An explainable ensemble machine learning model using baseline blood transcriptomics to predict Parkinson's disease motor progression
Author:
Open Access
- 18 February 2026
- journal article
- research article
- Published by Frontiers Media SA in Frontiers in Digital Health
- Vol. 8, 1774436
Abstract
Introduction: Predicting Parkinson's disease (PD) motor progression remains challenging despite advances in neuroimaging. Blood-based transcriptomic profiling offers a more accessible and cost-effective alternative. This study aimed to develop and validate a machine learning approach using blood-based transcriptomic data to predict 12-month motor severity in PD and to identify the transcriptomic features and biological pathways most strongly associated with progression. Methods: A Stacking Regressor ensemble model combining three gradient boosting algorithms (XGBoost, LightGBM, CatBoost) was developed using baseline Parkinson's Progression Markers Initiative (PPMI) data ( n = 390), integrating blood RNA sequencing (RNA-seq) and clinical features to predict 12-month UPDRS Part III scores. SHapley Additive exPlanations (SHAP) analysis was applied to identify key prognostic features, evaluating seven PD risk genes (SNCA, LRRK2, GBA, PRKN, PINK1, PARK7, VPS35) and pathway scores for mitochondrial dysfunction, neuroinflammation, and autophagy. Results: On an independent test set ( n = 78), the model achieved a Coefficient of Determination (R²) of 0.551 and Mean Absolute Error (MAE) of 6.01. SHAP analysis identified the baseline UPDRS × PINK1 interaction (UPDRS_BL × PINK1) as the most influential feature (mean |SHAP| = 0.283). Among transcriptomic features, VPS35 (mean |SHAP| = 0.010), GBA, and LRRK2 were most prominent. Mitochondrial dysfunction showed the highest pathway contribution (mean |SHAP| = 0.008). Discussion: The study establishes that machine learning integrating blood transcriptomics and clinical data effectively predicts motor progression in PD. Crucially, the interplay between initial clinical state and specific genetic backgrounds-particularly PINK1-is a more powerful prognostic indicator than any factor alone. This study provides systematic evidence that mitochondrial dysfunction is a dominant prognostic signal for disease progression, nominating key genes and pathways for future mechanistic and therapeutic investigation.Keywords
This publication has 30 references indexed in Scilit:
- Identification and prediction of Parkinson’s disease subtypes and progression using machine learning in two cohortsnpj Parkinson's Disease, 2022
- Explanation of machine learning models using shapley additive explanation and application for real data in hospitalComputer Methods and Programs in Biomedicine, 2022
- Prediction of motor Unified Parkinson's Disease Rating Scale scores in patients with Parkinson’s disease using surface electromyographyClinical Neurophysiology, 2021
- Predicting Parkinson's disease trajectory using clinical and neuroimaging baseline measuresParkinsonism & Related Disorders, 2021
- Minimal Clinically Important Difference for UPDRS‐III in Daily PracticeMovement Disorders Clinical Practice, 2018
- Genetics of Parkinson disease2018
- The Roles of PINK1, Parkin, and Mitochondrial Fidelity in Parkinson’s DiseaseNeuron, 2015
- Genetic etiology of Parkinson disease associated with mutations in the SNCA, PARK2, PINK1, PARK7, and LRRK2 genes: a mutation updateHuman Mutation, 2010
- The Clinically Important Difference on the Unified Parkinson's Disease Rating ScaleArchives of Neurology, 2010
- Is Combining Classifiers with Stacking Better than Selecting the Best One?Machine Learning, 2004