Table 1c.

Publications relevant to ML methods used for cancer survival prediction.

Publication	ML method	Cancer type	No of patients	Type of data	Accuracy	Validation method	Important features
Chen Y-C et al. [50]	ANN	Lung cancer	440	Clinical, gene expression	83.5%	Cross validation	Sex, age, T_stage, N_stage LCK and ERBB2 genes
Park K et al. [26]	Graph-based SSL algorithm	Breast cancer	162,500	SEER	71%	5-fold cross validation	Tumor size, age at diagnosis, number of nodes
Chang S-W et al. [32]	SVM	Oral cancer	31	Clinical, genomic	75%	Cross validation	Drink, invasion, p63 gene
Xu X et al. [51]	SVM	Breast cancer	295	Genomic	97%	Leave-one-out cross validation	50-gene signature
Gevaert O et al. [52]	BN	Breast cancer	97	Clinical, microarray	AUC = 0.851	Hold-Out	Age, angioinvasion, grade MMP9, HRASLA and RAB27B genes
Rosado P et al. [53]	SVM	Oral cancer	69	Clinical, molecular	98%	Cross validation	TNM_stage, number of recurrences
Delen D et al. [54]	DT	Breast cancer	200,000	SEER	93%	Cross validation	Age at diagnosis, tumor size, number of nodes, histology
Kim J et al. [36]	SSL Co-training algorithm	Breast cancer	162,500	SEER	76%	5-fold cross validation	Age at diagnosis, tumor size, number of nodes, extension of tumor