Skip to main content

Table 1 Features chosen to be predictors in CHD prediction model

From: Ensemble machine learning approach for screening of coronary heart disease based on echocardiography and risk factors

2D-STE features
  Peak systolic strain (PSS) 17 segments
Longitudinal strain Rate of systolic strain (SSR) 17 segments
(mid-layer) Time-to-peak (TP) 17 segments
  Mitral valve level (MV) 3 layers (ENDO/MID/EPI)
Global strain (GS) Papillary muscle level (PM) 3 layers
for radio Apical level (AP) 3 layers
Global longitudinal peak strain (GLPS) 3 layers (ENDO/MID/EPI)
Peak standard deviation (PSD)
Clinic features
Age (integer)
Gender (M/F)
Hypertension (Y/N)
Diabetes (Y/N)
Hyperlipemia (Y/N)
Smoke (Y/N)
Family history (Y/N)