Interpretable machine learning for cognitive impairment prediction in Parkinson's disease: a multicenter validation study with SHAP analysis.

Introduction: Parkinson's disease (PD)-related cognitive impairment (PD-CI) is a common and impactful complication of PD, yet current predictive models often rely on specialized resources, lack interpretability, or have limited cross-population validation. This study aimed to develop an interpretabl...

Descripción completa

Detalles Bibliográficos
Publicado en:Frontiers in Aging Neuroscience pp. 1 - 14
Autores principales: Wang, Ziyuan, Yan, Junqiang
Formato: research tables/charts Journal Article
Publicado: Frontiers Media S.A. 2025
Acceso en línea:Ver este registro en EBSCOhost
fields @attributes:
  recordID: 1
pdfLink:
plink: https://search.ebscohost.com/login.aspx?direct=true&db=ccm&AN=189571066&site=ehost-live
header:
  @attributes:
    shortDbName: ccm
    uiTerm: 189571066
    longDbName: CINAHL Complete
    uiTag: AN
  controlInfo:
    bkinfo:
    dissinfo:
    jinfo:
      jid:
        16634365
        BG2U
      jtl: Frontiers in Aging Neuroscience
      issn: 16634365
      maglogo: N
    pubinfo:
      dt: 2025
      pid: 40038
      pub: Frontiers Media S.A.
    artinfo:
      ui:
        189571066
        189571066
        189571066
        10.3389/fnagi.2025.1688653
        189571066
      ppf: 1
      ppct: 13
      formats:
      tig:
        atl: Interpretable machine learning for cognitive impairment prediction in Parkinson's disease: a multicenter validation study with SHAP analysis.
      aug:
        au:
          Wang, Ziyuan
          Yan, Junqiang
        affil: Key Laboratory of Neuromolecular Biology, The First Affiliated Hospital, College of Clinical Medicine of Henan University of Science and Technology, Luoyang, China
      sug:
        subj:
          Machine Learning Methods
          Prediction Models Evaluation
          Cognition Disorders Risk Factors
          Parkinson Disease Complications
          Risk Assessment
          Conceptual Framework
          Human
          Multicenter Studies
          Validation Studies
          Male
          Female
          Middle Age
          Aged
          Neuropsychological Tests
          Scales
          Biological Markers
          Random Forest Evaluation
          Boosting Machine Learning Algorithms Evaluation
          Neural Networks (Computer) Evaluation
          Prediction Algorithms Evaluation
          Neutrophil Lymphocyte Ratio
          Uric Acid Blood
          Inflammation
          Antioxidants Analysis
          Hematopoiesis
          Cognition Evaluation
          Confidence Intervals
          Unpaired T-Tests
          Mann-Whitney U Test
          Kendall's tau
          Chi Square Test
          Pearson's Correlation Coefficient
          Comparative Studies
          Electrolytes Blood
          Hemoglobins Blood
          Erythrocytes
          Health Services Needs and Demand
          Health Services Accessibility
          ROC Curve
          Descriptive Statistics
          Data Analysis Software
          Middle Aged: 45-64 years
          Aged: 65+ years
          Male
          Female
      ab: Introduction: Parkinson's disease (PD)-related cognitive impairment (PD-CI) is a common and impactful complication of PD, yet current predictive models often rely on specialized resources, lack interpretability, or have limited cross-population validation. This study aimed to develop an interpretable machine learning framework for PD-CI detection using only routine clinical data, addressing unmet needs in accessible and generalizable PD care. Methods: We analyzed 1,279 participants from the Parkinson's Progression Markers Initiative (PPMI) as the discovery cohort and 197 patients from an independent validation cohort. PD-CI was defined by a Montreal Cognitive Assessment (MoCA) score ≤26 and Unified Parkinson's Disease Rating Scale Part I (UPDRS-I) score ≥1. Twenty-one clinical features—encompassing hematological parameters, metabolic markers, and demographics—were preprocessed with synthetic minority over-sampling. Four machine learning models were trained and optimized via nested 5-fold cross-validation. Results: The Random Forest algorithm achieved superior performance in the discovery cohort (AUC = 0.83), outperforming CatBoost (AUC = 0.82), XGBoost (AUC = 0.79), and neural networks (AUC = 0.66). External validation of the framework preserved 71.57% accuracy. SHAP interpretability analysis identified age, neutrophil-to-lymphocyte ratio (NLR), and serum uric acid as critical predictors, revealing synergistic risk effects between elevated inflammation markers and reduced antioxidant levels. Discussion: This framework demonstrates diagnostic accuracy comparable to advanced neuroimaging while utilizing readily available clinical data, enhancing accessibility in resource-limited settings. It highlights neuroinflammation and oxidative stress as key mechanistic drivers of PD-CI, advancing pathophysiological understanding. Multicenter validation confirms the model's robustness across ethnic populations, supporting its utility as a clinically actionable tool for PD-CI screening and monitoring.
      pubtype: Academic Journal
      doctype:
        research
        tables/charts
        Journal Article
      ougenre: Article
    language: English
    refInfo:
    holdings:
      @attributes:
        islocal: N