Machine Learning with Social Determinants of Health for Cross-Sectional Diabetes Classification: Development and Temporal Validation.
8 affiliations
- 1Division of Neurosurgery, Department of Surgery, Taipei Tzu Chi Hospital, Buddhist Tzu Chi Medical Foundation, New Taipei City 23142, Taiwan.
- 2Interdisciplinary Program Kinesiology and Health, Chinese Culture University, Taipei 11114, Taiwan.
- 3School of Medicine, College of Medicine, Taipei Medical University, Taipei 11031, Taiwan.
- 4Division of Neurosurgery, Department of Surgery, National Taiwan University Hospital, College of Medicine, National Taiwan University, Taipei 10617, Taiwan.
- 5Division of Outcomes and Practice Advancement, Department of Pharmacy Practice, School of Pharmacy and Pharmaceutical Sciences, University at Buffalo, Buffalo, New York 14214, United States.
- 6Department of Healthcare Information and Management, School of Health and Medical Engineering, Ming Chuan University, Taoyuan 33300, Taiwan.
- 7Department of Emergency Medicine, Taipei Medical University Hospital, Taipei 11030, Taiwan.
- 8Graduate Institute of Injury Prevention and Control, College of Public Health, Taipei Medical University, Taipei 11031, Taiwan.
Abstract
Aims
Our study aimed to determine whether incorporating social determinants of health (SDOH) improves cross-sectional classification of prevalent diagnosed diabetes and to quantify the extent to which model performance is attributable to variables that may occur downstream of diabetes diagnosis.Methods
We analyzed data from the 2023 Behavioral Risk Factor Surveillance System (BRFSS) as the development cohort and the 2024 BRFSS as an independent temporal validation cohort. Analyses were restricted to adults aged 35 years or older residing in states that administered the SDOH module. The outcome was self-reported diagnosed diabetes. Before model development, 30% of the 2023 sample was reserved as a test set. Imputation, encoding, feature processing, and hyperparameter tuning were performed within nested cross-validation. Histogram-based gradient boosting and penalized logistic regression were evaluated across six pre-specified nested predictor specifications. Final models were applied unchanged to the 2024 cohort without refitting, re-tuning, or threshold recalibration. Performance estimates incorporated BRFSS survey weights.Results
The development cohort comprised 179,752 adults (weighted prevalence 16.97%) and the validation cohort 161,092 (18.07%). Discrimination ranged from 0.75 to 0.81 across algorithms, with gradient boosting and penalized logistic regression indistinguishable (0.811 versus 0.808). The full model achieved an area under the receiver operating characteristic curve (AUROC) of 0.811 (95% CI 0.801 - 0.822) and transported to the validation cohort with a calibration slope of 1.040. Adding nine SDOH items changed discrimination by 0.006 (95% CI 0.004 - 0.008), with maximum net benefit gain under 0.003; discrimination rose from 0.743 to 0.811 only when healthcare utilization and comorbidity measures were added. Several SDOH nonetheless showed robust adjusted associations, including food insecurity (OR 1.27 - 1.39) and supplemental nutrition assistance program receipt (OR 1.34, 95% CI 1.11 - 1.61). At a fixed threshold, sensitivity ranged from 0.62 to 0.89 across age groups.Conclusions
SDOH were independently associated with prevalent diagnosed diabetes but provided little incremental value beyond demographic, behavioral, and healthcare access measures, a finding that was consistent across consecutive survey cycles. Most of the observed discrimination was attributable to healthcare utilization and comorbidity variables that may plausibly reflect consequences of an established diagnosis rather than characteristics preceding disease recognition.
Related
- Development and Validation of a Machine Learning-Based Model for Elevated Depressive Symptom Risk in COPD Patients: A Multi-Cohort Cross-Sectional Study.
