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

NCER-PD Consortium; the ICEBERG study group

doi:10.1038/s41746-025-01862-1

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

NCER-PD Consortium
, the ICEBERG study group

Research output: Contribution to journal › Article › peer-review

2 Scopus citations

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 language	English
Article number	482
Journal	npj Digital Medicine
Volume	8
Issue number	1
DOIs	https://doi.org/10.1038/s41746-025-01862-1
State	Published - Dec 2025

Access to Document

10.1038/s41746-025-01862-1

Cite this

@article{9283f6d97bfe42979e0b7a648cff8d9a,

title = "Multi-cohort machine learning identifies predictors of cognitive impairment in Parkinson{\textquoteright}s disease",

abstract = "Cognitive impairment is a frequent complication of Parkinson{\textquoteright}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.",

author = "\{NCER-PD Consortium\} and \{the ICEBERG study group\} and Loo, \{Rebecca Ting Jiin\} and Lukas Pavelka and Graziella Mangone and Fouad Khoury and Marie Vidailhet and Corvol, \{Jean Christophe\} and Enrico Glaab and Lydia Yahia-Cherif and Caroline Weill and Marie Vidailhet and Romain Valabregue and Arthur Tenenhaus and Julie Socha and Sara Sambin and Sophie Rivaud-P{\'e}choux and Nadya Pyatigorskaya and Fanny Pineau and Dijana Petrovska and Vincent Perlbarg and Fanny Mochel and Poornima Menon and Graziella Mangone and Valentine Maheo and Richard Levy and Semenescu, \{Smaranda Leu\} and Suzanne Lesage and St{\'e}phane Leh{\'e}ricy and Micka{\"e}l L{\'e} and Mariani, \{Louise Laure\} and Christelle Laganot and Laetitia Jeancolas and Jonas Ihle and Farid Ichou and {\'E}lodie Hainque and Habert, \{Marie Odile\} and David Grabli and Manon Gomes and Rahul Gaurav and C{\'e}cile Gallea and Carole Dongmo-Kenfack and Pauline Dodet and Bertrand Degos and Virginie Czernecki and Corvol, \{Jean Christophe\} and Florence Cormier-Dequaire and Benoit Colsch and Aliz{\'e} Chalan{\c c}on and Alexis Brice and Eve Benchetrit and Samir Bekadar and Isabelle Arnulf and Marie-Alexandrine and Gelani Zelimkhanov and Evi Wollscheid-Lengeling and Paul Wilmes and Boas, \{Liliana Vilas\} and Carlos Vega and Michel Vaillant and Olena Tsurkalenko and Johanna Trouet and Loo, \{Rebecca Ting Jiin\} and Elodie Thiry and Hermann Thien and Maud Theresine and Kate Sokolowska and Ekaterina Soboleva and Ruxandra Soare and Amir Sharify and Raquel Severino and Jens Schwamborn and Reinhard Schneider and Sabine Schmitz and Venkata Satagopam and Stefano Sapienza and Eduardo Rosales and Kirsten Roomp and Olivia Roland and Ils{\'e} Richard and Lucie Remark and Bobbili, \{Dheeraj Reddy\} and Rajesh Rawal and Armin Rauschenberger and Achilleas Pexaras and Magali Perquin and Lukas Pavelka and Laure Pauly and Claire Pauly and Sinthuja Pachchek and Gomes, \{Clarissa P.C.\} and Fozia Noor and Nicolay, \{Jean Paul\} and Beatrice Nicolai and Sarah Nickels and Ulf Nehrbass and Romain Nati and Maeva Munsch and Sa{\"i}da Mtimet and Michel Mittelbronn and Maura Minelli and Myriam Menster and Alexia Mendibide and Francoise Meisch and Chouaib Mediouni and Deborah Mcintyre and Patrick May and Conde, \{Patricia Martins\} and Guilherme Marques and Marques, \{Tain{\'a} M.\} and Victoria Lorentz and Roseline Lentz and Zied Landoulsi and Pauline Lambert and Rejko Kr{\"u}ger and Olga Kofanova and Jochen Klucken and Sonja J{\'o}nsd{\'o}ttir and Nadine Jacoby and Alexander Hundt and Sascha Herzinger and Sylvia Herbrink and Margaux Henry and Estelle Henry and Michael Heneka and Linda Hansen and Hanff, \{Anne Marie\} and Ga{\"e}l Hammot and Anne Gr{\"u}newald and Valentin Groues and Mariella Graziano and J{\'e}r{\^o}me Graas and \{De Lope\}, \{Elisa G{\'o}mez\} and Martine Goergen and Enrico Glaab and Marijus Giraitis and Soumyabrata Ghosh and Laura Georges and Piotr Gawron and Manon Gantenbein and Carlos Gamio and Jo{\"e}lle Fritz and Katrin Frauenknecht and Lopes, \{Ana Festas\} and Angelo Ferrari and Uribe, \{Maria Fernanda Ni{\~n}o\} and Ramia, \{Nancy E.\} and Rene Dondelinger and Nico Diederich and Brian Dewitt and \{De Bremaeker\}, Nancy and Gessica Contesotto and Lorieza Castillo and David Bouvier and Ibrahim Boussaad and Alexandre Bisdorff and Guy Berchem and Sibylle B{\'e}chet and Katy Beaumont and Roxane Batutu and Michele Bassis and Giuseppe Arena and Wim Ammerlann and Muhammad Ali and Myriam Alexandre and Gloria Aguayo and Geeta Acharya",

