VisionMD: an open-source tool for video-based analysis of motor function in movement disorders

Area of Science:

• Neurology
• Biomedical Engineering
• Computer Science

Background:

• Parkinson's disease and other movement disorders significantly impact motor function.
• Objective and scalable assessment of motor symptoms is crucial for diagnosis and management.
• Current assessment methods can be subjective or require specialized equipment.

Purpose of the Study:

• To introduce VisionMD, an open-source software for automated video-based analysis of MDS-UPDRS Part III motor tasks.
• To provide precise, objective, and scalable assessments of motor symptoms.
• To enable longitudinal monitoring of movement disorders.

Main Methods:

• Utilized deep learning algorithms to track body movements from video recordings.
• Computed kinematic features to quantify motor symptom severity.
• Developed a user-friendly and customizable software framework.

Main Results:

• VisionMD enables precise and objective quantification of motor symptoms.
• The software provides scalable assessments suitable for large cohorts.
• VisionMD supports longitudinal tracking of symptom progression without specialized hardware.

Conclusions:

• VisionMD offers a powerful, accessible tool for evaluating motor symptoms in movement disorders.
• The software empowers clinicians and researchers with objective data for improved patient care and research.
• Open-source availability promotes wider adoption and further development in the field.