Explainable machine learning reveals the challenges of predicting new-onset motor complications in Parkinson’s disease

Predicting new-onset motor fluctuations and levodopa-induced dyskinesias (LID) is crucial for optimizing Parkinson’s disease management. To establish a transparent prognostic framework, we applied explainable machine learning to real-world, multicentric clinical data from 247 patients to forecast the 3-year onset of these complications. Evaluated strictly on complication-free patients, the models achieved moderate predictive power (LID MCC = 0.28; fluctuations MCC = 0.32). SHAP-based interpretability confirmed predictions aligned accurately with established clinical knowledge, driven primarily by levodopa duration and Levodopa Equivalent Daily Dose, with risk increasing significantly above a 300–400 mg threshold. Crucially, an ablation study revealed that excluding patients with pre-existing complications from training caused model sensitivity to collapse, demonstrating that the full spectrum of disease severity is essential for robust risk stratification. Ultimately, this rigorous methodological stress-test demonstrates that baseline clinical features alone yield limited absolute sensitivity, highlighting the necessity of integrating dynamic, longitudinal data to achieve clinical-grade individualized prediction.

Authors

Institutions

Publication Details

Journal
npj Parkinson s Disease
Published
2026-09-04
DOI
https://doi.org/10.1038/s41531-026-01550-1
Primary Topic
Parkinson's Disease Mechanisms and Treatments
Type
article
Field-Weighted Citation Impact
0.00

Funders

Controls
|||
ALL TIME
JAN
FEB
MAR
APR
MAY
JUN
JUL
AUG
SEP
article

Explainable machine learning reveals the challenges of predicting new-onset motor complications in Parkinson’s disease

Venet Osmani, Federica Sabatini, Antonio Verrico, Domenico Tortora et al.
npj Parkinson s Disease
Parkinson's Disease Mechanisms and Treatments
article

Explainable machine learning reveals the challenges of predicting new-onset motor complications in Parkinson’s disease

Venet Osmani, Federica Sabatini, Antonio Verrico, Domenico Tortora, Isabella Cama, Claudia Niccolai, Matteo Betti, Sara Garbarino, Bruno Giometto, Emilio Portaccio, Antonio Uccelli, Guido Pasquini, Monica Moroni, Raffaella Di Giacopo, Nicole Campese, Stefano Bovo, Antonella Castellano, Lorenzo Gios, Flavio Ragni, Andrea Falini, Filippo Gerli, Cristina Campi, Maria Chiara Malaguti, Walter Endrizzi, Andrea Rossi, A. Cirone, Giuseppe Jurman, Costanza Parodi, Ruggero Bacchin, Michele Piana, the NeuroArtP3 Network, Donatella Ottaviani, Chiara Longo
article en

Abstract

Predicting new-onset motor fluctuations and levodopa-induced dyskinesias (LID) is crucial for optimizing Parkinson’s disease management. To establish a transparent prognostic framework, we applied explainable machine learning to real-world, multicentric clinical data from 247 patients to forecast the 3-year onset of these complications. Evaluated strictly on complication-free patients, the models achieved moderate predictive power (LID MCC = 0.28; fluctuations MCC = 0.32). SHAP-based interpretability confirmed predictions aligned accurately with established clinical knowledge, driven primarily by levodopa duration and Levodopa Equivalent Daily Dose, with risk increasing significantly above a 300–400 mg threshold. Crucially, an ablation study revealed that excluding patients with pre-existing complications from training caused model sensitivity to collapse, demonstrating that the full spectrum of disease severity is essential for robust risk stratification. Ultimately, this rigorous methodological stress-test demonstrates that baseline clinical features alone yield limited absolute sensitivity, highlighting the necessity of integrating dynamic, longitudinal data to achieve clinical-grade individualized prediction.

npj Parkinson s Disease
Humanitas University (IT), Vita-Salute San Raffaele University (IT), Queen Mary University of London (GB), University of Trento (IT), Fondazione Bruno Kessler (IT), Istituto Giannina Gaslini (IT), Ospedale Santa Chiara (IT), Provincia Autonoma di Trento (IT), Ospedale Santa Maria (IT), Don Carlo Gnocchi Foundation (IT), IRCCS Ospedale San Raffaele (IT), Ospedale Policlinico San Martino (IT), Istituti di Ricovero e Cura a Carattere Scientifico (IT), University of Florence (IT), University of Genoa (IT)
Ministero della Salute
Openalex Percentile: Top 11%
Parkinson's Disease Mechanisms and Treatments
AI Navigator

Ask Laika to Summarize, Analyze, and Connect papers live on the map.

Summarize Papers & Methodologies

Extract key findings, datasets, and comparative methods across publications.

Benchmark Rankings & Visual Analytics

Rank top research institutions, authors, funders, topics, and journals by Field-Weighted Citation Impact (FWCI) and paper volume with instant charts.

Connect Distant Disciplines

Bridge topological clusters on the map to find hidden collaborative intersections.