Retrospective Study
Copyright ©The Author(s) 2025.
World J Gastroenterol. Apr 7, 2025; 31(13): 104697
Published online Apr 7, 2025. doi: 10.3748/wjg.v31.i13.104697
Table 1 Basic characteristics, mean ± SD
Index
Total
Train set
Test set
P value
Liver stiffness13.2 ± 5.013.2 ± 5.312.9 ± 4.00.91
Spv speed35.3 ± 9.135.5 ± 9.334.5 ± 8.60.4
Platelet count132.9 ± 63.8131.3 ± 64.7139.4 ± 60.20.23
Model for end-stage liver disease30.2 ± 1.930.3 ± 1.829.9 ± 2.10.044
Creatinine75.5 ± 27.176.2 ± 29.672.5 ± 12.90.74
Alanine aminotransferase38.0 ± 39.036.4 ± 34.644.5 ± 52.80.046
Aspartate aminotransferase47.8 ± 62.144.7 ± 53.360.2 ± 88.40.057
Total bilirubin30.5 ± 34.530.7 ± 34.229.6 ± 36.00.43
Direct bilirubin16.2 ± 27.816.4 ± 27.615.5 ± 29.00.48
Indirect bilirubin14.2 ± 9.814.3 ± 8.914.0 ± 13.00.27
Alkaline phosphatase108.8 ± 55.9105.2 ± 53.1123.0 ± 64.40.027
Red blood cell count4.3 ± 0.84.3 ± 0.84.4 ± 0.70.35
White blood cell count5.3 ± 1.95.3 ± 1.95.3 ± 1.60.64
Age53.4 ± 12.353.6 ± 12.452.5 ± 11.80.57
Spleen stiffness15.1 ± 4.815.2 ± 4.914.8 ± 4.70.83
pv1.2 ± 0.21.2 ± 0.21.2 ± 0.20.59
pvspeed27.5 ± 6.727.2 ± 6.628.5 ± 7.20.14
splong13.3 ± 2.613.3 ± 2.513.4 ± 2.70.88
spwide4.6 ± 1.04.7 ± 0.94.6 ± 1.00.34
spv0.8 ± 0.20.8 ± 0.20.9 ± 0.20.41
Prothrombin time15.5 ± 3.215.7 ± 3.414.8 ± 2.30.045
Albumin39.7 ± 8.940.0 ± 8.938.6 ± 8.80.4
International normalized ratio1.2 ± 0.31.3 ± 0.31.2 ± 0.30.22
Sex, n (%)
Female84 (27.1)67 (27.0)17 (27.4)1
Male226 (72.9)181 (73.0)45 (72.6)-
Child-Pugh class, n (%)
1168 (54.2)131 (52.8)37 (59.7)0.29
2119 (38.4)100 (40.3)19 (30.6)-
323 (7.4)17 (6.9)6 (9.7)-
Collateral, n (%)
No244 (78.7)196 (79.0)48 (77.4)0.86
Yes66 (21.3)52 (21.0)14 (22.6)-
Severe EGV, n (%)
No186 (60.0)149 (60.1)37 (59.7)1
Yes124 (40.0)99 (39.9)25 (40.3)-
Table 2 Data in training cohort, mean ± SD
Index
Total
Low risk
High risk
P value
Liver stiffness13.2 ± 5.313.2 ± 5.913.3 ± 4.20.33
Spv speed35.5 ± 9.336.4 ± 9.234.1 ± 9.30.026
Platelet count131.3 ± 64.7128.0 ± 73.2136.1 ± 49.20.048
Model for end-stage liver disease30.3 ± 1.830.5 ± 2.030.0 ± 1.50.25
Creatinine76.2 ± 29.676.9 ± 36.875.2 ± 12.80.018
Alanine aminotransferase36.4 ± 34.640.0 ± 42.830.8 ± 14.1 0.88
Aspartate aminotransferase44.7 ± 53.343.8 ± 49.746.1 ± 58.50.25
Total bilirubin30.7 ± 34.228.3 ± 37.134.3 ± 29.2< 0.001
Direct bilirubin16.4 ± 27.614.5 ± 29.419.1 ± 24.5< 0.001
Indirect bilirubin14.3 ± 8.913.8 ± 9.814.9 ± 7.40.042
Alkaline phosphatase105.2 ± 53.1101.3 ± 50.0111.1 ± 57.30.37
Red blood cell count4.3 ± 0.84.3 ± 0.94.2 ± 0.70.82
