Multi-cohort Machine Learning Identifies Predictors of Cognitive Impairment in Parkinson's Disease

Loo, R.T.J.; Pavelka, L.; Mangone, G.; Khoury, F.; Vidailhet, M.; Corvol, J.-C.; GLAAB, Enrico

doi:10.1038/s41746-025-01862-1

Request a copy

Article (Scientific journals)

Multi-cohort Machine Learning Identifies Predictors of Cognitive Impairment in Parkinson's Disease

Loo, R.T.J.; Pavelka, L.; Mangone, G. et al.

2025 • In npj Digital Medicine, in press (in press)

Peer Reviewed verified by ORBi

Permalink
https://hdl.handle.net/10993/65319

DOI
10.1038/s41746-025-01862-1

Files (1)Send to Details Statistics Bibliography Similar publications

Files

Full Text

npj_digital_medicine_pd_cognition_2025.pdf

Embargo Until 04/Jul/2026 - Author postprint (1.66 MB)

Request a copy

All documents in ORBilu are protected by a user license.

Send to

RIS BibTex APA Chicago Permalink X Linkedin

Details

Keywords :

Parkinson’s disease; Cognitive impairment; Machine learning; Multi-cohort analysis; Predictive modeling

Abstract :

[en] 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.

Research center :

Luxembourg Centre for Systems Biomedicine (LCSB): Biomedical Data Science (Glaab Group)

Disciplines :

Neurology
Human health sciences: Multidisciplinary, general & others
Biochemistry, biophysics & molecular biology
Life sciences: Multidisciplinary, general & others

Author, co-author :

Loo, R.T.J.

Pavelka, L.

Mangone, G.

Khoury, F.

Vidailhet, M.

Corvol, J.-C.

GLAAB, Enrico ; University of Luxembourg > Luxembourg Centre for Systems Biomedicine (LCSB) > Biomedical Data Science

External co-authors :

yes

Language :

English

Title :

Multi-cohort Machine Learning Identifies Predictors of Cognitive Impairment in Parkinson's Disease

Publication date :

2025

Journal title :

npj Digital Medicine

eISSN :

2398-6352

Volume :

in press

Issue :

in press

Pages :

in press

Peer reviewed :

Peer Reviewed verified by ORBi

Focus Area :

Systems Biomedicine

Development Goals :

3. Good health and well-being

FnR Project :

FNR17104370 - RECAST - Rebalancing Sleep-wake Disturbances In Parkinson's Disease With Deep Brain Stimulation, 2022 (01/07/2023-30/06/2026) - Enrico Glaab

Name of the research project :

U-AGR-7200 - INTER/22/17104370/RECAST - GLAAB Enrico

Funders :

FNR - Fonds National de la Recherche

Funding number :

NTER/22/17104370/RECAST

Available on ORBilu :

since 04 July 2025

Statistics

Number of views

125 (3 by Unilu)

Number of downloads

0 (0 by Unilu)

