Personalized medication recommendations for Parkinson’s disease patients using gated recurrent units and SHAP interpretability

• Published in: Scientific reports Vol. 15; no. 1; pp. 19074 - 12
• Main Authors: Riasi, Atiye, Delrobaei, Mehdi, Salari, Mehri
• Format: Journal Article
• Language: English
• Published: London Nature Publishing Group UK 30.05.2025; Nature Publishing Group; Nature Portfolio
• Subjects: 639/166; 692/699; 692/699/375; Aged; Algorithms; Antiparkinson Agents - therapeutic use; Decision support systems; Drugs; Explainable artificial intelligence; Female; Humanities and Social Sciences; Humans; Male; Middle Aged; Movement disorders; multidisciplinary; Neurodegenerative diseases; Parkinson Disease - drug therapy; Parkinson's disease; Personalized decisions; Pharmacological decisions; Precision Medicine - methods; ROC Curve; Science; Science (multidisciplinary); Sequential learning; Decision support systems; Explainable artificial intelligence; Pharmacological decisions; Personalized decisions; Sequential learning
• ISSN: 2045-2322; 2045-2322
• DOI: 10.1038/s41598-025-04217-8

Managing Parkinson’s disease (PD) through medication can be challenging due to varying symptoms and disease duration. This study aims to demonstrate the potential of sequence-by-sequence algorithms in recommending personalized medication combinations for patients with PD based on their previous visits. Our proposed method employs a gated recurrent unit model to predict accurate combinations of critical medication types for PD based on each patient’s motor symptoms and prescribed medication from previous visits. We built a multi-label model with gated recurrent units on two data architectures: (1) personalized input using each patient’s previous visits as a sample and (2) non-personalized input treating each visit as an independent sample. The 10-fold cross-validation results showed that the personalized architecture model outperforms the non-personalized model in accuracy (0.92), precision (0.94), recall (0.94), F1-score (0.94), Hamming loss (0.03), and macro average area under the receiver operating characteristic (0.94). To interpret the model’s predictions, we employed SHapley Additive exPlanations (SHAP) values, which provide insights into the importance of variables both globally (across the entire model) and at the individual patient level. The results contribute to the sequential-based decision support system potentially enhancing the remote management of PD pharmacologic issues.