Explainable machine learning for 10-year prediction of cognitive impairment in a rural Chinese population
6 affiliations
- 1Department of Cardiovascular Medicine, Zhengzhou Seventh People’s Hospital, Zhengzhou, Henan Province China
- 2Department of General Practice, Shenzhen Luohu District People’s Hospital, Luohu Clinical College of Shantou University Medical School, Shenzhen, Guangdong Province China
- 3School of Geographical Sciences, University of Bristol, Bristol, United Kingdom
- 4Department of Social Medicine and Health Care Management, School of Public Health, Hebei Medical University, Shijiazhuang, Hebei Province China
- 5Department of Biostatistics and Epidemiology, School of Public Health, Shenzhen University Medical School, Shenzhen, Guangdong Province China
- 6Department of Biostatistics and Epidemiology, School of Public Health, Zhengzhou, Zhengzhou University China
Abstract
Cognitive impairment (CI) is an emerging public health challenge in rural aging populations, where access to formal cognitive testing is limited. Using data from 4781 adults in the Rural Chinese Cohort Study (RCCS) with 10-year follow-up and the Shenzhen Aging-related Disorder Cohort (SADC) with baseline cognitive assessment, this study developed an interpretable machine learning model for long-term CI risk prediction and evaluated its cross-population transportability using eight routinely collected indicators. Among nine algorithms, the Random Forest model showed the most balanced performance, with AUCs of 0.721 (95% CI: 0.596, 0.846) in the RCCS internal validation set for 10-year incident CI prediction and 0.690 (95% CI: 0.664, 0.717) in the SADC baseline-CI evaluation, acceptable calibration, and positive net benefit across threshold probabilities of ~10–40%. SHAP identified age, education, and systolic blood pressure as the main predictive contributors. Subgroup analyses showed heterogeneous discrimination, while sensitivity analyses supported broadly consistent performance under alternative data partitioning and MICE imputation. Mediation analysis suggested a primarily direct association between baseline age and later CI. These findings indicate that a simple, interpretable model based on widely available clinical indicators may support preliminary risk stratification and targeted cognitive screening in resource-constrained rural settings.
Related
- Explainable machine learning identifies predictors for postural instability and cognitive impairment in early Parkinsons Disease
- Prediction of cognitive impairment in Parkinson’s disease using TabPFN: an integrative analysis of clinical data, longitudinal trajectories, and lipidomics
- Curve walking gait analysis using depth camera and machine learning for detecting cognitive impairment
- Stage-Stratified Explainable Machine Learning Identifies a Reproducible Transcriptomic Classifier with Stage-Dependent Feature Importance in Colorectal Cancer: A Multi-Cohort Study with Saudi Population Contextualisation
- Genetic Polymorphisms in SORL1, CLU, BIN1, and VDR Are Associated with Mild Cognitive Impairment and Dementia in a Russian Population.
BibTeX
@article{guo2026explainable,
title = {{Explainable machine learning for 10-year prediction of cognitive impairment in a rural Chinese population}},
author = {Botang Guo and Shiqi Li and Minyao Li and Yuanshuo Ma and Ying Fu and Yihao Shu and Yaqin Su and Kexin Li and Jinliang Liang and Taifeng Chen and Li Yang and Zibo Ni and Yang Zhao and Xueru Fu and Yuying Wu and Liuding Wen and Weifeng Huo and Haocheng Yang and Fulan Hu and Ming Zhang and Yu Liu and Ping Tang and Lei Yin and Dongsheng Hu},
journal = {NPJ Digital Medicine},
year = {2026},
month = jul,
doi = {10.1038/s41746-026-03023-4},
url = {https://doi.org/10.1038/s41746-026-03023-4},
note = {CC BY-NC-ND 4.0},
}
RIS
TY - JOUR
TI - Explainable machine learning for 10-year prediction of cognitive impairment in a rural Chinese population
AU - Botang Guo
AU - Shiqi Li
AU - Minyao Li
AU - Yuanshuo Ma
AU - Ying Fu
AU - Yihao Shu
AU - Yaqin Su
AU - Kexin Li
AU - Jinliang Liang
AU - Taifeng Chen
AU - Li Yang
AU - Zibo Ni
AU - Yang Zhao
AU - Xueru Fu
AU - Yuying Wu
AU - Liuding Wen
AU - Weifeng Huo
AU - Haocheng Yang
AU - Fulan Hu
AU - Ming Zhang
AU - Yu Liu
AU - Ping Tang
AU - Lei Yin
AU - Dongsheng Hu
PY - 2026
DA - 2026/07/15
JO - NPJ Digital Medicine
DO - 10.1038/s41746-026-03023-4
UR - https://doi.org/10.1038/s41746-026-03023-4
AB - Cognitive impairment (CI) is an emerging public health challenge in rural aging populations, where access to formal cognitive testing is limited. Using data from 4781 adults in the Rural Chinese Cohort Study (RCCS) with 10-year follow-up and the Shenzhen Aging-related Disorder Cohort (SADC) with baseline cognitive assessment, this study developed an interpretable machine learning model for long-term CI risk prediction and evaluated its cross-population transportability using eight routinely collected indicators. Among nine algorithms, the Random Forest model showed the most balanced performance, with AUCs of 0.721 (95% CI: 0.596, 0.846) in the RCCS internal validation set for 10-year incident CI prediction and 0.690 (95% CI: 0.664, 0.717) in the SADC baseline-CI evaluation, acceptable calibration, and positive net benefit across threshold probabilities of ~10–40%. SHAP identified age, education, and systolic blood pressure as the main predictive contributors. Subgroup analyses showed heterogeneous discrimination, while sensitivity analyses supported broadly consistent performance under alternative data partitioning and MICE imputation. Mediation analysis suggested a primarily direct association between baseline age and later CI. These findings indicate that a simple, interpretable model based on widely available clinical indicators may support preliminary risk stratification and targeted cognitive screening in resource-constrained rural settings.
SN - 2398-6352
ER -