More statistics

Scopus citations^®

Scopus citations^®
without self-citations

OpenAlex citations

Bibliography

J. Harvey et al. Machine learning-based prediction of cognitive outcomes in de novo Parkinson’s disease npj Parkinsons Dis. 8 150
N. Kandiah et al. Montreal cognitive assessment for the screening and prediction of cognitive decline in early Parkinson’s disease Parkinsonism Relat. Disord. 20 1145 1148
H. Wilson et al. Predict cognitive decline with clinical markers in Parkinson’s disease (PRECODE-1) J. Neural Transm. 127 51 59 1:CAS:528:DC%2BC1MXisVyiurrM
A.I. Garcia-Diaz et al. Cortical thinning correlates of changes in visuospatial and visuoperceptual performance in Parkinson’s disease: a 4-year follow-up Parkinsonism Relat. Disord. 46 62 68 1:STN:280:DC%2BC1M3gslajug%3D%3D
A. Luca et al. Cognitive impairment and levodopa induced dyskinesia in Parkinson’s disease: a longitudinal study from the PACOS cohort Sci. Rep. 11 1:CAS:528:DC%2BB3MXhsVKrtb8%3D 867
T. van Laar P.P. De Deyn D. Aarsland P. Barone J.E. Galvin Effects of cholinesterase inhibitors in Parkinson’s disease dementia: a review of clinical data CNS Neurosci. Ther. 17 428 441
C. Sun M.J. Armstrong Treatment of Parkinson’s disease with cognitive impairment: current approaches and future directions Behav. Sci. 11 54
S. Bernini et al. A double-blind randomized controlled trial of the efficacy of cognitive training delivered using two different methods in mild cognitive impairment in Parkinson’s disease: preliminary report of benefits associated with the use of a computerized tool Aging Clin. Exp. Res. 33 1567 1575
E. Mantovani C. Zucchella A.A. Argyriou S. Tamburin Treatment for cognitive and neuropsychiatric non-motor symptoms in Parkinson’s disease: current evidence and future perspectives Expert Rev. Neurotherapeutics 23 25 43 1:CAS:528:DC%2BB3sXivFGrtb8%3D
T. Loetscher Cognitive training interventions for dementia and mild cognitive impairment in Parkinson’s disease - a cochrane review summary with commentary NeuroRehabilitation 48 385 387
T.C. Carlisle L.D. Medina S.K. Holden Original research: initial development of a pragmatic tool to estimate cognitive decline risk focusing on potentially modifiable factors in Parkinson’s disease Front. Neurosci. 17 1278817
L. Pavelka et al. Age at onset as stratifier in idiopathic Parkinson’s disease – effect of ageing and polygenic risk score on clinical phenotypes npj Parkinsons Dis. 8 102 1:STN:280:DC%2BB2MbpsFartw%3D%3D
S.J. Chung et al. Baseline cognitive profile is closely associated with long-term motor prognosis in newly diagnosed Parkinson’s disease J. Neurol. 268 4203 4212 1:CAS:528:DC%2BB3MXhtlKnur7I
Yıldız, Z. et al. Relationship between apathy and cognitive functions in Parkinson’s disease. Psychological Appl. Trendshttps://doi.org/10.36315/2023inpact145 (2023).
J.G. Goldman et al. Diagnosing PD-MCI by MDS Task Force criteria: how many and which neuropsychological tests? Mov. Disord. 30 402 406
F.-F. Pan L. Huang K.-L. Chen Q.-H. Zhao Q.-H. Guo A comparative study on the validations of three cognitive screening tests in identifying subtle cognitive decline BMC Neurol. 20 78
T.E.K. Cersonsky et al. Using the Montreal cognitive assessment to identify individuals with subtle cognitive decline Neuropsychology 36 373 383
K.A. Mills et al. Cognitive impairment in Parkinson’s disease: Association between patient-reported and clinically measured outcomes Parkinsonism Relat. Disord. 33 107 114
S. Rosenblum et al. The Montreal Cognitive Assessment: Is it suitable for identifying mild cognitive impairment in Parkinson’s disease? Mov. Disord. Clin. Pract. 7 648 655
S.E. Marino et al. Subjective perception of cognition is related to mood and not performance Epilepsy Behav. 14 459 464 1:STN:280:DC%2BD1M3ltlKgtQ%3D%3D
J.G. Goldman G.T. Stebbins V. Leung B.C. Tilley C.G. Goetz Relationships among cognitive impairment, sleep, and fatigue in Parkinson’s disease using the MDS-UPDRS Parkinsonism Relat. Disord. 20 1135 1139
