Pre-existing and machine learning-based models for cardiovascular risk prediction

• Published in: Scientific reports Vol. 11; no. 1; pp. 8886 - 10
• Main Authors: Cho, Sang-Yeong, Kim, Sun-Hwa, Kang, Si-Hyuck, Lee, Kyong Joon, Choi, Dongjun, Kang, Seungjin, Park, Sang Jun, Kim, Tackeun, Yoon, Chang-Hwan, Youn, Tae-Jin, Chae, In-Ho
• Format: Journal Article
• Language: English
• Published: London Nature Publishing Group UK 26-04-2021; Nature Publishing Group; Nature Portfolio
• Subjects: 692/4019/592/75/2099; 692/700/459/1748; Adult; Aged; Algorithms; Cardiovascular disease; Cardiovascular diseases; Cardiovascular Diseases - diagnosis; Decision making; Female; Health risks; Humanities and Social Sciences; Humans; Learning algorithms; Machine Learning; Male; Middle Aged; Models, Cardiovascular; multidisciplinary; Neural networks; Prediction models; Regression analysis; Risk Assessment; Risk Factors; Science; Science (multidisciplinary); Statistical analysis; Statistics
• ISSN: 2045-2322; 2045-2322
• DOI: 10.1038/s41598-021-88257-w

Predicting the risk of cardiovascular disease is the key to primary prevention. Machine learning has attracted attention in analyzing increasingly large, complex healthcare data. We assessed discrimination and calibration of pre-existing cardiovascular risk prediction models and developed machine learning-based prediction algorithms. This study included 222,998 Korean adults aged 40–79 years, naïve to lipid-lowering therapy, had no history of cardiovascular disease. Pre-existing models showed moderate to good discrimination in predicting future cardiovascular events (C-statistics 0.70–0.80). Pooled cohort equation (PCE) specifically showed C-statistics of 0.738. Among other machine learning models such as logistic regression, treebag, random forest, and adaboost, the neural network model showed the greatest C-statistic (0.751), which was significantly higher than that for PCE. It also showed improved agreement between the predicted risk and observed outcomes (Hosmer–Lemeshow χ
2
 = 86.1, P < 0.001) than PCE for whites did (Hosmer–Lemeshow χ
2
 = 171.1, P < 0.001). Similar improvements were observed for Framingham risk score, systematic coronary risk evaluation, and QRISK3. This study demonstrated that machine learning-based algorithms could improve performance in cardiovascular risk prediction over contemporary cardiovascular risk models in statin-naïve healthy Korean adults without cardiovascular disease. The model can be easily adopted for risk assessment and clinical decision making.