Gastroenterology Meets Machine Learning: Status Quo and Quo Vadis

Table 2

Overview of performance metrics.

Metric	Formula	Description
Sensitivity (SV)		It measures the portion of positives that are correctly identified (performance measure of the whole positive of a dataset)
Specificity (SP)		It measures the portion negatives that are correctly identified (performance measure of the whole negative part of a dataset)
Positive Predictive Value (PPV)		The ratio of correctly diagnosed positives to the total of identified positives
Negative Predictive Value (NPV)		The ratio of correctly diagnosed negatives to the total of identified negatives
Accuracy (ACC)		The ratio of correctly diagnosed cases to the total diagnosed cases ( the overall performance measure)
Area under the receiver operating characteristics curve (AUC-ROC)	Graphical plot [13]	In a Receiver Operating Characteristics (ROC) curve the sensitivity is plotted in function of the false positive rate (100-Specificity) for different cut-off points of a parameter. Each point on the ROC curve represents a sensitivity/specificity pair corresponding to a particular decision threshold. The area under the ROC curve (AUC-ROC) is a measure of how well a parameter can distinguish between two diagnostic groups (diseased/normal)

TP: true positive (number of positive cases correctly detected).
TN: true negative (number of negative cases correctly detected).
FP: false positive (number of negative cases incorrectly detected as positive).
FN: false negative (number of positive cases incorrectly detected as negative).