Table 1a.

Publications relevant to ML methods used for cancer susceptibility prediction.

Publication	Method	Cancer type	No of patients	Type of data	Accuracy	Validation method	Important features
Ayer T et al. [19]	ANN	Breast cancer	62,219	Mammographic, demographic	AUC = 0.965	10-fold cross validation	Age, mammography findings
Waddell M et al. [44]	SVM	Multiple myeloma	80	SNPs	71%	Leave-one-out cross validation	snp739514, snp521522, snp994532
Listgarten J et al. [45]	SVM	Breast cancer	174	SNPs	69%	20-fold cross validation	snpCY11B2 (+) 4536 T/C snpCYP1B1 (+) 4328 C/G
Stajadinovic et al. [46]	BN	Colon carcinomatosis	53	Clinical, pathologic	AUC = 0.71	Cross-validation	Primary tumor histology, nodal staging, extent of peritoneal cancer