Key result
Machine learning and classical regression models using real-world health check-up data achieved excellent discrimination for predicting ischemic heart disease (C-index ~0.9) and acceptable discrimination for stroke (C-index >0.7).
Why the study?
Cardiovascular risk prediction models in Japan previously relied on concise prospective cohort studies, and large real-world digital health check-up and claims datasets could improve prediction accuracy and support social implementation.
Observational (n=572,971)
Effect estimate: C-index ~0.9 for IHD, >0.7 for stroke
Machine learning and classical regression models using large-scale real-world administrative and health check-up data can accurately predict the risk of ischemic heart disease and stroke in the Japanese working-age population.
Supports risk prediction from routine Japanese data; leaves open prospective validation before clinical adoption.
BACKGROUND: Previous cardiovascular risk prediction models in Japan have utilized prospective cohort studies with concise data. As the health information including health check-up records and administrative claims becomes digitalized and publicly available, application of large datasets based on such real-world data can achieve prediction accuracy and support social implementation of cardiovascular disease risk prediction models in preventive and clinical practice. In this study, classical regression and machine learning methods were explored to develop ischemic heart disease (IHD) and stroke prognostic models using real-world data. METHODS: IQVIA Japan Claims Database was searched to include 691,160 individuals (predominantly corporate employees and their families working in secondary and tertiary industries) with at least one annual health check-up record during the identification period (April 2013-December 2018). The primary outcome of the study was the first recorded IHD or stroke event. Predictors were annual health check-up records at the index year-month, comprising demographic characteristics, laboratory tests, and questionnaire features. Four prediction models (Cox, Elnet-Cox, XGBoost, and Ensemble) were assessed in the present study to develop a cardiovascular disease risk prediction model for Japan. RESULTS: The analysis cohort consisted of 572,971 invididuals. All prediction models showed similarly good performance. The Harrell's C-index was close to 0.9 for all IHD models, and above 0.7 for stroke models. In IHD models, age, sex, high-density lipoprotein, low-density lipoprotein, cholesterol, and systolic blood pressure had higher importance, while in stroke models systolic blood pressure and age had higher importance. CONCLUSION: Our study analyzed classical regression and machine learning algorithms to develop cardiovascular disease risk prediction models for IHD and stroke in Japan that can be applied to practical use in a large population with predictive accuracy.
No takes yet. Share an insight, caveat, or question.
Yoshida et al. (2023) conducted an observational in Ischemic heart disease and stroke (n=572,971). Cardiovascular disease risk prediction models (Cox, Elnet-Cox, XGBoost, Ensemble) was evaluated on First recorded ischemic heart disease or stroke event (model discrimination) (C-index ~0.9 for IHD, >0.7 for stroke). Machine learning and classical regression models using real-world health check-up data achieved excellent discrimination for predicting ischemic heart disease (C-index ~0.9) and acceptable discrimination for stroke (C-index >0.7).
Synapse has enriched 5 closely related papers on similar clinical questions. Consider them for comparative context: