CoChat

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

Open access
Loo, Rebecca Ting Jiin, Pavelka, Lukas, Mangone, Graziella, Khoury, Fouad, Vidailhet, Marie, Corvol, Jean-Christophe, Glaab, Enrico, On behalf of the NCER-PD Consortium, Acharya, Geeta, Aguayo, Gloria, Alexandre, Myriam, Ali, Muhammad, Ammerlann, Wim, Arena, Giuseppe, Bassis, Michele, Batutu, Roxane, Beaumont, Katy, Béchet, Sibylle, Berchem, Guy, Bisdorff, Alexandre, Boussaad, Ibrahim, Bouvier, David, Castillo, Lorieza, Contesotto, Gessica, De Bremaeker, Nancy, Dewitt, Brian, Diederich, Nico, Dondelinger, Rene, Ramia, Nancy E., Uribe, Maria Fernanda Niño, Ferrari, Angelo, Lopes, Ana Festas, Frauenknecht, Katrin, Fritz, Joëlle, Gamio, Carlos, Gantenbein, Manon, Gawron, Piotr, Georges, Laura, Ghosh, Soumyabrata, Giraitis, Marijus, Glaab, Enrico, Goergen, Martine, De Lope, Elisa Gómez, Graas, Jérôme, Graziano, Mariella, Groues, Valentin, Grünewald, Anne, Hammot, Gaël, Hanff, Anne-Marie, Hansen, Linda, Heneka, Michael, Henry, Estelle, Henry, Margaux, Herbrink, Sylvia, Herzinger, Sascha, Hundt, Alexander, Jacoby, Nadine, Jónsdóttir, Sonja, Klucken, Jochen, Kofanova, Olga, Krüger, Rejko, Lambert, Pauline, Landoulsi, Zied, Lentz, Roseline, Lorentz, Victoria, Marques, Tainá M., Marques, Guilherme, Conde, Patricia Martins, May, Patrick, Mcintyre, Deborah, Mediouni, Chouaib, Meisch, Francoise, Mendibide, Alexia, Menster, Myriam, Minelli, Maura, Mittelbronn, Michel, Mtimet, Saïda, Munsch, Maeva, Nati, Romain, Nehrbass, Ulf, Nickels, Sarah, Nicolai, Beatrice, Nicolay, Jean-Paul, Noor, Fozia, Gomes, Clarissa P. C., Pachchek, Sinthuja, Pauly, Claire, Pauly, Laure, Pavelka, Lukas, Perquin, Magali, Pexaras, Achilleas, Rauschenberger, Armin, Rawal, Rajesh, Bobbili, Dheeraj Reddy, Remark, Lucie, Richard, Ilsé, Roland, Olivia, Roomp, Kirsten, Rosales, Eduardo, Sapienza, Stefano, Satagopam, Venkata, Schmitz, Sabine, Schneider, Reinhard, Schwamborn, Jens, Severino, Raquel, Sharify, Amir, Soare, Ruxandra, Soboleva, Ekaterina, Sokolowska, Kate, Theresine, Maud, Thien, Hermann, Thiry, Elodie, Loo, Rebecca Ting Jiin, Trouet, Johanna, Tsurkalenko, Olena, Vaillant, Michel, Vega, Carlos, Boas, Liliana Vilas, Wilmes, Paul, Wollscheid-Lengeling, Evi, Zelimkhanov, Gelani, the ICEBERG study group, Marie-Alexandrine, Arnulf, Isabelle, Bekadar, Samir, Benchetrit, Eve, Brice, Alexis, Chalançon, Alizé, Colsch, Benoit, Cormier-Dequaire, Florence, Corvol, Jean-Christophe, Czernecki, Virginie, Degos, Bertrand, Dodet, Pauline, Dongmo-Kenfack, Carole, Gallea, Cécile, Gaurav, Rahul, Gomes, Manon, Grabli, David, Habert, Marie-Odile, Hainque, Élodie, Ichou, Farid, Ihle, Jonas, Jeancolas, Laetitia, Laganot, Christelle, Mariani, Louise Laure, Lé, Mickaël, Lehéricy, Stéphane, Lesage, Suzanne, Semenescu, Smaranda Leu, Levy, Richard, Maheo, Valentine, Mangone, Graziella, Menon, Poornima, Mochel, Fanny, Perlbarg, Vincent, Petrovska, Dijana, Pineau, Fanny, Pyatigorskaya, Nadya, Rivaud-Péchoux, Sophie, Sambin, Sara, Socha, Julie, Tenenhaus, Arthur, Valabregue, Romain, Vidailhet, Marie, Weill, Caroline, Yahia-Cherif, Lydia · 2025 · npj Digital Medicine

The DOI matches its Crossref record; 95 of the 95 references it cites were found in a registry or an index.

