Accepted for/Published in: Journal of Medical Internet Research
Date Submitted: Jul 24, 2026
Date Accepted: Oct 21, 2026
Comprehensive Clinical Decision-Support Framework for Obesity Prevention Using Large-Scale Health Checkup Data: Development and Evaluation Study
ABSTRACT
Background:
Obesity prevention requires identifying adults who are currently non-obese but likely to transition to obesity, rather than classifying current anthropometric status. Korea operates a national health screening program that routinely collects anthropometric, blood pressure, laboratory, medical history, and lifestyle information, but obesity screening in this setting primarily classifies current anthropometric status and does not estimate future transition risk or provide an individualised risk context for prioritising preventive counselling.
Objective:
This study aimed to develop and evaluate a comprehensive clinical decision-support framework for obesity prevention using large-scale health checkup data.
Methods:
We used data from the repeated Kangbuk Samsung Health Study. Adults with an index body mass index (BMI) <25 kg/m², at least three health checkup visits, a two-year obesity-free washout, and post-index follow-up were included. BMI-defined incident obesity was defined as a first follow-up BMI of ≥25 kg/m². The framework integrated Lite single-visit risk prediction, a survival component for time-to-transition context, Plus repeated-measurement updating, and an explainability layer to support triage, trajectory interpretation, and follow-up prioritisation. The Lite ensemble was externally evaluated in 328,268 National Health Insurance Service (NHIS) participants.
Results:
We used data from the repeated Kangbuk Samsung Health Study. Adults with an index body mass index (BMI) <25 kg/m², at least three health checkup visits, a two-year obesity-free washout, and post-index follow-up were included. BMI-defined incident obesity was defined as a first follow-up BMI of ≥25 kg/m². The framework integrated Lite single-visit risk prediction, a survival component for time-to-transition context, Plus repeated-measurement updating, and an explainability layer to support triage, trajectory interpretation, and follow-up prioritisation. The Lite ensemble was externally evaluated in 328,268 National Health Insurance Service (NHIS) participants.
Conclusions:
Large-scale health checkup data can be organised into a comprehensive clinical decision-support framework for obesity prevention, providing single-visit triage, temporal risk context, risk-domain explanation, and exploratory repeated-measurement updating. Because the outcome is BMI-defined, the framework should be interpreted as risk communication and decision support, not as an automated intervention or evidence of behaviour-change effectiveness.
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.