Development and validation of ischemic heart disease and stroke prognostic models using large-scale real-world data from Japan
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 suc...
| Main Authors: | , , , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
Komiyama Printing Co. Ltd
2023-02-01
|
| Series: | Environmental Health and Preventive Medicine |
| Subjects: | |
| Online Access: | https://www.jstage.jst.go.jp/article/ehpm/28/0/28_22-00106/_html/-char/en |
| _version_ | 1797893783960944640 |
|---|---|
| author | Shigeto Yoshida Shu Tanaka Masafumi Okada Takuya Ohki Kazumasa Yamagishi Yasushi Okuno |
| author_facet | Shigeto Yoshida Shu Tanaka Masafumi Okada Takuya Ohki Kazumasa Yamagishi Yasushi Okuno |
| author_sort | Shigeto Yoshida |
| collection | DOAJ |
| description | 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. |
| first_indexed | 2024-04-10T06:58:19Z |
| format | Article |
| id | doaj.art-87353cac504240ecafff622e314973a6 |
| institution | Directory Open Access Journal |
| issn | 1342-078X 1347-4715 |
| language | English |
| last_indexed | 2024-04-10T06:58:19Z |
| publishDate | 2023-02-01 |
| publisher | Komiyama Printing Co. Ltd |
| record_format | Article |
| series | Environmental Health and Preventive Medicine |
| spelling | doaj.art-87353cac504240ecafff622e314973a62023-02-28T04:27:44ZengKomiyama Printing Co. LtdEnvironmental Health and Preventive Medicine1342-078X1347-47152023-02-0128161610.1265/ehpm.22-00106ehpmDevelopment and validation of ischemic heart disease and stroke prognostic models using large-scale real-world data from JapanShigeto Yoshida0https://orcid.org/0000-0001-5056-6473Shu Tanaka1Masafumi Okada2Takuya Ohki3Kazumasa Yamagishi4Yasushi Okuno5Data Science and Advanced Analytics, IQVIA Solutions Japan K.K.Real-World Evidence Solutions, IQVIA Solutions Japan K.K.Real-World Evidence Solutions, IQVIA Solutions Japan K.K.Real-World Evidence Solutions, IQVIA Solutions Japan K.K.Department of Public Health Medicine, Faculty of Medicine, and Health Services Research and Development Center, University of TsukubaMedical Sciences Innovation Hub Program, RIKENBackground: 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.https://www.jstage.jst.go.jp/article/ehpm/28/0/28_22-00106/_html/-char/enrisk prediction modelmachine learningischemic heart diseasestrokereal-world data |
| spellingShingle | Shigeto Yoshida Shu Tanaka Masafumi Okada Takuya Ohki Kazumasa Yamagishi Yasushi Okuno Development and validation of ischemic heart disease and stroke prognostic models using large-scale real-world data from Japan Environmental Health and Preventive Medicine risk prediction model machine learning ischemic heart disease stroke real-world data |
| title | Development and validation of ischemic heart disease and stroke prognostic models using large-scale real-world data from Japan |
| title_full | Development and validation of ischemic heart disease and stroke prognostic models using large-scale real-world data from Japan |
| title_fullStr | Development and validation of ischemic heart disease and stroke prognostic models using large-scale real-world data from Japan |
| title_full_unstemmed | Development and validation of ischemic heart disease and stroke prognostic models using large-scale real-world data from Japan |
| title_short | Development and validation of ischemic heart disease and stroke prognostic models using large-scale real-world data from Japan |
| title_sort | development and validation of ischemic heart disease and stroke prognostic models using large scale real world data from japan |
| topic | risk prediction model machine learning ischemic heart disease stroke real-world data |
| url | https://www.jstage.jst.go.jp/article/ehpm/28/0/28_22-00106/_html/-char/en |
| work_keys_str_mv | AT shigetoyoshida developmentandvalidationofischemicheartdiseaseandstrokeprognosticmodelsusinglargescalerealworlddatafromjapan AT shutanaka developmentandvalidationofischemicheartdiseaseandstrokeprognosticmodelsusinglargescalerealworlddatafromjapan AT masafumiokada developmentandvalidationofischemicheartdiseaseandstrokeprognosticmodelsusinglargescalerealworlddatafromjapan AT takuyaohki developmentandvalidationofischemicheartdiseaseandstrokeprognosticmodelsusinglargescalerealworlddatafromjapan AT kazumasayamagishi developmentandvalidationofischemicheartdiseaseandstrokeprognosticmodelsusinglargescalerealworlddatafromjapan AT yasushiokuno developmentandvalidationofischemicheartdiseaseandstrokeprognosticmodelsusinglargescalerealworlddatafromjapan |