What type of study is this?

This is a Validation Study study.

What question did this study set out to answer?

To develop a machine learning framework for predicting cognitive impairment in Parkinson’s disease using routine clinical data.

November 11, 2025Frontiers in Aging Neuroscience0 citationsOpen Access

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

View Full Paper

Ask AI

Bookmark

Authors

Machine learning models predict cognitive impairment in Parkinson’s disease, suggesting neuroinflammation impacts outcomes.

To develop a machine learning framework for predicting cognitive impairment in Parkinson’s disease using routine clinical data.
Analyzed 1,279 participants from the Parkinson’s Progression Markers Initiative as the discovery cohort.
Defined cognitive impairment via Montreal Cognitive Assessment score and Unified Parkinson’s Disease Rating Scale score.
Employed synthetic minority over-sampling for preprocessing clinical features.
Trained and optimized four machine learning models using nested 5-fold cross-validation.
The Random Forest algorithm achieved an AUC of 0.83 in the discovery cohort, outperforming other models.
External validation retained 71.57% accuracy in identifying cognitive impairment.
SHAP analysis identified age, NLR, and serum uric acid as critical predictors of cognitive impairment.

Wang et al. (2025) studied this question.

View Full Paper

Ask AI

Bookmark

November 11, 2025Frontiers in Aging Neuroscience0 citationsOpen Access

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

View Full Paper

Ask AI

Bookmark

Authors

Machine learning models predict cognitive impairment in Parkinson’s disease, suggesting neuroinflammation impacts outcomes.

To develop a machine learning framework for predicting cognitive impairment in Parkinson’s disease using routine clinical data.
Analyzed 1,279 participants from the Parkinson’s Progression Markers Initiative as the discovery cohort.
Defined cognitive impairment via Montreal Cognitive Assessment score and Unified Parkinson’s Disease Rating Scale score.
Employed synthetic minority over-sampling for preprocessing clinical features.
Trained and optimized four machine learning models using nested 5-fold cross-validation.
The Random Forest algorithm achieved an AUC of 0.83 in the discovery cohort, outperforming other models.
External validation retained 71.57% accuracy in identifying cognitive impairment.
SHAP analysis identified age, NLR, and serum uric acid as critical predictors of cognitive impairment.

Wang et al. (2025) studied this question.

View Full Paper

Ask AI

Bookmark