Classification of coronary artery disease using radial artery pulse wave analysis via machine learning

Table 3 The performance comparison of different ML models (mean ± std)

Model	Accuracy	AUC	Recall	Prec	F1	Kappa	MCC	TT(sec)
Extra Trees Classifier	0.8519 ± 0.0251	0.9151 ± 0.0279	0.8424 ± 0.0271	0.8598 ± 0.0265	0.8510 ± 0.0251	0.7770 ± 0.0378	0.7814 ± 0.0382	0.0480
CatBoost Classifier	0.8496 ± 0.0253	0.9137 ± 0.0282	0.8400 ± 0.0299	0.8571 ± 0.0267	0.8483 ± 0.0255	0.7732 ± 0.0382	0.7777 ± 0.0381	6.9440
Random Forest Classifier	0.8447 ± 0.0185	0.9136 ± 0.0311	0.8373 ± 0.0174	0.8507 ± 0.0211	0.8439 ± 0.0182	0.7663 ± 0.0277	0.7698 ± 0.0292	0.0390
Light Gradient Boosting Machine	0.8190 ± 0.0304	0.9066 ± 0.0316	0.8079 ± 0.0361	0.8281 ± 0.0250	0.8178 ± 0.0286	0.7274 ± 0.0457	0.7324 ± 0.0442	0.1870
Gradient Boosting Classifier	0.8143 ± 0.0290	0.9092 ± 0.0231	0.8062 ± 0.0283	0.8194 ± 0.0301	0.8127 ± 0.0280	0.7202 ± 0.0438	0.7239 ± 0.0452	0.2930
Extreme Gradient Boosting	0.8120 ± 0.0336	0.9098 ± 0.0293	0.8007 ± 0.0372	0.8214 ± 0.0289	0.8108 ± 0.0324	0.7169 ± 0.0507	0.7222 ± 0.0491	0.0940
Decision Tree Classifier	0.6893 ± 0.0654	0.7677 ± 0.0500	0.6770 ± 0.0739	0.7000 ± 0.0615	0.6882 ± 0.0654	0.5326 ± 0.0983	0.5373 ± 0.0974	0.0090

ISSN: 1472-6947