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.

Overview

The claims and statistics of this paper haven’t been checked yet.

Free: it reads the open-access text and checks the first 5 claims that cite a source we can check. Create a free account to check every claim.

A few free checks a day · papers already verified open instantly · results are public

Integrity signals

Registry

Crossref · 10.1038/s41746-025-01862-1

Cites

95 of 95 references verified0 citation errors · 0 not checkable

Statistics

Figures

Fig. 1 SHAP value plot revealing key predictors’ influence on PD-MCI classification in the cross-cohort analysis. Each row shows a predictor’s impact on mild cognitive impairment (PD-MCI) classification, with SHAP values indicating the direction and magnitude of effect. Points represent individual patients, with colors indicating the predictor’s value (red = high, blue = low). Positive SHAP values (right side) indicate increased likelihood of PD-MCI, while negative values (left side) suggest decreased likelihood. The Benton Judgment of Line Orientation score shows the strongest effect, with lower scores (blue) associated with increased PD-MCI risk. Age at PD diagnosis demonstrates the second strongest impact, with later onset (red) correlating with higher PD-MCI probability. Additional predictors include MDS-UPDRS subscores (Parts II, IV, and I) and weight, each showing varying degrees of influence on cognitive impairment classification.
Fig. 1 SHAP value plot revealing key predictors’ influence on PD-MCI classification in the cross-cohort analysis. Each row shows a predictor’s impact on mild cognitive impairment (PD-MCI) classification, with SHAP values indicating the direction and magnitude of effect. Points represent individual patients, with colors indicating the predictor’s value (red = high, blue = low). Positive SHAP values (right side) indicate increased likelihood of PD-MCI, while negative values (left side) suggest decreased likelihood. The Benton Judgment of Line Orientation score shows the strongest effect, with lower scores (blue) associated with increased PD-MCI risk. Age at PD diagnosis demonstrates the second strongest impact, with later onset (red) correlating with higher PD-MCI probability. Additional predictors include MDS-UPDRS subscores (Parts II, IV, and I) and weight, each showing varying degrees of influence on cognitive impairment classification.CC BY · PubMed Central
Fig. 2 SHAP value plot revealing key predictors’ influence on SCD classification in the cross-cohort analysis. Each row shows a predictor’s impact on subjective cognitive decline (SCD) classification, with SHAP values indicating the direction and magnitude of effect. Points represent individual patients, with colors indicating the predictor’s value (red = high, blue = low). Positive SHAP values (right side) indicate increased likelihood of SCD, while negative values (left side) suggest decreased likelihood. The MDS-UPDRS Part I score shows the strongest effect, with higher scores (red) associated with increased SCD risk. Age at PD diagnosis demonstrates the second strongest impact, with later onset (red) correlating with higher SCD probability.
Fig. 2 SHAP value plot revealing key predictors’ influence on SCD classification in the cross-cohort analysis. Each row shows a predictor’s impact on subjective cognitive decline (SCD) classification, with SHAP values indicating the direction and magnitude of effect. Points represent individual patients, with colors indicating the predictor’s value (red = high, blue = low). Positive SHAP values (right side) indicate increased likelihood of SCD, while negative values (left side) suggest decreased likelihood. The MDS-UPDRS Part I score shows the strongest effect, with higher scores (red) associated with increased SCD risk. Age at PD diagnosis demonstrates the second strongest impact, with later onset (red) correlating with higher SCD probability.CC BY · PubMed Central
Fig. 3 Forest plot of median conversion times (years) and hazard ratios for key predictors of time-to-PD-MCI in the cross-cohort analysis. Forest plot showing the relationship between two key predictors (Benton Judgment of Line Orientation score and age at PD diagnosis) and the development of mild cognitive impairment (PD-MCI). The left panel displays median conversion times with 95% confidence intervals (CIs), stratified by predictor thresholds (≥16 vs <16 for Benton score; ≥53 vs <53 years for age at PD diagnosis). Solid blue lines indicate statistically significant differences between groups (p-value < 0.05), while grey lines indicate non-significant differences. The right panel shows corresponding hazard ratios (HR) with 95% CIs, where HR greater than 1 indicate increased risk of PD-MCI for the higher category compared to the reference group (lower category). For age at PD diagnosis, patients diagnosed at ≥53 years show significantly higher risk of developing PD-MCI compared to those diagnosed earlier.
