Table 4 Results of models published in previous studies. Used as reference.

From: Development of a novel deep learning method that transforms tabular input variables into images for the prediction of SLD

Models

Accuracy

Sensitivity

Specificity

Recall macro

AUC ROC

49 LR German population

–

–

–

–

0.876

LR Pomerania population

–

–

–

–

0.860

HSI German population

–

–

–

–

0.841

HSI Pomerania population

–

–

–

–

0.782

50 XGB

0.8977

0.9247

0.8890

0.9069*

0.9690

39 FLI/LR

–

0.87

0.61

0.64

0.86

0.755*

0.735*

0.85

60 LR

0.691

0.745

0.651

0.695*

0.733

53 XGB

0.9415

0.9091

0.9521

0.9306*

0.9306

43 RF

0.8648

0.8716

0.8589

0.8653*

0.925

  1. *Values calculated by us from the results displayed, using the formula of recall macro: (Sensitivity + Specificity)/2.
  2. Datasets used in some previous studies are different and not publicly available.
Back to article page