Machine learning models of clinically relevant biomarkers for the prediction of stable obstructive coronary artery disease

Juntae Kim; Su Yeon Lee; Byung Hee Cha; Wonseop Lee; JiWung Ryu; Young Hak Chung; Dongmin Kim; Seong-Hoon Lim; Tae Soo Kang; Byoung-Eun Park; Myung-Yong Lee; Sungsoo Cho

doi:10.3389/fcvm.2022.933803

Machine learning models of clinically relevant biomarkers for the prediction of stable obstructive coronary artery disease

Front Cardiovasc Med. 2022 Jul 19:9:933803. doi: 10.3389/fcvm.2022.933803. eCollection 2022.

Authors

Affiliations

¹ Division of Cardiovascular Medicine, Department of Internal Medicine, Dankook University Hospital, Dankook University College of Medicine, Cheonan-si, South Korea.
² CNAI, Seoul, South Korea.
³ Department of Cardiology, Heart and Brain Hospital, Chung-Ang University Gwangmyeong Hospital, Chung-Ang University College of Medicine, Gwangmyeong, South Korea.

Abstract

Background: In patients with suspected obstructive coronary artery disease (CAD), evaluation using a pre-test probability model is the key element for diagnosis; however, its accuracy is controversial. This study aimed to develop machine learning (ML) models using clinically relevant biomarkers to predict the presence of stable obstructive CAD and to compare ML models with an established pre-test probability of CAD models.

Methods: Eight machine learning models for prediction of obstructive CAD were trained on a cohort of 1,312 patients [randomly split into the training (80%) and internal validation sets (20%)]. Twelve clinical and blood biomarker features assessed on admission were used to inform the models. We compared the best-performing ML model and established the pre-test probability of CAD (updated Diamond-Forrester and CAD consortium) models.

Results: The CatBoost algorithm model showed the best performance (area under the receiver operating characteristics, AUROC, 0.796, and 95% confidence interval, CI, 0.740-0.853; Matthews correlation coefficient, MCC, 0.448) compared to the seven other algorithms. The CatBoost algorithm model improved risk prediction compared with the CAD consortium clinical model (AUROC 0.727; 95% CI 0.664-0.789; MCC 0.313). The accuracy of the ML model was 74.6%. Age, sex, hypertension, high-sensitivity cardiac troponin T, hemoglobin A1c, triglyceride, and high-density lipoprotein cholesterol levels contributed most to obstructive CAD prediction.

Conclusion: The ML models using clinically relevant biomarkers provided high accuracy for stable obstructive CAD prediction. In real-world practice, employing such an approach could improve discrimination of patients with suspected obstructive CAD and help select appropriate non-invasive testing for ischemia.

Keywords: artificial intelligence; coronary artery disease; machine learning; personalized medicine; stable angina pectoris.