Table 1.

Algorithms of Machine Learning used in Cancer Diagnosis

Omics types	Data type	Analyzing tools	Cancer types
Non-Omics	Clinicopathological	Neural Networks, Decision Tree, Logistic Regression	Breast Cancer [122]
Non-Omics	Clinicopathological	ANN, SVM, semi-supervised learning	Breast Cancer [123]
Non-Omics	Clinicopathological	ELM, Neural Networks, Genetic Algorithm	Prostate Cancer [124]
Non-Omics	Clinicopathological	Two-stage fuzzy neural network	Prostate Cancer [125]
Non-Omics	Clinicopathological	Linear Regression, Support Vector Machines, Gradient Boosting Machines, Decision Tree,	Lung Cancer [126]
Non-Omics	Radiomics	DT, Adaboost, RUSBoost algorithm, Matthews correlation coefficient	Gliomas [127]
Non-Omics	MR Images and Clinicopathological	SVM, bagged SVM, KNN, Adaboost, RF, GBT	Bladder Cancer [128]
Single Omics	Genomics	SVM, log-rank test, Cox hazard regression model, genetic algorithm,	Ovarian Cancer [129]
Single Omics	Genomics	Pathway Based Deep Clustering Model, R89-restricted Boltzmann Machine, Deep Belief Network	GBM and Ovarian Cancer [130]
Single Omics	Metabolomics	SVM, Naive Bayes, RF, KNN, C4.5, PLS-DA, LASSO,	Colonic Cancer [131]
Single Omics	Metabolomics	SVM, RF, RPART, LDA, generalized boosted model	Breast Cancer [132]
Non-Omics and Single Omics	Clinicopathological and Genomics	Ensemble model SVM, ANN, KNN, ROC and calibration slope	Breast Cancer [133]
Non-Omics and Single Omics	Clinicopathological and Genomics	SVM, ROC	Prostate Cancer [134]
Non-Omics and Single Omics	Histopathology images and proteomics	RF, CNN	Kidney Cancer [134]
Multi-Omics	Genomics, Transcriptomics and proteomics	Random Forest Regressor, Wilcoxon signed ranked test, gene-specific model, Generic model, trans issue model and RF. l	Breast and Ovarian Cancer [135]