White blood cell count5.3 ± 1.95.4 ± 2.15.3 ± 1.70.67
Age53.6 ± 12.452.3 ± 13.755.6 ± 10.00.025
Spleen stiffness15.2 ± 4.913.7 ± 4.517.3 ± 4.7< 0.001
pv1.2 ± 0.21.3 ± 0.21.2 ± 0.10.16
pvspeed27.2 ± 6.628.0 ± 6.826.0 ± 6.10.03
splong13.3 ± 2.513.6 ± 2.812.9 ± 2.00.11
spwide4.7 ± 0.94.5 ± 0.94.8 ± 0.90.012
spv0.8 ± 0.20.9 ± 0.20.8 ± 0.20.016
Prothrombin time15.7 ± 3.415.5 ± 3.217.8 ± 3.60.032
Albumin40.0 ± 8.940.7 ± 8.925.13 ± 6.50.015
International normalized ratio1.3 ± 0.31.2 ± 0.31.3 ± 0.40.25
Sex, n (%)
Female67 (27.0)26 (17.4)41 (41.4)< 0.001
Male181 (73.0)123 (82.6)58 (58.6)-
Child–Pugh class, n (%)
1131 (52.8)71 (47.7)60 (60.6)0.025
2100 (40.3)70 (47.0)30 (30.3)-
317 (6.9)8 (5.4)9 (9.1)-
Collateral, n (%)
No196 (79.0)120 (80.5)76 (76.8)0.53
Yes52 (21.0)29 (19.5)23 (23.2)-
Table 3 Statistical measures for all models
Model name
Area under curve
Accuracy
Precision
Recall
Specificity
F1 score
Positive predict value
Positive predict value
Random forest0.97 (0.94-1.00)0.93 (0.87-0.98)0.92 (0.85-1.00)0.87 (0.72-1.00)0.95 (0.92-1.00)0.88 (0.80-0.98)0.92 (0.85-1.00)0.91 (0.84-1.00)
AdaBoost0.94 (0.88-0.99)0.84 (0.76-0.94)0.85 (0.69-1.00)0.71 (0.53-0.90)0.91 (0.84-1.00)0.76 (0.62-0.91)0.88 (0.69-1.00)0.85 (0.74-0.95)
Artificial neural network0.77 (0.61-0.85)0.63 (0.52-0.74)0.51 (0.30-0.70)0.49 (0.31-0.73)0.69 (0.55-0.83)0.47 (0.32-0.67)0.46 (0.30-0.70)0.73 (0.56-0.85)
Decision tree0.79 (0.67-0.89)0.81 (0.69-0.90)0.74 (0.56-0.94)0.69 (0.50-0.86)0.85 (0.75-0.97)0.71 (0.55-0.86)0.74 (0.56-0.94)0.84 (0.71-0.93)
Extra tree0.97 (0.95-1.00)0.94 (0.87-0.98)0.91 (0.83-1.00)0.85 (0.71-1.00)0.91 (0.91-1.00)0.88 (0.80-0.98)0.93 (0.83-1.00)0.92 (0.84-1.00)
Gradient boosting machine0.92 (0.84-0.98)0.86 (0.75-0.94)0.83 (0.67-1.00)0.72 (0.55-0.92)0.91 (0.83-1.00)0.76 (0.64-0.91)0.84 (0.67-1.00)0.84 (0.75-0.96)
K-nearest neighbors0.89 (0.80-0.96)0.82 (0.71-0.90)0.73 (0.54-0.90)0.72 (0.55-0.91)0.83 (0.72-0.95)0.68 (0.57-0.86)0.73 (0.54-0.90)0.85 (0.72-0.95)
Lightgbm0.96 (0.91-0.99)0.86 (0.79-0.95)0.81 (0.73-1.00)0.74 (0.54-0.92)0.94 (0.87-1.00)0.79 (0.65-0.92)0.85 (0.74-1.00)0.86 (0.76-0.95)
Logistic regression0.73 (0.60-0.85)0.67 (0.55-0.77)0.54 (0.33-0.74)0.61 (0.41-0.82)0.68 (0.53-0.83)0.58 (0.38-0.73)0.58 (0.33-0.74)0.76 (0.61-0.89)
Support vector machine0.74 (0.62-0.86)0.61 (0.50-0.73)0.47 (0.23-0.72)0.34 (0.15-0.56)0.77 (0.64-0.90)0.39 (0.19-0.58)0.47 (0.23-0.72)0.63 (0.52-0.80)
Extreme gradient boosting0.96 (0.92-0.99)0.86 (0.81-0.97)0.87 (0.74-1.00)0.78 (0.62-0.95)0.94 (0.86-1.00)0.83 (0.70-0.94)0.84 (0.74-1.00)0.88 (0.78-0.98)