- Development and interpretable validation of a machine-learning model for edentulism risk in US adults : A cross-sectional study integrating five algorithms and dietary data from NHANES 2009–2014
- Development and psychometric validation of a health literacy competency scale for nurses, and its application in a cross-sectional survey: a methodological study
- Validation of Machine Learning Models for classification of bladder dysfunction and risk of hydronephrosis in patients with Spina Bifida using videourodynamic data
- Multidimensional Determinants of Hypertension Self-Management to Inform the Development of a Person-Centered Nursing-Based Self-Care Bundle: A Cross-Sectional Study in Primary Care
BibTeX
@article{kung2026machine,
title = {{Machine Learning with Social Determinants of Health for Cross-Sectional Diabetes Classification: Development and Temporal Validation.}},
author = {Woon-Man Kung and Hsien Chang Yeh and Abel Po-Hao Huang and Md Mohaimenul Islam and Chieh-Chen Wu and Yao-Chin Wang},
journal = {International journal of medical sciences},
year = {2026},
month = sep,
doi = {10.7150/ijms.137605},
url = {https://europepmc.org/article/MED/42909408},
note = {CC BY},
}
RIS
TY - JOUR
TI - Machine Learning with Social Determinants of Health for Cross-Sectional Diabetes Classification: Development and Temporal Validation.
AU - Woon-Man Kung
AU - Hsien Chang Yeh
AU - Abel Po-Hao Huang
AU - Md Mohaimenul Islam
AU - Chieh-Chen Wu
AU - Yao-Chin Wang
PY - 2026
DA - 2026/09/11
JO - International journal of medical sciences
DO - 10.7150/ijms.137605
UR - https://europepmc.org/article/MED/42909408
AB - Aims Our study aimed to determine whether incorporating social determinants of health (SDOH) improves cross-sectional classification of prevalent diagnosed diabetes and to quantify the extent to which model performance is attributable to variables that may occur downstream of diabetes diagnosis.Methods We analyzed data from the 2023 Behavioral Risk Factor Surveillance System (BRFSS) as the development cohort and the 2024 BRFSS as an independent temporal validation cohort. Analyses were restricted to adults aged 35 years or older residing in states that administered the SDOH module. The outcome was self-reported diagnosed diabetes. Before model development, 30% of the 2023 sample was reserved as a test set. Imputation, encoding, feature processing, and hyperparameter tuning were performed within nested cross-validation. Histogram-based gradient boosting and penalized logistic regression were evaluated across six pre-specified nested predictor specifications. Final models were applied unchanged to the 2024 cohort without refitting, re-tuning, or threshold recalibration. Performance estimates incorporated BRFSS survey weights.Results The development cohort comprised 179,752 adults (weighted prevalence 16.97%) and the validation cohort 161,092 (18.07%). Discrimination ranged from 0.75 to 0.81 across algorithms, with gradient boosting and penalized logistic regression indistinguishable (0.811 versus 0.808). The full model achieved an area under the receiver operating characteristic curve (AUROC) of 0.811 (95% CI 0.801 - 0.822) and transported to the validation cohort with a calibration slope of 1.040. Adding nine SDOH items changed discrimination by 0.006 (95% CI 0.004 - 0.008), with maximum net benefit gain under 0.003; discrimination rose from 0.743 to 0.811 only when healthcare utilization and comorbidity measures were added. Several SDOH nonetheless showed robust adjusted associations, including food insecurity (OR 1.27 - 1.39) and supplemental nutrition assistance program receipt (OR 1.34, 95% CI 1.11 - 1.61). At a fixed threshold, sensitivity ranged from 0.62 to 0.89 across age groups.Conclusions SDOH were independently associated with prevalent diagnosed diabetes but provided little incremental value beyond demographic, behavioral, and healthcare access measures, a finding that was consistent across consecutive survey cycles. Most of the observed discrimination was attributable to healthcare utilization and comorbidity variables that may plausibly reflect consequences of an established diagnosis rather than characteristics preceding disease recognition.
SN - 1449-1907
ER -