What question did this study set out to answer?

To develop and evaluate machine learning models classifying six major chronic conditions using multidimensional social, behavioral, and psychological determinants, and to quantify domain-specific predictive importance.

August 1, 2026Annals of EpidemiologyOpen Access

Machine Learning Classification of Prevalent Chronic Disease Using Multidimensional Social, Behavioral, and Psychological Determinants: A Cross-Sectional Analysis of the 2024 National Health Interview Survey

View Full Paper

Ask AI

Bookmark

Authors

CZCai Zhang JHJie Hao SLShidi Lin

Discussion

Member takes

Overview

Cross-sectional analysis finds social and psychological factors strongly predict mental disorders but not cardiometabolic conditions in US adults, highlighting disease-specific screening needs.

Key Points

To develop and evaluate machine learning models classifying six major chronic conditions using multidimensional social, behavioral, and psychological determinants, and to quantify domain-specific predictive importance.
Analyzed cross-sectional data from 32,614 adults in the 2024 National Health Interview Survey using 24 predictor variables across seven social determinants of health domains.
Trained Logistic Regression, Gradient Boosting Machine (GBM), and Random Forest models evaluated with 5-fold stratified cross-validation (AUROC, F1, AUPRC) and verified via SHAP importance.
GBM achieved the highest discriminative performance across five of six conditions, with AUROC scores spanning from 0.793 for anxiety to 0.857 for COPD.
Psychosocial factors accounted for 52% and 42% of predictive importance for depression and anxiety, but contributed less than 3% for cardiometabolic diseases, where age and BMI predominated.

Cite This Study

Zhang et al. (2026) studied this question.

synapsesocial.com/papers/6a76cb67e8156ceda1adf84e https://doi.org/10.1016/j.annepidem.2026.110249

View Full Paper

Ask AI

Bookmark

August 1, 2026Annals of EpidemiologyOpen Access

Machine Learning Classification of Prevalent Chronic Disease Using Multidimensional Social, Behavioral, and Psychological Determinants: A Cross-Sectional Analysis of the 2024 National Health Interview Survey

View Full Paper

Ask AI

Bookmark

Authors

CZCai Zhang JHJie Hao SLShidi Lin

Discussion

Member takes

Overview

Cross-sectional analysis finds social and psychological factors strongly predict mental disorders but not cardiometabolic conditions in US adults, highlighting disease-specific screening needs.

Key Points

To develop and evaluate machine learning models classifying six major chronic conditions using multidimensional social, behavioral, and psychological determinants, and to quantify domain-specific predictive importance.
Analyzed cross-sectional data from 32,614 adults in the 2024 National Health Interview Survey using 24 predictor variables across seven social determinants of health domains.
Trained Logistic Regression, Gradient Boosting Machine (GBM), and Random Forest models evaluated with 5-fold stratified cross-validation (AUROC, F1, AUPRC) and verified via SHAP importance.
GBM achieved the highest discriminative performance across five of six conditions, with AUROC scores spanning from 0.793 for anxiety to 0.857 for COPD.
Psychosocial factors accounted for 52% and 42% of predictive importance for depression and anxiety, but contributed less than 3% for cardiometabolic diseases, where age and BMI predominated.

Cite This Study

Zhang et al. (2026) studied this question.

synapsesocial.com/papers/6a76cb67e8156ceda1adf84e https://doi.org/10.1016/j.annepidem.2026.110249

Also Consider

Synapse has enriched 5 closely related papers on similar clinical questions. Consider them for comparative context:

View Full Paper

Ask AI

Bookmark