J. Huang et al. Subjective cognitive decline in patients with Parkinson’s disease: an updated review Front. Aging Neurosci. 15 1117068
J. Ren et al. Comparing the effects of GBA variants and onset age on clinical features and progression in Parkinson’s disease CNS Neurosci. Ther. 30 1:CAS:528:DC%2BB3sXhslSlt7jI e14387
Y.-X. Wang et al. Associations between cognitive impairment and motor dysfunction in Parkinson’s disease Brain Behav. 7 e00719
M. Ikeda H. Kataoka S. Ueno Can levodopa prevent cognitive decline in patients with Parkinson’s disease? Am. J. Neurodegener. Dis. 6 9 14
R.T.J. Loo et al. Levodopa-induced dyskinesia in Parkinson’s disease: Insights from cross-cohort prognostic analysis using machine learning Parkinsonism Relat. Disord. 126 107054 1:CAS:528:DC%2BB2cXhsFels7jL
L. Pavelka et al. Luxembourg Parkinson’s study -comprehensive baseline analysis of Parkinson’s disease and atypical parkinsonism Front. Neurol. 14 1330321
K. Marek et al. The Parkinson Progression Marker Initiative (PPMI) Prog. Neurobiol. 95 629 635
P. Dodet et al. Sleep disorders in Parkinson’s disease, an early and multiple problem npj Parkinson’s Dis. 10 46
Z. Zhang et al. Effect of onset age on the levodopa threshold dosage for dyskinesia in Parkinson’s disease Neurol. Sci. 43 3165 3174
J. Ciafone B. Little A.J. Thomas P. Gallagher The neuropsychological profile of mild cognitive impairment in lewy body dementias J. Int. Neuropsychol. Soc. 26 210 225
G. Devigili et al. Unraveling autonomic dysfunction in GBA-related Parkinson’s disease Mov. Disord. Clin. Pract. 10 1620 1638
M.J. Kelly et al. Predictors of motor complications in early Parkinson’s disease: a prospective cohort study Mov. Disord. 34 1174 1183
J. Chen et al. Predictors of cognitive impairment in newly diagnosed Parkinson’s disease with normal cognition at baseline: A 5-year cohort study Front. Aging Neurosci. 15 1:CAS:528:DC%2BB3sXit1SgsbfI 1142558
R. Biundo et al. Cognitive profiling of Parkinson disease patients with mild cognitive impairment and dementia Parkinsonism Relat. Disord. 20 394 399
T. Phongpreecha et al. Multivariate prediction of dementia in Parkinson’s disease npj Parkinson’s Dis. 6 20
A. Gorji A.F. Jouzdani Machine learning for predicting cognitive decline within five years in Parkinson’s disease: comparing cognitive assessment scales with DAT SPECT and clinical biomarkers PLoS ONE 19 1:CAS:528:DC%2BB2cXitFOitb7K e0304355
G. Palermo et al. Dopamine transporter, age, and motor complications in Parkinson’s disease: a clinical and single-photon emission computed tomography study Mov. Disord. 35 1028 1036 1:CAS:528:DC%2BB3cXht1amu7zN
Y. Xiao et al. Different associated factors of subjective cognitive complaints in patients with early- and late-onset Parkinson’s disease Front. Neurol. 12 749471
F. Zhou et al. Abnormal intra- and inter-network functional connectivity of brain networks in early-onset Parkinson’s disease and late-onset Parkinson’s disease Front. Aging Neurosci. 15 1132723
M. Picillo et al. Sex-related longitudinal change of motor, non-motor, and biological features in early Parkinson’s disease J. Parkinsons Dis. 12 421 436
I. Beheshti S. Booth J.H. Ko Differences in brain aging between sexes in Parkinson’s disease npj Parkinsons Dis. 10 35
H. Iwaki et al. Differences in the presentation and progression of Parkinson’s disease by sex Mov. Disord. 36 106 117
H. Chen et al. Performance of the Benton Judgment of Line Orientation test across patients with different types of dementia J. Alzheimers Dis. 102 437 448
B. Cholerton et al. Sex differences in progression to mild cognitive impairment and dementia in Parkinson’s disease Parkinsonism Relat. Disord. 50 29 36
P. Chiara et al. Cognitive function in Parkinson’s disease: the influence of gender Basal Ganglia 3 131 135
