Table 10.

Referenced literature that considered Machine Learning on various disease diagnoses.

Study	Contributions	Algorithm	Dataset	Data Type	Performance Evaluation
[120]	Classify pediatric colonic inflammatory bowel disease subtype	RF	74 Privately owned cases	Image	Accuracy—100%
[121]	classification of liver diseases	svm	ILPD and BUPA	Tabular	Accuracy—90–92%, Sensitivity—89–91%, F1-score—94–94.3%
[122]	Hypertension	LR and ANN	BRFSS	Tabular	Accuracy—72%, AUC > 0.77
[123]	Brain tumor diagnostic	CNN	Brain tumor challenge websites and MRI centers	Image	Accuracy—90–99%
[124]	Brain tumor segmentation for multi-modality MRI	RF	MICCAI, BraTS 2013	Image	88% disc overlap
[125]	Melanoma detection with dermoscopic images	SVM with color and feature extractor	PH2	Image	Accuracy—96%
[126]	Melanoma skin cancer detection	NB, DT, and KNN	MED-NODE	Image	DT (Accuracy—82.35%)
[127]	Skin cancer detection with infrared thermal imaging	Ensemble learning and DL		Image	Precision—0.9665, Recall—0.9411, F1-score—0.9536, ROC-AUC—0.9185
[128]	Hepatocellular carcinoma	InceptionV3	Genomic data commons databases	Image	Accuracy—89–96%
[129]	Identification of liver cancer	Watershed gaussian based DL (WGDL)	Privately owned	Image	Accuracy—99.38%
[130]	Hepatocellular carcinoma (HCC) postoperative death outcomes	RF, Gradient boosting, Gbm, LR, DT	BioStudies database	Tabular	AUC—0.803 (RF)