Table 1.

Summary of datasets used in experiments (sorted by the no. of subjects in ascending order)

Dataset	No. of subjects (pos/neg)	Var. type	No. of var.	Task
GSE 27899IL [15]	10/10	DNA methylation	27578	diagnose ulcerative colitis
Prostate cancer [16]	14/9	microarray gene expression	15009	diagnose prostate cancer
Colon cancer [16]	15/11	microarray gene expression	15009	diagnose colon cancer
Lung cancer [16]	20/7	microarray gene expression	15009	diagnose lung cancer
Breast cancer [16]	17/15	microarray gene expression	15009	diagnose breast cancer
Leukemia [17]	11/27	microarray gene expression	7129	diagnose leukemia
GSE 29490 [18]	20/7	DNA methylation	26916	diagnose colorectal carchinoma
GSE 25869 [19]	14/9	DNA methylation	27570	diagnose gastric cancer
Breast tissue [20]	21/85	impedance measurements	9	diagnose breast tumor
LSVT [21]	42/84	wavelet and frequency based measurements	310	assessment of treatments in Parkinson
DLBCL [22]	88/72	microarray gene expression	715	diagnose DLBCL
Myeloma [23]	137/36	microarray gene expression	12625	diagnose bone lesions
Parkinsons [24]	147/48	vocal based measurements	22	diagnose Parkinson disease
Wdbc [25]	212/357	nuclear feature from image	30	diagnose breast tumor
Indian liver [26]	414/165	biochemistry based measurements	9	diagnose liver disease
Pima Indians diabetes [27]	268/500	clinical measurements	8	diagnose diabetes