Machine learning insight into the role of imaging and clinical variables for the prediction of obstructive coronary artery disease and revascularization: An exploratory analysis of the CONSERVE study.
Lohendran BaskaranXiaohan YingZhuoran XuSubhi J Al'ArefBenjamin C LeeSang-Eun LeeIbrahim DanadHyung-Bok ParkRavi BathinaAndrea BaggianoVirginia BeltramaRodrigo Júlio CerciEui-Young ChoiJung-Hyun ChoiSo-Yeon ChoiJason ColeJoon-Hyung DohSang-Jin HaAe-Young HerCezary KepkaJang-Young KimJin-Won KimSang-Wook KimWoong KimYao LuAmit KumarRan HeoJi Hyun LeeJi-Min SungUma ValetiDaniele AndreiniGianluca PontoneDonghee HanTodd C VillinesFay LinHyuk-Jae ChangJames K MinLeslee J ShawPublished in: PloS one (2020)
For obstructive CAD, the ML model outperformed CAD2. BMI is an important variable, although currently not included in most scores. In this ML model, imaging variables were most associated with revascularization. Imaging modality did not influence model performance. Removal of imaging variables reduced model performance.