Potential Pitfalls of Remote and Automated Video Assessments of Movements Disorders

Park, Kye Won; Wu, Hsin Jui; Yu, Tianze; Mahal, Ravneet; Mirian, Maryam S.; McKeown, Martin J.

doi:10.1002/mds.29325

Cited by 3 publications

(5 citation statements)

References 2 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…The structure of the Decision Tree and the confusion matrix of the classification results are shown in Figure 8 and Figure 9, respectively. entropy = 2.278 samples = 60 value = [7,13,14,15,11] 8)) aligns well with the MDS-UPDRS rating guidelines. These guidelines instruct raters to evaluate finger tapping based on: (i) amplitude, (ii) velocity, (iii) decrement in amplitude or velocity during repetitive tapping, and (iv) the presence of halts or hesitations [3].…”

Section: Classification Of Updrs Finger Tapping Scoresupporting

confidence: 72%

“…However, concerns regarding costs and potential issues with patient compliance regarding wearable sensors have led to growing interest in video-based analysis. This method offers a non-contact, unobtrusive alternative for the automated assessment of motor symptoms in PD [12,13]. That said, there are technical challenges associated with the remote interpretation of video recordings [5].…”

Section: Introductionmentioning

confidence: 99%

See 1 more Smart Citation

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

Yu,

Park,

McKeown

et al. 2023

Sensors

Self Cite

View full text Add to dashboard Cite

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.

show abstract

Section: Classification Of Updrs Finger Tapping Scoresupporting

confidence: 72%

Section: Introductionmentioning

confidence: 99%

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

Yu,

Park,

McKeown

et al. 2023

Sensors

Self Cite

View full text Add to dashboard Cite

show abstract

“…First, the video’s quality may affect an AI model’s performance. [ 43 ] We can categorise the potential factors that impede video quality into three groups: video-related, content-related and network-related factors. Video-related factors encompass not only basic video settings such as temporal and spatial resolutions, but also advanced aspects like lighting conditions in the recording space, motion blurring and focus.…”

Section: Potential Pitfalls Of Video-based Monitoringmentioning

confidence: 99%

Artificial intelligence-based video monitoring of movement disorders in the elderly: a review on current and future landscapes

Park,

Mirian,

McKeown

2024

Singapore Medical Journal

Self Cite

View full text Add to dashboard Cite

Due to global ageing, the burden of chronic movement and neurological disorders (Parkinson’s disease and essential tremor) is rapidly increasing. Current diagnosis and monitoring of these disorders rely largely on face-to-face assessments utilising clinical rating scales, which are semi-subjective and time-consuming. To address these challenges, the utilisation of artificial intelligence (AI) has emerged. This review explores the advantages and challenges associated with using AI-driven video monitoring to care for elderly patients with movement disorders. The AI-based video monitoring systems offer improved efficiency and objectivity in remote patient monitoring, enabling real-time analysis of data, more uniform outcomes and augmented support for clinical trials. However, challenges, such as video quality, privacy compliance and noisy training labels, during development need to be addressed. Ultimately, the advancement of video monitoring for movement disorders is expected to evolve towards discreet, home-based evaluations during routine daily activities. This progression must incorporate data security, ethical considerations and adherence to regulatory standards.

show abstract

“…Still, it has limitations, including lower accuracy than marker-based systems, difficulty tracking occluded or partially visible body parts, and sensitivity to environmental factors. Nonetheless, ongoing advances in computer vision and machine learning are enhancing the accuracy and robustness of these techniques [ 262 – 267 ], making them potentially valuable for tremor characterization—for example, Park et al [ 15 ] utilized Mediapipe [ 268 ] to analyze its feasibility in telemedicine for PD. Although the study involved healthy subjects, the findings suggested that movement tracking accuracy was hindered by poor video quality.…”

Section: Technologies For Tremor Assessmentmentioning

confidence: 99%

“…2 Types of tremor assessment technologies include activity level tasks and tools such as tablets and smartphones for drawing, physiological technologies such as surface electromyography (EMG) and electroencephalogram (EEG), and body function level movement-based technologies such as inertial measurement units (IMUs) and camera systems for measuring upper limb pose and movement. Figures adapted from [ 13 , 14 ] used under CC BY 4.0 and from [ 15 ] used under granted copyright by CCC RightsLink …”

Section: Introductionmentioning

confidence: 99%

Upper limb intention tremor assessment: opportunities and challenges in wearable technology

Paredes-Acuna,

Utpadel-Fischler,

Ding

et al. 2024

J NeuroEngineering Rehabil

View full text Add to dashboard Cite

Background Tremors are involuntary rhythmic movements commonly present in neurological diseases such as Parkinson's disease, essential tremor, and multiple sclerosis. Intention tremor is a subtype associated with lesions in the cerebellum and its connected pathways, and it is a common symptom in diseases associated with cerebellar pathology. While clinicians traditionally use tests to identify tremor type and severity, recent advancements in wearable technology have provided quantifiable ways to measure movement and tremor using motion capture systems, app-based tasks and tools, and physiology-based measurements. However, quantifying intention tremor remains challenging due to its changing nature. Methodology & Results This review examines the current state of upper limb tremor assessment technology and discusses potential directions to further develop new and existing algorithms and sensors to better quantify tremor, specifically intention tremor. A comprehensive search using PubMed and Scopus was performed using keywords related to technologies for tremor assessment. Afterward, screened results were filtered for relevance and eligibility and further classified into technology type. A total of 243 publications were selected for this review and classified according to their type: body function level: movement-based, activity level: task and tool-based, and physiology-based. Furthermore, each publication's methods, purpose, and technology are summarized in the appendix table. Conclusions Our survey suggests a need for more targeted tasks to evaluate intention tremors, including digitized tasks related to intentional movements, neurological and physiological measurements targeting the cerebellum and its pathways, and signal processing techniques that differentiate voluntary from involuntary movement in motion capture systems.

show abstract

Potential Pitfalls of Remote and Automated Video Assessments of Movements Disorders

Cited by 3 publications

References 2 publications

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

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

Artificial intelligence-based video monitoring of movement disorders in the elderly: a review on current and future landscapes

Upper limb intention tremor assessment: opportunities and challenges in wearable technology

Contact Info

Product

Resources

About