Fig. 3 Forest plot of median conversion times (years) and hazard ratios for key predictors of time-to-PD-MCI in the cross-cohort analysis. Forest plot showing the relationship between two key predictors (Benton Judgment of Line Orientation score and age at PD diagnosis) and the development of mild cognitive impairment (PD-MCI). The left panel displays median conversion times with 95% confidence intervals (CIs), stratified by predictor thresholds (≥16 vs <16 for Benton score; ≥53 vs <53 years for age at PD diagnosis). Solid blue lines indicate statistically significant differences between groups (p-value < 0.05), while grey lines indicate non-significant differences. The right panel shows corresponding hazard ratios (HR) with 95% CIs, where HR greater than 1 indicate increased risk of PD-MCI for the higher category compared to the reference group (lower category). For age at PD diagnosis, patients diagnosed at ≥53 years show significantly higher risk of developing PD-MCI compared to those diagnosed earlier.CC BY · PubMed Central
Fig. 4 Forest plot of time-to-SCD predictors showing median conversion times (years) and hazard ratios in the cross-cohort analysis. The plot illustrates how multiple clinical predictors affect subjective cognitive decline (SCD). The left panel shows median time to SCD onset with 95% confidence intervals (CIs), comparing subgroups for each predictor. Solid blue lines indicate statistically significant differences between groups (p-value < 0.05), while grey lines indicate non-significant differences. Key predictors include MDS-UPDRS Part I score (≥12 vs <12), postural abnormalities, tremor characteristics, and age at PD diagnosis (≥62 vs <62 years). The right panel displays corresponding hazard ratios (HR) with 95% CIs, where values > 1 indicate increased risk. Notable findings include a significantly higher SCD risk for patients diagnosed after age 62 and those with higher MDS-UPDRS Part I scores. Some features such as sleep problems and REM sleep behavior disorder show wider confidence intervals, suggesting more uncertainty in their predictive value.
Fig. 4 Forest plot of time-to-SCD predictors showing median conversion times (years) and hazard ratios in the cross-cohort analysis. The plot illustrates how multiple clinical predictors affect subjective cognitive decline (SCD). The left panel shows median time to SCD onset with 95% confidence intervals (CIs), comparing subgroups for each predictor. Solid blue lines indicate statistically significant differences between groups (p-value < 0.05), while grey lines indicate non-significant differences. Key predictors include MDS-UPDRS Part I score (≥12 vs <12), postural abnormalities, tremor characteristics, and age at PD diagnosis (≥62 vs <62 years). The right panel displays corresponding hazard ratios (HR) with 95% CIs, where values > 1 indicate increased risk. Notable findings include a significantly higher SCD risk for patients diagnosed after age 62 and those with higher MDS-UPDRS Part I scores. Some features such as sleep problems and REM sleep behavior disorder show wider confidence intervals, suggesting more uncertainty in their predictive value.CC BY · PubMed Central
Fig. 5 Machine learning pipeline for predicting cognitive impairment in Parkinson’s disease. Machine learning analysis pipeline for predicting cognitive impairment in Parkinson’s Disease. Schematic representation of the data processing and analysis workflow. Input data from three independent cohorts (LuxPARK, PPMI, and ICEBERG) is pre-processed and then analyzed using both single-cohort and multi-cohort approaches. These analyses are applied to predict both mild cognitive impairment (PD-MCI) and subjective cognitive decline (SCD) outcomes in Parkinson’s disease. The models are evaluated using cross-validation, decision curve and calibration analyses.
Fig. 5 Machine learning pipeline for predicting cognitive impairment in Parkinson’s disease. Machine learning analysis pipeline for predicting cognitive impairment in Parkinson’s Disease. Schematic representation of the data processing and analysis workflow. Input data from three independent cohorts (LuxPARK, PPMI, and ICEBERG) is pre-processed and then analyzed using both single-cohort and multi-cohort approaches. These analyses are applied to predict both mild cognitive impairment (PD-MCI) and subjective cognitive decline (SCD) outcomes in Parkinson’s disease. The models are evaluated using cross-validation, decision curve and calibration analyses.CC BY · PubMed Central

Verification

Claims the paper makes

The claims and statistics of this paper haven’t been checked yet.

