Explainable machine learning model predicting neurological deterioration in Wilson's disease via MRI radiomics and clinical features.

Journal: Parkinsonism & related disorders
Published Date: Jun 4, 2025

Abstract

BACKGROUND: This study aims to build a machine learning (ML) model to predict the deterioration of neurological symptoms in Wilson's disease (WD) patients during short-term anti-copper therapy. The model combines brain T1WI MRI radiomics with clinical features and employs SHapley Additive exPlanations (SHAP) to interpret the contributions of the features.

Authors

  • Shijing Wang
    State Key Laboratory of Natural Medicines, School of Life Science and Technology, China Pharmaceutical University, Nanjing 210009, China.
  • Jie Chang
    School of Chinese Materia Medica, Nanjing University of Chinese Medicine, 138 Xianlin Road, Nanjing 210023, China.
  • Caiyu Yang
    Institute of Neurology, Anhui University of Traditional Chinese Medicine, Hefei, 230038, China; Affiliated Hospital of Institute of Neurology, Anhui Univesity of Traditional Chinese Medicine, No. 357, Changjiang Middle Road, Hefei, 230038, China.
  • Rao Rao
    Institute of Neurology, Anhui University of Traditional Chinese Medicine, Hefei, 230038, China; Affiliated Hospital of Institute of Neurology, Anhui Univesity of Traditional Chinese Medicine, No. 357, Changjiang Middle Road, Hefei, 230038, China.
  • Tong Wu
    National Clinical Research Center for Obstetrical and Gynecological Diseases Tongji Hospital, Tongji Medical College, Huazhong University of Science and Technology Wuhan China.
  • Jiawei Wang
    Biomedicine Discovery Institute, Monash University, VIC 3800, Australia.
  • Dandan Sun
    School of Materials Science and Engineering, Henan Key Laboratory of Advanced Nylon Materials and Application, Henan Innovation Center for Functional Polymer Membrane Materials, Zhengzhou University, Zhengzhou, 450001, China. lsrzzdx@zzu.edu.cn.
  • Kun Xia
    Department of Big Data and Biomedical AI, College of Future Technology, Peking University, Beijing, China.
  • Xun Wang
    College of Computer Science and Technology, China University of Petroleum, Dongying, China.
  • Yongzhu Han
    Institute of Neurology, Anhui University of Traditional Chinese Medicine, Hefei, 230038, China; Affiliated Hospital of Institute of Neurology, Anhui Univesity of Traditional Chinese Medicine, No. 357, Changjiang Middle Road, Hefei, 230038, China.
  • Yongsheng Han
    Institute of Neurology, Anhui University of Traditional Chinese Medicine, Hefei, 230038, China; Wannan Medical College, Wuhu, 241002, China; Center for Xin'an Medicine and Modernization of Traditional Chinese Medicine of IHM, Anhui University of Chinese Medicine, Hefei, 230012, China. Electronic address: hyssp@126.com.

Keywords

External Resources

Popular Topics
Recent Journals