Table 2.

Performance measures used

Name	Equation	Usage
Balanced accuracy (BAC)	$\frac{\mathit{SEN}+\mathit{SPEC}}{2}$	Accuracy measure that accounts for bias in the data.
Sensitivity (SEN)	$\frac{\mathit{TP}}{\mathit{TP}+\mathit{FN}}$	Model’s ability to correctly identify positives
Specificity (SPEC)	$\frac{\mathit{TN}}{\mathit{TN}+\mathit{FP}}$	Model’s ability to correctly identify negatives
Coverage (COV)	$\frac{\mathit{\text{in}}\mathit{\text{domain}}\mathit{\text{structures}}}{\mathit{\text{Number}}\mathit{\text{of}}\mathit{structures}}*100$	Model’s coverage of the given validation set representing the applicability of the model.