Explainable machine learning and multivariable logistic regression for identifying prevalent self-reported physician-diagnosed chronic lung disease in postmenopausal women: development and multi-cohort external validation
Abstract
BackgroundChronic lung disease (CLD) is an important cause of morbidity among postmenopausal women, yet simple non-invasive community screening tools are lacking. We aimed to develop and externally validate an interpretable multivariable prediction model for identifying prevalent self-reported physician-diagnosed CLD in this population.MethodsWe analyzed postmenopausal women from the US Health and Retirement Study (HRS; development n = 4,578, internal validation n = 1,962), with external validation in the English Longitudinal Study of Ageing (ELSA; n = 4,574) and a Chinese clinical cohort (n = 650). The primary outcome was prevalent self-reported or clinically recorded physician-diagnosed CLD, including chronic bronchitis, emphysema, or COPD where available. Predictors were selected via nested LASSO penalization. Twelve candidate statistical and machine-learning algorithms were benchmarked; the primary multivariable logistic regression model was evaluated on native uncalibrated probabilities at a locked screening threshold (9.81%) across discrimination, calibration, and clinical net benefit.ResultsThe current 9-predictor model retained smoking status, self-rated health, arthritis, heart disease, osteoporosis, basic activities of daily living difficulty, depressive symptoms, physical activity, and employment. The multivariable logistic regression model achieved AUROCs of 0.771 (95% CI, 0.748–0.793) in HRS development, 0.769 (0.734–0.803) in internal validation, 0.762 (0.735–0.790) in ELSA external validation, and 0.693 (0.634–0.750) in the Chinese cohort. Current smoking and poor self-rated health showed the strongest associations with prevalent CLD. In the Chinese clinical cohort, the model exhibited severe calibration underestimation (observed-to-expected ratio 2.763), demonstrating negative external validation driven by spectrum bias between community and hospital-based settings.ConclusionA parsimonious 9-predictor logistic regression model achieves acceptable discrimination and calibration across community cohorts for identifying prevalent self-reported physician-diagnosed CLD among community-dwelling postmenopausal women. However, direct transport to hospital-based settings is not supported without local recalibration because of pronounced spectrum bias.
Related
- Development and temporal validation of an explainable machine-learning model for identifying anxiety symptoms in adults with sudden sensorineural hearing loss
- Antenatal care contact and optimal IPTp-SP uptake among pregnant women in a district hospital in Ghana: multivariable regression and exploratory decomposition analysis
- Prevalence and risk factors of postmenopausal osteoporosis: a systematic review and meta-analysis based on multivariate logistic regression
- Prediction of Six-Month Glycemic Status in Type 2 Diabetes: Development and Internal Validation of a Multivariable Model
- Explainable machine learning for identifying insufficient sleep duration among preschool children in cold-region China: a cross-sectional study
BibTeX
@article{du2026explainable,
title = {{Explainable machine learning and multivariable logistic regression for identifying prevalent self-reported physician-diagnosed chronic lung disease in postmenopausal women: development and multi-cohort external validation}},
author = {Caizhong Du and Nana Xue and Liqin Dang and Gang Wang and Shiqin Wang},
journal = {Frontiers in Public Health},
year = {2026},
month = nov,
doi = {10.3389/fpubh.2026.1982073},
url = {https://www.frontiersin.org/articles/10.3389/fpubh.2026.1982073},
note = {CC BY 4.0},
}
RIS
TY - JOUR
TI - Explainable machine learning and multivariable logistic regression for identifying prevalent self-reported physician-diagnosed chronic lung disease in postmenopausal women: development and multi-cohort external validation
AU - Caizhong Du
AU - Nana Xue
AU - Liqin Dang
AU - Gang Wang
AU - Shiqin Wang
PY - 2026
DA - 2026/11/05
JO - Frontiers in Public Health
DO - 10.3389/fpubh.2026.1982073
UR - https://www.frontiersin.org/articles/10.3389/fpubh.2026.1982073
AB - BackgroundChronic lung disease (CLD) is an important cause of morbidity among postmenopausal women, yet simple non-invasive community screening tools are lacking. We aimed to develop and externally validate an interpretable multivariable prediction model for identifying prevalent self-reported physician-diagnosed CLD in this population.MethodsWe analyzed postmenopausal women from the US Health and Retirement Study (HRS; development n = 4,578, internal validation n = 1,962), with external validation in the English Longitudinal Study of Ageing (ELSA; n = 4,574) and a Chinese clinical cohort (n = 650). The primary outcome was prevalent self-reported or clinically recorded physician-diagnosed CLD, including chronic bronchitis, emphysema, or COPD where available. Predictors were selected via nested LASSO penalization. Twelve candidate statistical and machine-learning algorithms were benchmarked; the primary multivariable logistic regression model was evaluated on native uncalibrated probabilities at a locked screening threshold (9.81%) across discrimination, calibration, and clinical net benefit.ResultsThe current 9-predictor model retained smoking status, self-rated health, arthritis, heart disease, osteoporosis, basic activities of daily living difficulty, depressive symptoms, physical activity, and employment. The multivariable logistic regression model achieved AUROCs of 0.771 (95% CI, 0.748–0.793) in HRS development, 0.769 (0.734–0.803) in internal validation, 0.762 (0.735–0.790) in ELSA external validation, and 0.693 (0.634–0.750) in the Chinese cohort. Current smoking and poor self-rated health showed the strongest associations with prevalent CLD. In the Chinese clinical cohort, the model exhibited severe calibration underestimation (observed-to-expected ratio 2.763), demonstrating negative external validation driven by spectrum bias between community and hospital-based settings.ConclusionA parsimonious 9-predictor logistic regression model achieves acceptable discrimination and calibration across community cohorts for identifying prevalent self-reported physician-diagnosed CLD among community-dwelling postmenopausal women. However, direct transport to hospital-based settings is not supported without local recalibration because of pronounced spectrum bias.
SN - 2296-2565
ER -