Parkinson's severity diagnosis explainable model based on 3D multi-head attention residual network

Jiehui Huang, Lishan Lin, Fengcheng Yu, Xuedong He, Wenhui Song, Jiaying Lin, Zhenchao Tang, Kang Yuan, Yucheng Li, Haofan Huang, Zhong Pei, Wenbiao Xian, Calvin Yu-Chian Chen

Abstract: Highlights•Developed a facial video-based end-to-end PD severity diagnosis deep learning model.•The effective embedding of LSTM and attention modules enhances the model performance.•Provides an interpretable experiment consistent with clinical diagnostic experience.•The lightweight model achieves competitive and reliable diagnostic results.