Multi-cohort machine learning identifies predictors of cognitive impairment in Parkinson’s disease

  • Rebecca Ting Jiin Loo
  • , Lukas Pavelka
  • , Graziella Mangone
  • , Fouad Khoury
  • , Marie Vidailhet
  • , Jean Christophe Corvol
  • , Enrico Glaab*
  • , Lydia Yahia-Cherif
  • , Caroline Weill
  • , Marie Vidailhet
  • , Romain Valabregue
  • , Arthur Tenenhaus
  • , Julie Socha
  • , Sara Sambin
  • , Sophie Rivaud-Péchoux
  • , Nadya Pyatigorskaya
  • , Fanny Pineau
  • , Dijana Petrovska
  • , Vincent Perlbarg
  • , Fanny Mochel
  • Poornima Menon, Graziella Mangone, Valentine Maheo, Richard Levy, Smaranda Leu Semenescu, Suzanne Lesage, Stéphane Lehéricy, Mickaël Lé, Louise Laure Mariani, Christelle Laganot, Laetitia Jeancolas, Jonas Ihle, Farid Ichou, Élodie Hainque, Marie Odile Habert, David Grabli, Manon Gomes, Rahul Gaurav, Cécile Gallea, Carole Dongmo-Kenfack, Pauline Dodet, Bertrand Degos, Virginie Czernecki, Jean Christophe Corvol, Florence Cormier-Dequaire, Benoit Colsch, Alizé Chalançon, Alexis Brice, Eve Benchetrit, Samir Bekadar, NCER-PD Consortium, Anne-Marie Hanff, ICEBERG study group
*Corresponding author for this work

Research output: Contribution to journalArticleAcademicpeer-review

Abstract

Cognitive impairment is a frequent complication of Parkinson’s disease (PD), affecting up to half of newly diagnosed patients. To improve early detection and risk assessment, we developed machine learning models using clinical data from three independent PD cohorts, which are (LuxPARK, PPMI, ICEBERG). Models were trained to predict mild cognitive impairment (PD-MCI) and subjective cognitive decline (SCD) using Explainable Artificial Intelligence (XAI) for classification and time-to-event analysis. Multi-cohort models showed greater performance stability over single-cohort models, while retaining competitive average performance. Age at diagnosis and visuospatial ability were identified as key predictors. Significant sex differences observed highlight the importance of considering sex-specific factors in cognitive assessment. Men were more likely to report SCD. Our findings highlight the potential of multi-cohort machine learning for early identification and personalized management of cognitive decline in PD.
Original languageEnglish
Article number482
Journalnpj Digital Medicine
Volume8
Issue number1
DOIs
Publication statusPublished - 1 Dec 2025

Fingerprint

Dive into the research topics of 'Multi-cohort machine learning identifies predictors of cognitive impairment in Parkinson’s disease'. Together they form a unique fingerprint.

Cite this