Free: it reads the open-access text and checks the first 5 claims that cite a source we can check. Create a free account to check every claim.

A few free checks a day · papers already verified open instantly · results are public

Claims other papers make about this one

Each is checked against this paper’s own text: does it say what the citing paper says it does?

Self-check

Percentages, sums and reported differences re-computed from the paper’s own numbers.

The self-check needs the paper’s full text.

Citations

Cites

Show all 95 references

Research works printed but not linked: 5

  1. van Buuren, S. & Groothuis-Oudshoorn, K. mice: Multivariate Imputation by Chained Equations in R. J. Stat. Soft. 45, 1–67 (2011). · DOI · Paper page
  2. Freund, Y. & Schapire, R. A short introduction to boosting. J. Jpn. Soc. Artif. 14, 1612 (1999).
  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).
  4. 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).
  5. Lundberg, S. M. & Lee, S.-I. A unified approach to interpreting model predictions. In Neural Information Processing Systems (NIPS 2017) 4768–4777 (NIPS, 2017).

Cited by

See all 9

Metadata

Authors
Loo, R. T. J., Pavelka, L., Mangone, G., Khoury, F., Vidailhet, M., Corvol, J.-C., Glaab, E., On behalf of the NCER-PD Consortium, Acharya, G., Aguayo, G., Alexandre, M., Ali, M., Ammerlann, W., Arena, G., Bassis, M., Batutu, R., Beaumont, K., Béchet, S., Berchem, G., Bisdorff, A., Boussaad, I., Bouvier, D., Castillo, L., Contesotto, G., De Bremaeker, N., Dewitt, B., Diederich, N., Dondelinger, R., Ramia, N. E., Uribe, M. F. N., Ferrari, A., Lopes, A. F., Frauenknecht, K., Fritz, J., Gamio, C., Gantenbein, M., Gawron, P., Georges, L., Ghosh, S., Giraitis, M., Glaab, E., Goergen, M., De Lope, E. G., Graas, J., Graziano, M., Groues, V., Grünewald, A., Hammot, G., Hanff, A.-M., Hansen, L., Heneka, M., Henry, E., Henry, M., Herbrink, S., Herzinger, S., Hundt, A., Jacoby, N., Jónsdóttir, S., Klucken, J., Kofanova, O., Krüger, R., Lambert, P., Landoulsi, Z., Lentz, R., Lorentz, V., Marques, T. M., Marques, G., Conde, P. M., May, P., Mcintyre, D., Mediouni, C., Meisch, F., Mendibide, A., Menster, M., Minelli, M., Mittelbronn, M., Mtimet, S., Munsch, M., Nati, R., Nehrbass, U., Nickels, S., Nicolai, B., Nicolay, J.-P., Noor, F., Gomes, C. P. C., Pachchek, S., Pauly, C., Pauly, L., Pavelka, L., Perquin, M., Pexaras, A., Rauschenberger, A., Rawal, R., Bobbili, D. R., Remark, L., Richard, I., Roland, O., Roomp, K., Rosales, E., Sapienza, S., Satagopam, V., Schmitz, S., Schneider, R., Schwamborn, J., Severino, R., Sharify, A., Soare, R., Soboleva, E., Sokolowska, K., Theresine, M., Thien, H., Thiry, E., Loo, R. T. J., Trouet, J., Tsurkalenko, O., Vaillant, M., Vega, C., Boas, L. V., Wilmes, P., Wollscheid-Lengeling, E., Zelimkhanov, G., the ICEBERG study group, Marie-Alexandrine, Arnulf, I., Bekadar, S., Benchetrit, E., Brice, A., Chalançon, A., Colsch, B., Cormier-Dequaire, F., Corvol, J.-C., Czernecki, V., Degos, B., Dodet, P., Dongmo-Kenfack, C., Gallea, C., Gaurav, R., Gomes, M., Grabli, D., Habert, M.-O., Hainque, É., Ichou, F., Ihle, J., Jeancolas, L., Laganot, C., Mariani, L. L., Lé, M., Lehéricy, S., Lesage, S., Semenescu, S. L., Levy, R., Maheo, V., Mangone, G., Menon, P., Mochel, F., Perlbarg, V., Petrovska, D., Pineau, F., Pyatigorskaya, N., Rivaud-Péchoux, S., Sambin, S., Socha, J., Tenenhaus, A., Valabregue, R., Vidailhet, M., Weill, C., & Yahia-Cherif, L.
Affiliations
  • Centre National de la Recherche Scientifique (FR)
  • University of Luxembourg (LU)
  • Centre Hospitalier de Luxembourg (LU)
  • Luxembourg Institute of Health (LU)
  • Laboratoire National de Santé (LU)
  • Pitié-Salpêtrière Hospital (FR)
  • Hôpital de la Timone (FR)
  • Institut du Cerveau (FR)
  • Commissariat à l'Énergie Atomique et aux Énergies Alternatives (FR)
  • Hôpital Avicenne (FR)
  • Télécom SudParis (FR)
Venue
npj Digital Medicine
Published
2025-07-26
Volume
8
Issue
1
Pages
482-482
ISSN
2398-6352 (ISSN-L)
OpenAlex
W4412659465
Cited by
9
References
92
Citations by year
2026: 9
FWCI
5.48
Type
journal article
Language
en
Open access
Licence
Locations
  • npj Digital Medicine (publishedVersion, cc-by)
  • PubMed Central (publishedVersion, cc-by)
  • PubMed (publishedVersion)
  • Research Publications (Maastricht University) (publishedVersion, cc-by)
  • Open Repository and Bibliography (University of Luxembourg) (submittedVersion, cc-by)
  • DOAJ (DOAJ: Directory of Open Access Journals) (submittedVersion, cc-by-sa)
Funders
Fonds National de la Recherche Luxembourg (INTER/EJP RD22/17027921/PreDYT)
Topics
  • Health Sciences › Medicine › Clinical Neurology › Parkinson's Disease Mechanisms and Treatments
  • Health Sciences › Medicine › Psychiatry and Mental health › Dementia and Cognitive Impairment Research
  • Health Sciences › Health Professions › Health Information Management › Artificial Intelligence in Healthcare
Keywords
Parkinson's disease, cognitive impairment, mild cognitive impairment, subjective cognitive decline, explainable AI, risk prediction, age at diagnosis, visuospatial ability, sex differences, early detection of cognitive decline

