Clinical Scorecard: Innovative Remote Evaluation of Motor and Cognitive Functions in Parkinson's Disease: Utilizing Large Datasets, Machine Learning, and Telehealth Solutions

At a Glance

Key Highlights

• Development of the Motor and Cognitive Videoconference (MaC-VC) protocol enabling remote, non-expert administration of MDS-UPDRS III and MoCA tests
• Abridged online MDS-UPDRS III accounts for 95% variance of full in-person scores, demonstrating validity
• Machine learning classifiers show high predictive accuracy (AUC > 0.9) across datasets, supporting generalizability

Guideline-Based Recommendations

Diagnosis

• Utilize MaC-VC protocol for remote assessment of motor (MDS-UPDRS III) and cognitive (MoCA) functions in PD
• Consider abridged MDS-UPDRS III for efficient online evaluation correlating strongly with full assessments

Management

• Incorporate telehealth solutions to improve accessibility and scalability of PD assessments
• Leverage machine learning classifiers to support clinical decision-making across diverse populations

Monitoring & Follow-up

• Regular remote monitoring of motor and cognitive symptoms using validated online tools like MaC-VC
• Use cross-dataset validated ML models to track disease progression and stratify patients

Risks

• Ensure data privacy and patient confidentiality when handling sensitive remote assessment data
• Be aware of potential limitations in remote testing due to technology access or user proficiency

Patient & Prescribing Data

145 PD participants from over 60 geographical locations assessed remotely; compared with 1264 expert-rated in-person assessments

Remote assessments via MaC-VC are feasible and yield results consistent with in-person evaluations, supporting broader telehealth adoption

Clinical Best Practices

• Train non-expert personnel in administering MaC-VC protocol to expand reach of PD assessments
• Use abridged MDS-UPDRS III and MoCA tests validated for remote use to maintain assessment accuracy
• Apply machine learning models validated across datasets to enhance diagnostic and monitoring accuracy
• Maintain strict data privacy standards and obtain informed consent for remote data collection
• Combine remote assessments with in-person evaluations when necessary to confirm findings

References

• Binoy et al., Online cognitive testing in Parkinson’s disease: advantages and challenges, Front. Neurol. 2024
• Goetz et al., Movement disorder society-sponsored revision of the Unified Parkinson’s disease rating scale (MDS-UPDRS), Mov. Disord. 2008
• Nasreddine et al., The Montreal Cognitive Assessment, MoCA: a brief screening tool for mild cognitive impairment, J. Am. Geriatr. Soc. 2005
• Hewitt et al., Transitioning to telehealth neuropsychology service, Clin. Neuropsychol. 2020
• Moustafa et al., Motor symptoms in Parkinson’s disease: a unified framework, Neurosci. Biobehav. Rev. 2016