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

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...

Full description

Saved in:
Bibliographic Details
Main Authors: Rebecca Ting Jiin Loo, Lukas Pavelka, Graziella Mangone, Fouad Khoury, Marie Vidailhet, Jean-Christophe Corvol, Enrico Glaab, On behalf of the NCER-PD Consortium
Format: Article
Language:English
Published: Nature Portfolio 2025-07-01
Series:npj Digital Medicine
Online Access:https://doi.org/10.1038/s41746-025-01862-1
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1849341600513130496
author Rebecca Ting Jiin Loo
Lukas Pavelka
Graziella Mangone
Fouad Khoury
Marie Vidailhet
Jean-Christophe Corvol
Enrico Glaab
On behalf of the NCER-PD Consortium
author_facet Rebecca Ting Jiin Loo
Lukas Pavelka
Graziella Mangone
Fouad Khoury
Marie Vidailhet
Jean-Christophe Corvol
Enrico Glaab
On behalf of the NCER-PD Consortium
author_sort Rebecca Ting Jiin Loo
collection DOAJ
description 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.
format Article
id doaj-art-4335af89da084639b99c8a2ca1c22d91
institution Kabale University
issn 2398-6352
language English
publishDate 2025-07-01
publisher Nature Portfolio
record_format Article
series npj Digital Medicine
spelling doaj-art-4335af89da084639b99c8a2ca1c22d912025-08-20T03:43:36ZengNature Portfolionpj Digital Medicine2398-63522025-07-018111210.1038/s41746-025-01862-1Multi-cohort machine learning identifies predictors of cognitive impairment in Parkinson’s diseaseRebecca Ting Jiin Loo0Lukas Pavelka1Graziella Mangone2Fouad Khoury3Marie Vidailhet4Jean-Christophe Corvol5Enrico Glaab6On behalf of the NCER-PD ConsortiumBiomedical Data Science Group, Luxembourg Centre for Systems Biomedicine (LCSB), University of LuxembourgTransversal Translational Medicine, Luxembourg Institute of Health (LIH)Sorbonne Université, Paris Brain Institute - ICM, Inserm, CNRS, Assistance Publique Hôpitaux de Paris, Pitié-Salpêtrière Hospital, Department of NeurologySorbonne Université, Paris Brain Institute - ICM, Inserm, CNRS, Assistance Publique Hôpitaux de Paris, Pitié-Salpêtrière Hospital, Department of NeurologySorbonne Université, Paris Brain Institute - ICM, Inserm, CNRS, Assistance Publique Hôpitaux de Paris, Pitié-Salpêtrière Hospital, Department of NeurologySorbonne Université, Paris Brain Institute - ICM, Inserm, CNRS, Assistance Publique Hôpitaux de Paris, Pitié-Salpêtrière Hospital, Department of NeurologyBiomedical Data Science Group, Luxembourg Centre for Systems Biomedicine (LCSB), University of LuxembourgAbstract 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.https://doi.org/10.1038/s41746-025-01862-1
spellingShingle Rebecca Ting Jiin Loo
Lukas Pavelka
Graziella Mangone
Fouad Khoury
Marie Vidailhet
Jean-Christophe Corvol
Enrico Glaab
On behalf of the NCER-PD Consortium
Multi-cohort machine learning identifies predictors of cognitive impairment in Parkinson’s disease
npj Digital Medicine
title Multi-cohort machine learning identifies predictors of cognitive impairment in Parkinson’s disease
title_full Multi-cohort machine learning identifies predictors of cognitive impairment in Parkinson’s disease
title_fullStr Multi-cohort machine learning identifies predictors of cognitive impairment in Parkinson’s disease
title_full_unstemmed Multi-cohort machine learning identifies predictors of cognitive impairment in Parkinson’s disease
title_short Multi-cohort machine learning identifies predictors of cognitive impairment in Parkinson’s disease
title_sort multi cohort machine learning identifies predictors of cognitive impairment in parkinson s disease
url https://doi.org/10.1038/s41746-025-01862-1
work_keys_str_mv AT rebeccatingjiinloo multicohortmachinelearningidentifiespredictorsofcognitiveimpairmentinparkinsonsdisease
AT lukaspavelka multicohortmachinelearningidentifiespredictorsofcognitiveimpairmentinparkinsonsdisease
AT graziellamangone multicohortmachinelearningidentifiespredictorsofcognitiveimpairmentinparkinsonsdisease
AT fouadkhoury multicohortmachinelearningidentifiespredictorsofcognitiveimpairmentinparkinsonsdisease
AT marievidailhet multicohortmachinelearningidentifiespredictorsofcognitiveimpairmentinparkinsonsdisease
AT jeanchristophecorvol multicohortmachinelearningidentifiespredictorsofcognitiveimpairmentinparkinsonsdisease
AT enricoglaab multicohortmachinelearningidentifiespredictorsofcognitiveimpairmentinparkinsonsdisease
AT onbehalfofthencerpdconsortium multicohortmachinelearningidentifiespredictorsofcognitiveimpairmentinparkinsonsdisease