Limited accessibility to neurological care leads to underdiagnosed Parkinson's Disease (PD), preventing early intervention. Existing AI-based PD detection methods primarily focus on unimodal analysis of motor or speech tasks, overlooking the multifaceted nature of the disease. To address this, we introduce a large-scale, multi-task video dataset consisting of 1102 sessions (each containing videos of finger tapping, facial expression, and speech tasks captured via webcam) from 845 participants (272 with PD). We propose a novel Uncertainty-calibrated Fusion Network (UFNet) that leverages this multimodal data to enhance diagnostic accuracy. UFNet employs independent task-specific networks, trained with Monte Carlo Dropout for uncertainty quantification, followed by self-attended fusion of features, with attention weights dynamically adjusted based on task-specific uncertainties. To ensure patient-centered evaluation, the participants were randomly split into three sets: 60% for training, 20% for model selection, and 20% for final performance evaluation. UFNet significantly outperformed single-task models in terms of accuracy, area under the ROC curve (AUROC), and sensitivity while maintaining non-inferior specificity. Withholding uncertain predictions further boosted the performance, achieving 88.0+-0.3%
View on arXiv@article{islam2025_2406.14856,
title={ Accessible, At-Home Detection of Parkinson's Disease via Multi-task Video Analysis },
author={ Md Saiful Islam and Tariq Adnan and Jan Freyberg and Sangwu Lee and Abdelrahman Abdelkader and Meghan Pawlik and Cathe Schwartz and Karen Jaffe and Ruth B. Schneider and E Ray Dorsey and Ehsan Hoque },
journal={arXiv preprint arXiv:2406.14856},
year={ 2025 }
}