Machine Learning Model for Predicting Coronary Heart Disease Risk: Development and Validation Using Insights From a Japanese Population–Based Study
We developed a model to predict CHD using ML and applied SHAP methods for interpretation. This approach highlights the multifactor nature of CHD risk evaluation, aiming to support health care professionals in identifying risk factors and formulating effective prevention strategies.
Authors
- Takao Inoué (ORCID: https://orcid.org/0000-0002-2080-7480)
- Masayuki Teramoto (ORCID: https://orcid.org/0000-0002-2318-2447)
- Mai Inoue (ORCID: https://orcid.org/0000-0003-3204-1627)
- Yoshihiro Kokubo (ORCID: https://orcid.org/0000-0002-0705-9449)
- Ahmed Arafa (ORCID: https://orcid.org/0000-0002-3335-2243)
- Michihiro Araki (ORCID: https://orcid.org/0000-0002-6686-4018)
- Attayeb Mohsen (ORCID: https://orcid.org/0000-0003-0690-8012)
- Agustin Martin‐Morales (ORCID: https://orcid.org/0000-0002-3564-4776)
- Yuki Kuriya (ORCID: https://orcid.org/0000-0001-5118-7803)
- Yoko M. Nakao (ORCID: https://orcid.org/0000-0002-3627-5626)
- Thien Vu (ORCID: https://orcid.org/0000-0002-6956-0191)
- Mari Yoshizaki (ORCID: https://orcid.org/0009-0002-5031-0632)
- Naoki Watanabe (ORCID: https://orcid.org/0000-0002-6418-991X)
- Masaki Yamamoto (ORCID: https://orcid.org/0000-0001-9179-6080)
- Chisa Matsumoto (ORCID: https://orcid.org/0000-0002-8066-8363)
- J. Tay
- Yuka Kato (ORCID: https://orcid.org/0009-0009-2739-9609)
Institutions
- Beni-Suef University (EG)
- Shiga University of Medical Science (JP)
- Shiga University (JP)
- Kyoto University (JP)
- Cho Ray Hospital (VN)
- National Institute of Biomedical Innovation, Health and Nutrition (JP)
- Yamato University (JP)
- Tokyo Medical University Hospital (JP)
- National Cerebral and Cardiovascular Center (JP)
- Libyan Academy (LY)
- Kobe University (JP)
- The University of Osaka (JP)
Publication Details
- Journal
- JMIR Cardio
- Published
- 2025-02-24
- DOI
- https://doi.org/10.2196/68066
- Citations
- 16
- Primary Topic
- Artificial Intelligence in Healthcare
- Type
- article
- Field-Weighted Citation Impact
- 47.00