M.C. Bakeberg et al. Differential effects of sex on longitudinal patterns of cognitive decline in Parkinson’s disease J. Neurol. 268 1903 1912
T.H. Reekes et al. Sex specific cognitive differences in Parkinson disease npj Parkinsons Dis. 6 7 1:CAS:528:DC%2BB3cXms1yqt7k%3D
H. Almgren et al. Machine learning-based prediction of longitudinal cognitive decline in early Parkinson’s disease using multimodal features Sci. Rep. 13 1:CAS:528:DC%2BB3sXhslWjtbzP 13193
S.H. Kang J. Lee S.-B. Koh Constipation is associated with mild cognitive impairment in patients with de novo Parkinson’s disease J. Mov. Disord. 15 38 42
J.D. Jones E. Rahmani E. Garcia J.P. Jacobs Gastrointestinal symptoms are predictive of trajectories of cognitive functioning in de novo Parkinson’s disease Parkinsonism Relat. Disord. 72 7 12
E.K. Tur E. Gözke Autonomic symptoms in early-stage Parkinson’s patients and their relationship with cognition and disease parameters Anatol. Curr. Med J. 5 498 502
A.V. Nagy et al. Cognitive impairment in REM-sleep behaviour disorder and individuals at risk of Parkinson’s disease Parkinsonism Relat. Disord. 109 105312 1:STN:280:DC%2BB28fnslWjtg%3D%3D
G. Maggi L. Trojano P. Barone G. Santangelo Sleep disorders and cognitive dysfunctions in Parkinson’s disease: a meta-analytic study Neuropsychol. Rev. 31 643 682
J. Cosgrove J.E. Alty S. Jamieson Cognitive impairment in Parkinson’s disease Postgrad. Med. J. 91 212 220
C.-H. Ma N. Ren J. Xu L. Chen Clinical features, plasma neurotransmitter levels and plasma neurohormone levels among patients with early-stage Parkinson’s disease with sleep disorders Cell Commun. Signal. 23 144
W.R. Gibb A.J. Lees The relevance of the Lewy body to the pathogenesis of idiopathic Parkinson’s disease J. Neurol. Neurosurg. Psychiatry 51 745 752 1:STN:280:DyaL1czgtVSqsg%3D%3D
K. Marek et al. The Parkinson’s progression markers initiative (PPMI) – establishing a PD biomarker cohort Ann. Clin. Transl. Neurol. 5 1460 1477 1:CAS:528:DC%2BC1cXisF2iu77O
S. Rosenblum S. Meyer A. Richardson S. Hassin-Baer Capturing subjective mild cognitive decline in Parkinson’s disease Brain Sci. 12 741
M.J. Azur E.A. Stuart C. Frangakis P.J. Leaf Multiple imputation by chained equations: what is it and how does it work? Int. J. Methods Psychiatr. Res. 20 40 49
S. van Buuren K. Groothuis-Oudshoorn mice: Multivariate Imputation by Chained Equations in R J. Stat. Soft. 45 1 67
J. Luo et al. A comparison of batch effect removal methods for enhancement of prediction performance using MAQC-II microarray gene expression data Pharmacogenomics J. 10 278 291 1:CAS:528:DC%2BC3cXpsFWltb8%3D
B.M. Bolstad R.A. Irizarry M. Åstrand T.P. Speed A comparison of normalization methods for high density oligonucleotide array data based on variance and bias Bioinformatics 19 185 193 1:CAS:528:DC%2BD3sXitlCnsL4%3D
D. Kostka R. Spang Microarray based diagnosis profits from better documentation of gene expression signatures PLoS Comput. Biol. 4 e22
W.E. Johnson C. Li A. Rabinovic Adjusting batch effects in microarray expression data using empirical Bayes methods Biostatistics 8 118 127
C. Chen et al. Removing batch effects in analysis of expression microarray data: an evaluation of six batch adjustment methods PLoS One 6 e17238 1:CAS:528:DC%2BC3MXjtFejsLY%3D
C. Lazar et al. Batch effect removal methods for microarray gene expression data integration: a survey Brief. Bioinform. 14 469 490
C.K. Stein et al. Removing batch effects from purified plasma cell gene expression microarrays with modified ComBat BMC Bioinforma. 16 63
M. Bach A. Werner M. Palt The proposal of undersampling method for learning from imbalanced datasets Proc. Comput. Sci. 159 125 134
G. Karami M. Giuseppe Orlando A. Delli Pizzi M. Caulo C. Del Gratta Predicting overall survival time in glioblastoma patients using gradient boosting machines algorithm and recursive feature elimination technique Cancers 13 4976
