Table 1.

An overview of machine learning (ML) techniques in breast cancer diagnosis.

Reference	Computation Technique	Scope	Evaluation Results	Datasets
Acharya et al. [96]	Texture features + SVM	Breast cancer detection using thermal imaging	Accuracy = 88.10%, specificity = 90.48%, sensitivity = 85.71%	25 normal and 25 cancerous collected from Singapore General Hospital, Singapore
Maglogiannis et al. [97]	SVM	Diagnosis and prognosis	Accuracy = 96.91%, specificity = 97.67%, Sensitivity = 97.84%	Wisconsin prognostic breast cancer (WPBC)
Huang et al. [98]	SVM	Classifying benign and malignant	Accuracy = 94.4%, specificity = 94.4%, Sensitivity = 94.3%	250 images of benign breast tumors from 215 patients and carcinomas from 35 patients.
Wang et al. [7]	SVM	Reduce the diagnosis variance and increase the diagnostic accuracy of breast cancer	Variance = 97.89%, increase in accuracy by 33.34%	Wisconsin Breast Cancer, Wisconsin Diagnostic Breast Cancer, and the U.S. National Cancer Institute’s Surveillance, Epidemiology, and End Results (SEER) program
Abbass [101]	EANN	Diagnosis	Average accuracy = 0.981 ± 0.005	Wisconsin
Bhardwaj et al. [108]	Genetically optimized neural network	Classification	Accuracy of 98.24%, 99.63% and 100% for 50–50, 60–40, 70–30 training–testing partition, respectively	WBCD
Tourassi et al. [102]	CSNN	Diagnosis	CSNN ROC area index = 0.84 ± 0.02	500 private images
Çakır et al. [106]	Weka	Treatment methods	Accuracy = 92%	462 patients data
Karabatak [109]	Weighted Naïve Bayesian	Detection	Sensitivity = 99.11%, specificity = 98.25%, accuracy = 98.54%	WBCD
Şahan et al. [107]	Fuzzy + KNN	Diagnosis	Accuracy = 99.14%	WBCD
Bagui et al. [110]	Rank nearest neighbor	Diagnosis	Accuracy = 98.1%	WBCD
Chen et al. [111]	Rough set_SVM	Distinguishing benign breast tumour from malignant one	Accuracy = 99.41%, Sensitivity = 100%, specificity = 100%	WBCD
Polat et al. [112]	Least square SVM	Classification	Accuracy = 94.87%, Sensitivity = 96.42%, specificity = 95.86%	WBCD