First author Country Patient no. Output marker Input markers Algorithm Results or conclusions Reibnegger, 1991 [54 ] Austria 42 Different liver disease ( , , and ) Neopterin, AST, ALT, and AST/ALT ratio Comparison with linear discriminant analysis and with CART and BP-ANN Compared with the other two techniques, BP-ANN showed a unique ability to detect features hidden in the input data. Gao, 2004 [55 ] China 3222 DM ( , ) Pulse, family history, nephropathy, waist-to-hip ratio, hypertension, exercise, and age BP-ANN vs. logistic regression BP-ANN could assimilate more complicated relationships and is better than logistic regression. Kim, 2005 [56 ] Korea 94 US images of donor liver with respect to macrosteatosis (moderate or severe , normal or mild ) ALP, GPT, GOT, γ -GGT, hepatorenal ratio of echogenicity, tail area ratio, and tail length of portal vein wall echogenicity BP-ANN vs. ordinal logistic regression The area under ROC curve of ANN was significantly greater than that of radiologists ( ). Liew, 2007 [57 ] China (Taiwan) 117 Gallbladder disease (with , no ) Gender, age, BMI, waist circumference, hip circumference, SBP, DBP, sugar, CHO, TG, UA, AST, ALT, Alb, WBC, haemoglobin, MCV, insulin, hsCRP, total protein, HDL-C, HbA1C, HOMA, acute inflammation, chronic inflammation, eosinophil, cholesterolosis, cholesterol polyp, and gastric metaplasia BP-ANN vs. logistic regression The average correct classification rate of ANNs was higher than that of logistic regression (97.14% vs. 88.2%) Chuang, 2011 [58 ] China (Taiwan) 166 Liver disease ( , ) HBsAg, HBeAg, anti-HBs, anti-HBe, anti-HBc, anti-HCV, AST, ALT, TBil, ALB, ALP, r-GT, AFP, gender, marriage, blood type, age, education, occupation, tattoo, smoking, chewing betel nut, alcohol, fatigue, sleep, nap, exercise, breakfast, vegetables, fruits, food date mark, food composition, low salt, healthy status, weight, physical discomfort, healthy examination, acupuncture, and blood donation A comparison of BP-ANN, CART, logistic regression, and DA BP-ANN was the best model for liver disease with the accuracy of 95%. The accuracy rates of CART, logistic regression, and DA were 91%, 86%, and 84%, respectively. Zhang, 2016 [59 ] China 120 Pathology diagnosis results of colorectal disease (colorectal , ) CEA, CA50, HSP60, CYFRA21-1, TPA, AFP, CA199, CA242, CA724, CA125, CA153, and UGT1A8 BP-ANN vs. forward logistic stepwise regression vs. SVM The AUROC of combined detection was 0.988, in logistic regression. The detection rate was 75% in the BP-ANN model. Fei, 2017 [60 ] China 79 PSMVT (positive or negative) Age, sex, Hct, PT, FBG, D-dimer, Ca, TG, AMY, APACHEII score, and Ranson score One-layer BP-ANN vs. logistic regression The ANN model was more accurate than logistic regression in predicting the occurrence of PSMVT. Ma, 2017 [61 ] China 575 BMI ( , ) Weight, height, age, fs-TG, fs-TC, and fs-GLU BP-ANN vs. multiple linear regression The BP-ANN models achieved higher prediction accuracy than linear regression. Shao, 2017 [62 ] China 288 Inoperable HCA Sex, age, stage, diameter, liver metastasis, ascites, prior abdominal surgery, comorbidity, and bismuth stage BP-ANN vs. logistic regression model The AUC of the BP-ANN had larger AUC than the multivariate logistic regression model ( ).