note = "Publisher Copyright: {\textcopyright} The Author(s) 2025.",

year = "2025",

month = dec,

doi = "10.1038/s41746-025-01862-1",

language = "English",

volume = "8",

journal = "npj Digital Medicine",

issn = "2398-6352",

number = "1",

}

TY - JOUR

T1 - Multi-cohort machine learning identifies predictors of cognitive impairment in Parkinson’s disease

AU - NCER-PD Consortium

AU - the ICEBERG study group

AU - Loo, Rebecca Ting Jiin

AU - Pavelka, Lukas

AU - Mangone, Graziella

AU - Khoury, Fouad

AU - Vidailhet, Marie

AU - Corvol, Jean Christophe

AU - Glaab, Enrico

AU - Yahia-Cherif, Lydia

AU - Weill, Caroline

AU - Vidailhet, Marie

AU - Valabregue, Romain

AU - Tenenhaus, Arthur

AU - Socha, Julie

AU - Sambin, Sara

AU - Rivaud-Péchoux, Sophie

AU - Pyatigorskaya, Nadya

AU - Pineau, Fanny

AU - Petrovska, Dijana

AU - Perlbarg, Vincent

AU - Mochel, Fanny

AU - Menon, Poornima

AU - Mangone, Graziella

AU - Maheo, Valentine

AU - Levy, Richard

AU - Semenescu, Smaranda Leu

AU - Lesage, Suzanne

AU - Lehéricy, Stéphane

AU - Lé, Mickaël

AU - Mariani, Louise Laure

AU - Laganot, Christelle

AU - Jeancolas, Laetitia

AU - Ihle, Jonas

AU - Ichou, Farid

AU - Hainque, Élodie

AU - Habert, Marie Odile

AU - Grabli, David

AU - Gomes, Manon

AU - Gaurav, Rahul

AU - Gallea, Cécile

AU - Dongmo-Kenfack, Carole

AU - Dodet, Pauline

AU - Degos, Bertrand

AU - Czernecki, Virginie

AU - Corvol, Jean Christophe

AU - Cormier-Dequaire, Florence

AU - Colsch, Benoit

AU - Chalançon, Alizé

AU - Brice, Alexis

AU - Benchetrit, Eve

AU - Bekadar, Samir

AU - Arnulf, Isabelle

AU - Marie-Alexandrine,

AU - Zelimkhanov, Gelani

AU - Wollscheid-Lengeling, Evi

AU - Wilmes, Paul

AU - Boas, Liliana Vilas

AU - Vega, Carlos

AU - Vaillant, Michel

AU - Tsurkalenko, Olena

AU - Trouet, Johanna

AU - Loo, Rebecca Ting Jiin

AU - Thiry, Elodie

AU - Thien, Hermann

AU - Theresine, Maud

AU - Sokolowska, Kate

AU - Soboleva, Ekaterina

AU - Soare, Ruxandra

AU - Sharify, Amir

AU - Severino, Raquel

AU - Schwamborn, Jens

AU - Schneider, Reinhard

AU - Schmitz, Sabine

AU - Satagopam, Venkata

AU - Sapienza, Stefano

AU - Rosales, Eduardo

AU - Roomp, Kirsten

AU - Roland, Olivia

AU - Richard, Ilsé

AU - Remark, Lucie

AU - Bobbili, Dheeraj Reddy

AU - Rawal, Rajesh

AU - Rauschenberger, Armin

AU - Pexaras, Achilleas

AU - Perquin, Magali

