Accessible assessment of motor and cognitive symptoms in Parkinson’s disease: integrating large datasets, machine-learning, and videoconferencing - Summary - MDSpire
Advertisement
Accessible assessment of motor and cognitive symptoms in Parkinson’s disease: integrating large datasets, machine-learning, and videoconferencing
To address specific challenges in accessibility, scalability, and geographical diversity in motor and cognitive assessments for Parkinson's disease (PD) through innovative remote evaluation methods.
Key Findings:
The abridged MDS-UPDRS III accounted for 95% of the variance in complete scores, indicating its effectiveness as a remote assessment tool.
Consistent significant trends observed in MDS-UPDRS-III, MoCA, disease duration, and sex across datasets, suggesting reliability across different populations.
ML classifiers achieved high classification performance (AUCs > 0.9) both within and between datasets, underscoring the potential for machine learning in clinical assessments.
Interpretation:
The findings support the feasibility and generalizability of the MaC-VC protocol, enhancing accessibility and scalability of PD assessments.
Limitations:
Datasets analyzed are not publicly available due to privacy concerns, which may limit the reproducibility of the study.
Code for data analysis is not openly available, though can be requested, potentially hindering transparency.
Conclusion:
MaC-VC demonstrates potential for remote evaluations in PD, addressing key barriers in traditional assessment methods.
Baptist Health Foundation announced that it has received a $2 million donation from Anthony and Joyce Esernia to establish a new endowed chair at Baptist Health Miami Neuroscience Institute.
