Video-based machine learning models for predicting deep brain stimulation outcomes in Parkinson’s disease patients

npj Parkinson s Disease 2026 Open access

Read full text
Authors: Tianxue Hu, Quan Zhang, Zixiao. Yin, Yichen Xu, Boya Dong, Qi An, Yanwen Wang, Yifei Gan, Houyou Fan, Zehua Zhao, Zhaoting Zheng, Rujin Wang
+5 more Xianze Li, Pengda Yang, Hutao Xie, Jianguo Zhang, Anchao Yang
DOI: 10.1038/s41531-025-01252-0
Cited by: 1
References: 53

Abstract

Current levodopa challenge test (LCT) for deep brain stimulation (DBS) candidate screening in Parkinson's disease (PD) relies on subjective clinical scales, limiting its predictive capacity for postoperative motor outcomes. We developed video-based machine learning models using quantified kinematic metrics during preoperative LCT in seventy PD patients who underwent DBS surgery. Objective multi-domain motor features were extracted via validated motor assessment software. Binary classification defined patients' outcomes as DBS+ (≥30% improvement in MDS-UPDRS Part III) or DBS- (

Fields of Study & Subjects

Neurological disorders and treatments Parkinson's Disease Mechanisms and Treatments Parkinson's Disease and Spinal Disorders

Publication details

Journal / source
npj Parkinson s Disease
Publisher
Springer Science and Business Media LLC
Volume
12
Issue
1
Pages
40–40
Publication date
9 January 2026
Language
EN