I.A. Wood P.M. Visscher K.L. Mengersen Classification based upon gene expression data: bias and precision of error rates Bioinformatics 23 1363 1370 1:CAS:528:DC%2BD2sXns1Olu7k%3D
Y. Freund R.E. Schapire A decision-theoretic generalization of on-line learning and an application to boosting J. Comput. Syst. Sci. 55 119 139
Y. Freund R. Schapire A short introduction to boosting J. Jpn. Soc. Artif. 14 1612
Berk, R. A. Classification and Regression Trees (CART). In S tatistical Learning from a Regression Perspective (ed. Berk, R. A.) 157–211 (Springer International Publishing, 2020). https://doi.org/10.1007/978-3-030-40189-4_3.
Prokhorenkova, L., Gusev, G., Vorobev, A., Dorogush, A. V. & Gulin, A. CatBoost: unbiased boosting with categorical features. In Advances in Neural Information Processing Systems ((NeurIPS, 2018).
J.R. Quinlan Improved use of continuous attributes in C4.5 J. Artif. Intell. Res. 4 77 90
Tan, Y. S. et al. Fast interpretable greedy-tree sums. Proc. Natl. Acad. Sci. U.S.A.122, e2310151122 (2025).
H. McTavish et al. Fast Sparse Decision Tree Optimization via reference ensembles AAAI 36 9604 9613
J.H. Friedman Greedy function approximation: a gradient boosting machine Ann. Stat. 29 1189 1232
Agarwal, A., Tan, Y. S., Ronen, O., Singh, C. & Yu, B. Hierarchical shrinkage: improving the accuracy and interpretability of tree-based models. In International Conference on Machine Learning 111–135 (PMLR, 2022).
Chen, T. & Guestrin, C. XGBoost: a scalable tree boosting system. In A CM SIGKDD International Conference on Knowledge Discovery and Data Mining, 785–794, https://doi.org/10.1145/2939672.2939785 (2016).
K. He et al. Component-wise gradient boosting and false discovery control in survival analysis with high-dimensional covariates Bioinformatics 32 50 57
D. Bertsimas J. Dunn E. Gibson A. Orfanoudaki Optimal survival trees Mach. Learn. 111 2951 3023
P. Geurts D. Ernst L. Wehenkel Extremely randomized trees Mach. Learn. 63 3 42
M. Wang et al. Dementia risk prediction in individuals with mild cognitive impairment: a comparison of Cox regression and machine learning models BMC Med. Res. Methodol. 22 284
M.Y. Park T. Hastie L1-regularization path algorithm for generalized linear models J. R. Stat. Soc. Ser. B Stat. Methodol. 69 659 677
N. Simon J. Friedman T. Hastie R. Tibshirani Regularization paths for Cox’s proportional hazards model via coordinate descent J. Stat. Softw. 39 1 13
H. Ishwaran U.B. Kogalur E.H. Blackstone M.S. Lauer Random survival forests Ann. Appl. Stat. 2 841 860
Lundberg, S. M. & Lee, S.-I. A unified approach to interpreting model predictions. In Neural Information Processing Systems (NIPS 2017) 4768–4777 (NIPS, 2017).
S. Sundrani J. Lu Computing the hazard ratios associated with explanatory variables using machine learning models of survival data JCO Clin. Cancer Inform. 5 364 378
X. Sun W. Xu Fast implementation of DeLong’s algorithm for comparing the areas under correlated receiver operating characteristic curves IEEE Signal Process. Lett. 21 1389 1393
L. Kang W. Chen N.A. Petrick B.D. Gallas Comparing two correlated C indices with right-censored survival outcome: a one-shot nonparametric approach Stat. Med. 34 685 703
J.A. Ferreira A.H. Zwinderman On the Benjamini–Hochberg method Ann. Stat. 34 1827 1849
G. Corani A. Benavoli A Bayesian approach for comparing cross-validated algorithms on multiple data sets Mach. Learn. 100 285 304
D. Piovani R. Sokou A.G. Tsantes A.S. Vitello S. Bonovas Optimizing clinical decision making with decision curve analysis: Insights for clinical investigators Healthcare 11 2244
Z. Zhang et al. Decision curve analysis: a technical note Ann. Transl. Med. 6 308
T.G. Trucano L.P. Swiler T. Igusa W.L. Oberkampf M. Pilch Calibration, validation, and sensitivity analysis: What’s what Reliab. Eng. Syst. Saf. 91 1331 1357
Bamber, D. Evaluation of the performance of survival analysis models: Discrimination and calibration measures. In Handbook of Statistics vol. 23 1–25 (Elsevier, 2003).