AU - Pavelka, Lukas

AU - Pauly, Laure

AU - Pauly, Claire

AU - Pachchek, Sinthuja

AU - Gomes, Clarissa P.C.

AU - Noor, Fozia

AU - Nicolay, Jean Paul

AU - Nicolai, Beatrice

AU - Nickels, Sarah

AU - Nehrbass, Ulf

AU - Nati, Romain

AU - Munsch, Maeva

AU - Mtimet, Saïda

AU - Mittelbronn, Michel

AU - Minelli, Maura

AU - Menster, Myriam

AU - Mendibide, Alexia

AU - Meisch, Francoise

AU - Mediouni, Chouaib

AU - Mcintyre, Deborah

AU - May, Patrick

AU - Conde, Patricia Martins

AU - Marques, Guilherme

AU - Marques, Tainá M.

AU - Lorentz, Victoria

AU - Lentz, Roseline

AU - Landoulsi, Zied

AU - Lambert, Pauline

AU - Krüger, Rejko

AU - Kofanova, Olga

AU - Klucken, Jochen

AU - Jónsdóttir, Sonja

AU - Jacoby, Nadine

AU - Hundt, Alexander

AU - Herzinger, Sascha

AU - Herbrink, Sylvia

AU - Henry, Margaux

AU - Henry, Estelle

AU - Heneka, Michael

AU - Hansen, Linda

AU - Hanff, Anne Marie

AU - Hammot, Gaël

AU - Grünewald, Anne

AU - Groues, Valentin

AU - Graziano, Mariella

AU - Graas, Jérôme

AU - De Lope, Elisa Gómez

AU - Goergen, Martine

AU - Glaab, Enrico

AU - Giraitis, Marijus

AU - Ghosh, Soumyabrata

AU - Georges, Laura

AU - Gawron, Piotr

AU - Gantenbein, Manon

AU - Gamio, Carlos

AU - Fritz, Joëlle

AU - Frauenknecht, Katrin

AU - Lopes, Ana Festas

AU - Ferrari, Angelo

AU - Uribe, Maria Fernanda Niño

AU - Ramia, Nancy E.

AU - Dondelinger, Rene

AU - Diederich, Nico

AU - Dewitt, Brian

AU - De Bremaeker, Nancy

AU - Contesotto, Gessica

AU - Castillo, Lorieza

AU - Bouvier, David

AU - Boussaad, Ibrahim

AU - Bisdorff, Alexandre

AU - Berchem, Guy

AU - Béchet, Sibylle

AU - Beaumont, Katy

AU - Batutu, Roxane

AU - Bassis, Michele

AU - Arena, Giuseppe

AU - Ammerlann, Wim

AU - Ali, Muhammad

AU - Alexandre, Myriam

AU - Aguayo, Gloria

AU - Acharya, Geeta

PY - 2025/12

Y1 - 2025/12

N2 - 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.

AB - 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.

UR - https://www.scopus.com/pages/publications/105022013634

U2 - 10.1038/s41746-025-01862-1

DO - 10.1038/s41746-025-01862-1

M3 - Article

AN - SCOPUS:105022013634

SN - 2398-6352

VL - 8

JO - npj Digital Medicine

JF - npj Digital Medicine

IS - 1

M1 - 482

ER -

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

Abstract

Access to Document

Other files and links

Fingerprint

Cite this