Table 15 Classification results of datasets after feature selection under SCAD-LR classifier
From: Missing data imputation, prediction, and feature selection in diagnosis of vaginal prolapse
Imputation methods | FSM(No. of selected features) | Accuracy | F1 | AUC |
|---|---|---|---|---|
Mean | Lasso(20) | 0.7111(0.0077) | 0.8095(0.0058) | 0.6025(0.0069) |
SCAD(41) | 0.7119(0.0081) | 0.8098(0.0061) | 0.6041(0.0072) | |
BAR(7) | 0.6992(0.0085) | 0.8033(0.0062) | 0.5837(0.0073) | |
EM | Lasso(20) | 0.7124(0.0080) | 0.8103(0.0060) | 0.6043(0.0071) |
SCAD(30) | 0.7124(0.0078) | 0.8102(0.0059) | 0.6049(0.0071) | |
BAR(7) | 0.7063(0.0079) | 0.8069(0.0060) | 0.5950(0.0067) | |
KNN | Lasso(20) | 0.7134(0.0080) | 0.8108(0.0060) | 0.6069(0.0072) |
SCAD(38) | 0.7141(0.0078) | 0.8109(0.0059) | 0.6083(0.0071) | |
BAR(7) | 0.7063(0.0079) | 0.8069(0.0060) | 0.5950(0.0067) | |
DAE | Lasso(27) | 0.7009(0.0089) | 0.7997(0.0071) | 0.6007(0.0078) |
SCAD(62) | 0.6945(0.0058) | 0.7985(0.0047) | 0.5840(0.0060) | |
BAR(7) | 0.6945(0.0058) | 0.7985(0.0047) | 0.5840(0.0060) | |
GAIN | Lasso(10) | 0.7899(0.0067) | 0.8500(0.0053) | 0.7433(0.0075) |
SCAD(52) | 0.7918(0.0074) | 0.8501(0.0059) | 0.7505(0.0081) | |
BAR(9) | 0.7908(0.0069) | 0.8514(0.0055) | 0.7411(0.0078) |