About these checks

Registry, retraction, Cites and statistics results are computed, not judged, with one exception: a printed reference that no index lists is read once by a model before it counts as a citation error. Claims are extracted by a model and kept only when their quote appears verbatim in the text; each cited source is then checked, with a model’s help, for whether it says what the claim relies on. Those verdicts can be wrong — read the claim’s quote and the cited source before relying on one.

Statistics and arithmetic are recomputed, not judged.

Confidence bands are shown only for fields calibrated on our annotated test set. None is calibrated yet, so no band is shown.

What counts as a claim ›How we measure confidence ›How we check this ›

Are you an author, or do you see a problem with this page? Request a review

How to cite

Cite CoChat for the checks on this page, and the paper for its own findings.

This page
CoChat. (2026). Citation check: Multi-cohort machine learning identifies predictors of cognitive impairment in Parkinson’s disease. https://app.cochat.ai/papers/10.1038/s41746-025-01862-1
The paper
Loo, R. T. J., Pavelka, L., Mangone, G., Khoury, F., Vidailhet, M., Corvol, J.-C., Glaab, E., On behalf of the NCER-PD Consortium, Acharya, G., Aguayo, G., Alexandre, M., Ali, M., Ammerlann, W., Arena, G., Bassis, M., Batutu, R., Beaumont, K., Béchet, S., Berchem, G., . . . Yahia-Cherif, L. (2025). Multi-cohort machine learning identifies predictors of cognitive impairment in Parkinson’s disease. npj Digital Medicine. https://doi.org/10.1038/s41746-025-01862-1

Data sources

Bibliographic data: Semantic Scholar, OpenAlex, Crossref.

Contains information from the Semantic Scholar Academic Graph Datasets, made available under the ODC Attribution License (ODC-BY 1.0).

Semantic Scholar’s data is described in: Kinney, R., et al. (2023). The Semantic Scholar Open Data Platform. arXiv:2301.10140.