Table 5.

Referenced literature that considered machine-learning-based breast cancer disease diagnosis.

Study	Contributions	Algorithm	Dataset	Data Type	Performance Evaluation
[14]	Breast cancer	NB, BN, RF and DT (C4.5)	BCSC	Image	ROC—0.937 (BN)
[66]	Classification of breast density and mass	SVM	Mini-MIAS, INBreast	Image	Mini-MIAS: Accuracy—99%, AUC—0.9325
[67]	Classify vector features as malignant or non-malignant	SVM	IRMA, DDSM	Image	IRMA: Sensitivity—99%, Specificity—99%, DDSM: Sensitivity—97%, Specificity—96%
[68]	Classification of breast cancers by tumor size	LR-ANN	156 Privately owned cases	Image	Accuracy—81.8%, Sensitivity—85.4%, Specificity—77.8%, AUC—0.855
[69]	CAD tumor	Binary-LR	18 Privately owned cases	Image	Accuracy—80.39%
[70]	Differentiating malignant and benign masses	NB, LR-AdaBoost	246 Privately owned image	Image	Sensitivity—90%, Specificity—97.5%, AUC—0.98