velocity changed linearly with disease severity, while other non-traditional features displayed non-linear trends. The proposed disease severity prediction approach demonstrated superior accuracy in detecting PD and distinguishing between different levels of disease severity when compared to existing approaches.

FastEval Parkinsonism: an instant deep learning-assisted video-based online system for Parkinsonian motor symptom evaluation

The Motor Disorder Society's Unified Parkinson's Disease Rating Scale (MDS-UPDRS) is designed to assess bradykinesia, the cardinal symptoms of Parkinson's disease (PD). However, it cannot capture the all-day variability of bradykinesia outside the clinical environment. Here, we introduce FastEval Parkinsonism ( https://fastevalp.cmdm.tw/ ), a deep learning-driven video-based system, providing users to capture keypoints, estimate the severity, and summarize in a report. Leveraging 840 finger-tapping videos from 186 individuals (103 patients with Parkinson's disease (PD), 24 participants with atypical parkinsonism (APD), 12 elderly with mild parkinsonism signs (MPS), and 47 healthy controls (HCs)), we employ a dilated convolution neural network with two data augmentation techniques. Our model achieves acceptable accuracies (AAC) of 88.0% and 81.5%. The frequency-intensity (FI) value of thumb-index finger distance was indicated as a pivotal hand parameter to quantify the performance. Our model also shows the usability for multi-angle videos, tested in an external database enrolling over 300 PD patients.

The Effectiveness of Inpatient Rehabilitation in Parkinson's Disease: A Systematic Review of Recent Studies

Background

Parkinson's disease (PD) is a progressive disease, which is associated with the loss of activities of daily living independency. Several rehabilitation options have been studied during the last years, to improve mobility and independency.

Objective

This systematic review will focus on inpatient multidisciplinary rehabilitation (MR) in people with Parkinson's disease (PwPD), based on recent studies from 2020 onwards.

Methods

Search strategy in three databases included: multidisciplinary rehabilitation, Parkinson's Disease, inpatient rehabilitation, motor-, functional- and cognitive performance, cost-effectiveness, Quality of Life, and medication changes/Levodopa equivalent daily doses.

Results

Twenty-two studies were included, consisting of 13 studies dealing with inpatient MR and 9 studies on inpatient non-MR interventions. Inpatient PD multidisciplinary rehabilitation proved to be effective, as well as non-MR rehabilitation.

Conclusions

This review confirms the efficacy of inpatient MR and non-MR in PD, but is skeptical about the past and current study designs. New study designs, including new physical training methods, more attention to medication and costs, new biomarkers, artificial intelligence, and the use of wearables, will hopefully change rehabilitation trials in PwPD in the future.

Clinically Informed Automated Assessment of Finger Tapping Videos in Parkinson's Disease

The utilization of Artificial Intelligence (AI) for assessing motor performance in Parkinson's Disease (PD) offers substantial potential, particularly if the results can be integrated into clinical decision-making processes. However, the precise quantification of PD symptoms remains a persistent challenge. The current standard Unified Parkinson's Disease Rating Scale (UPDRS) and its variations serve as the primary clinical tools for evaluating motor symptoms in PD, but are time-intensive and prone to inter-rater variability. Recent work has applied data-driven machine learning techniques to analyze videos of PD patients performing motor tasks, such as finger tapping, a UPDRS task to assess bradykinesia. However, these methods often use abstract features that are not closely related to clinical experience. In this paper, we introduce a customized machine learning approach for the automated scoring of UPDRS bradykinesia using single-view RGB videos of finger tapping, based on the extraction of detailed features that rigorously conform to the established UPDRS guidelines. We applied the method to 75 videos from 50 PD patients collected in both a laboratory and a realistic clinic environment. The classification performance agreed well with expert assessors, and the features selected by the Decision Tree aligned with clinical knowledge. Our proposed framework was designed to remain relevant amid ongoing patient recruitment and technological progress. The proposed approach incorporates features that closely resonate with clinical reasoning and shows promise for clinical implementation in the foreseeable future.