Accepted for/Published in: Online Journal of Public Health Informatics
Date Submitted: Dec 23, 2025
Date Accepted: Jul 21, 2026
Date Submitted to PubMed: Jul 21, 2026
Explainable Machine Learning for Public Health Informatics in HEDIS Childhood Immunization Status Combo 10
ABSTRACT
HEDIS Childhood Immunization Status (CIS) Combination 10 is a pediatric quality measure, but aggregate reporting limits public health informatics use by obscuring component-level drivers of noncompletion. To apply explainable machine learning as a public health informatics approach to identify vaccine components associated with CIS Combo 10 completion among U.S. children aged 24-35 months. We analyzed 2021-2023 National Immunization Survey-Child public-use files. The age-eligible cohort included 32,997 children; weighted modeling included 16,021 children. Survey-weighted logistic regression estimated national trends with 95% CIs, and Random Forest modeling with SHAP and cross-validation identified component-level predictors. CIS Combo 10 completion declined from 53.7% in 2021 to 44.6% in 2023 (annual OR 0.83, 95% CI 0.831-0.834; P<.001). Influenza and rotavirus had the largest mean absolute SHAP values. CIS Combo 10 completion declined substantially from 2021 to 2023. An explainable public health informatics approach identified influenza and rotavirus as actionable targets for immunization quality improvement.
Citation
Request queued. Please wait while the file is being generated. It may take some time.
Copyright
© The authors. All rights reserved. This is a privileged document currently under peer-review/community review (or an accepted/rejected manuscript). Authors have provided JMIR Publications with an exclusive license to publish this preprint on it's website for review and ahead-of-print citation purposes only. While the final peer-reviewed paper may be licensed under a cc-by license on publication, at this stage authors and publisher expressively prohibit redistribution of this draft paper other than for review purposes.