Copyright ©The Author(s) 2021.
World J Gastroenterol. Sep 14, 2021; 27(34): 5715-5726
Published online Sep 14, 2021. doi: 10.3748/wjg.v27.i34.5715
Table 1 Hepatitis detection based on data mining
Sample size (type)
Evaluation index
1Predicting incidence of hepatitis AANN; ARIMAN/A (CDC data)ANN: Correlation coefficient 0.71; ARIMA: Correlation coefficient 0.66[12]
2Predicting incidence of hepatitis BARIMA; ElmanNN486983 cases (data from health commission)ARIMA: RMSE 0.94, MAE 0.81; ElmanNN: RMSE 0.89, MAE 0.70[13]
3Forecasting incidence of hepatitis BHybrid method (combing GM and BP-ANN)10486959 cases (data from health ministry)R 0.9495, RMSE 4.863 × 103, MAE 3.9704 × 104[14]
4Prediction of incidence of hepatitis EARIMA; SVM; LSTMN/A (CDC data)ARIMA: RMSE 0.022, MAE 0.018; SVM: RMSE 0.0204, MAE 0.0167; LSTM: RMSE 0.01, MAE 0.011[15]
5Automated classification of the different stages of hepatitis BADHB-ML-MFIS expert system52 patients (serological data)Overall accuracy: 0.922; No hepatitis accuracy: 1; Due to infection accuracy: 0.75; Acute HBV accuracy: 0.95; Chronic HBV accuracy: 0.91[16]
6Analyzing HBV infection from normal blood samplesPolynomial function; RBF119 serum samples from HBV infected patients (Raman spectroscopy data)Polynomial kernel (order-2): Quadratic programming/least squares: Accuracy 98%, precision 97%, sensitivity 100%, specificity 95%; RBF kernel (RBF sigma-2): Quadratic programming: accuracy 94%, precision 90%, sensitivity 100%, specificity 87%; RBF kernel (RBF sigma-2): Least squares: Accuracy 95%, precision 92%, sensitivity 100%, specificity 90%[8]
7Rapidly screening hepatitis B from non-hepatitis BLSTM1134 blood samples (Raman spectroscopy data)Accuracy 97.32%, sensitivity 97.87%, specificity 96.77%, precision 96.84%[17]
8Finding undiagnosed patients with hepatitis C infectionLogistic regression; Gradient boosting trees; Gradient boosting trees with temporal variables; Stacked ensemble; Random forest9721923 patients (data from the patient’s medical history)The stacked ensemble had a specificity of 0.99 and precision of 0.97 at a recall level of 0.50[19]
9Predicting hepatitis C virus progression among veterans CS Cox modellongitudinal Cox model; CS boosting modelLongitudinal-boosting model72683 CHC individuals (VHA data)CS Cox model: Concordance 0.746; Longitudinal Cox model: Concordance 0.764; CS boosting model: Concordance 0.758; Longitudinal-boosting model: Concordance 0.774[20]
10Forecasting response to IFN plus RIB treatment in HCV patients ANN300 patients (serological data)The diagnostic accuracy rose from 52% (ANN 2) to 70% (ANN 6)[21]
Table 2 Hepatitis or hepatitis associated lesion detection based on radiology
Algorithms (model)
Sample size (type)
Evaluation index
1Predicting clinical severity in AAH patientsRandom forest; Convolutional neural network69 cases (CT texture features)Accuracy: 82.4% of RFE-RF in the test set; Accuracy: 70% of CNN in the test set[26]
2Assessing significant liver fibrosis by multiparametric ultrasomics dataAdaboost; Random forest; SVM (multiparametric ultrasomics)144 HBV infected patients (multiparametric ultrasomics)AUROC: 0.85 ± 0.01 of Adaboost, random forest, SVM in multiparametric ultrasomics including conventional ultrasomics, ORF and CEMF[9]
3Grading liver fibrosisInception-V3 network (transfer learning) 466 patients (multimodal ultrasound)AUCs of TL in GM + EM reached 0.950, 0.932, and 0.930, respectively, for grading S4, ≥ S3, and ≥ S2an[28]
4Predicting cirrhosisLASSO (radiomics nomogram)144 cases of HBV patients (CT features and clinical factors)AUROC: 0.915 in the training cohort, 0.872 in the validation cohort, overall correctly classified rate of 82.0%[29]
5Differentiating hepatic fibrosis’ gradeRFC (CTTA-based models); SVM (CTTA-based models)30 fibrosis patients (CT texture features)Train AUC 0.95 in RFC (model 1); Test AUC 0.90 in RFC (model 1); Train AUC 0.88 in SVM (model 2); Test AUC 0.76 in SVM (model 2)[30]
6Assessing liver fibrosis severityA prototype convolutional neural network558 cases (CT images)AUCs were 0.82, 0.85, and 0.88 of VolL/VolS in diagnosing advanced fibrosis, cirrhosis, and decompensated cirrhosis in the whole study population[31]
7Staging liver fibrosisConvolutional neural network 634 fibrosis patients (MR images and MR/virus)AUCs were 0.84, 0.84, and 0.85 of the model full for diagnosing F4, ≥ F3, and ≥ F2 in the test set, respectively[34]
8Assessing liver fibrosis in chronic hepatitis BConvolution neural network (DLRE)398 HBV patients (shear wave elastography)AUCs of DLRE 1.00, 0.99, and 0.99 for classifying F4, ≥ F3, and ≥ F2 in the training set and 0.97, 0.98, and 0.85 in the validation set[35]
9Diagnosing FNH from HCC in the non-cirrhotic liverLASSO (radiomics nomogram)156 patients (CT images and clinical factors)Accuracy: 92.4% in the training set, 89.2% in the validation set[38]
10Diagnosing HCCLASSO (radiomics signature)211 patients (MR images)AUROC: 0.861 in the training set, 0.810 in the validation set[39]
11Preoperative prediction of HCC gradeLASSO (combined model with clinical factors and radiomics signature)170 HCC patients (MR images and clinical factors)AUROC: 0.742, 0.786, and 0.800 based on T1WI images, T2WI images, and combined T1WI and T2WI images in the combined model[41]
12Predicting MVI risk in HBV-related HCC preoperativelyLASSO (radiomics nomogram)304 HCC patients (CT images and AFP)AUROC: 0.846 in the training set, 0.844 in the validation set[43]
13Preoperative prediction of MVI in HCC patients LASSO (combined model)157 HCC patients (CT images and clinical factors)AUROC: 0.835 in the training dataset, 0.801 in the validation dataset[44]
14Predicting risk of HE complicated by hepatitis B related cirrhosisLASSO (integrated model of radiomics and clinical features)304 cirrhosis patients (CT images and clinical factors)Accuracy: 0.93 in the training cohort, 0.83 in the testing cohort[45]
15Predicting liver failure in cirrhotic patients with HCC after major hepatectomyLASSO (integrated radiomics-based mode)101 HCC patients (MR images and clinical factors)Accuracy: 0.802 in radiomics-based model[47]