BPG is committed to discovery and dissemination of knowledge
Retrospective Study
Copyright: ©Author(s) 2026.
World J Gastroenterol. Jul 7, 2026; 32(25): 119071
Published online Jul 7, 2026. doi: 10.3748/wjg.119071
Table 1 Spectral computed tomography enterography scanning parameters
Manufacturer
General-electric
General-electric
Scanner modelRevolution CTDiscovery CT750
SequenceAxialAxial
Gantry rotation time (second)0.30.3
Tube voltage (kV)80-14080-140
Tube current (mA)150-300150-300
Detector collimation (mm)256 × 0.62564 × 0.625
Matrix512 × 512512 × 512
Pitch1.375:11.375:1
Slice thickness (mm)5.05.0
Slice spacing (mm)5.05.0
Table 2 Clinical factors in the training and testing sets, mean ± SD
Clinical factorsIleal (n = 102)
Ileocolonic (n = 167)
Train (n = 71)
Test (n = 31)
P value
Train (n = 116)
Test (n = 51)
P value
Gender0.3870.989
Male56228236
Female1593415
Age at CD diagnosis (year), median IQR28 (20-38)30 (21-35)0.95124 (19-31)27 (20-39)0.126
Disease duration (day), median IQR5 (2-23)5 (1-58)0.8354 (2-16.75)3 (1-15)0.446
CRP at baseline (mg/L), median IQR5.27 (2.17-17.06)4.6 (1.30-19.91)0.99113.29 (3.19-36.30)9.49 (4.25-25.20)0.541
ESR at baseline (mm/hour), median IQR16.25 (12.00-25.00)22.00 (7.00-36.00)0.55530.40 (17.63-43.75)16.00 (11.50-31.00)< 0.001
WBC at baseline (× 109/L)6.32 ± 2.096.31 ± 2.290.9777.34 ± 2.236.46 ± 1.780.02
Alb at baseline (g/L)39.66 ± 4.6138.65 ± 4.730.31337.68 ± 5.8837.36 ± 4.790.74
FC at baseline (μg/g), median IQR762.58 (394.78-1085.72)774.94 (429.66-1137.76)0.9521086.68 (850.76-1335.94)1019.20 (798.78-1263.00)0.078
Perianal involvement0.6410.667
-40194518
+31127133
Smoking status at diagnosis0.8580.46
-642911549
+7212
Previous steroids or immunomodulators use0.8580.478
046218232
12192616
24183
Montreal behavior0.3550.811
Nonstricturing, nonpenetrating (B1)47209841
Stricturing (B2)76116
Penetrating (B3)17574
HBI at baseline, median IQR2 (1-4)2 (1-5)0.284 (1-6)3 (1-5)0.425
MH0.8710.971
MH31133917
Non-MH40187734
Table 3 Positive results of univariate and multivariate logistic regression analysis for predicting mucosal healing in Crohn’s disease
FeaturesIleal
Ileocolonic
Univariate
Multivariate
Univariate
Multivariate
OR
95%CI
P value
OR
95%CI
P value
OR
95%CI
P value
OR
95%CI
P value
Gender0.2500.064-0.9830.0470.0790.006-1.0610.0551.9080.834-4.3640.126
Age at CD diagnosis1.0290.989-1.0710.1551.0090.968-1.0530.662
Disease duration (day)1.0000.997-1.0030.8751.0010.998-1.0030.669
CRP at baseline1.0020.971-1.0340.8961.0181.000-1.0360.0511.0100.987-1.0320.397
ESR at baseline0.9720.931-1.0150.1951.0000.981-1.0190.997
WBC at baseline0.8260.650-1.0490.1171.0780.904-1.2850.404
Alb at baseline0.8800.785-0.9860.0230.8930.754-1.0580.0410.9970.934-1.0650.931
FC at baseline0.9990.998-1.0000.1420.9990.998-1.0000.0150.9990.998-1.0010.031
Perianal involvement0.4430.170-1.1590.0950.2470.051-1.1870.0811.3520.617-2.9650.451
Smoking status at diagnosis1.0370.214-5.0160.964828993669.3580.0001.000
Previous steroids or immunomodulators use3.4911.096-11.1240.1041.4850.559-3.9480.711
Montreal behavior1.0580.343-3.2620.7523.1870.369-27.5700.566
HBI at baseline0.7990.642-0.9660.0590.9350.629-1.3890.7401.0900.942-1.2620.247
Rad score1.1731.010-1.3630.0373.8201.541-9.4730.004
Pat score6.1352.282-16.492< 0.0013.9922.198-7.250< 0.001
Table 4 Results of all models predictive ability for predicting mucosal healing in Crohn’s disease
Models

AUC (95%CI)
Accuracy
Sensitivity
Specificity
PPV
NPV
Model 1Train0.921 (0.860-0.982)0.8590.9250.7740.8410.889
Test0.799 (0.641-0.957)0.7740.7780.7690.8240.714
Model 2Train0.724 (0.616-0.833)0.6900.6500.7420.7650.622
Test0.669 (0.486-0.851)0.6770.6670.6920.7500.600
Model 3Train0.931 (0.874-0.989)0.8730.8750.8710.8970.844
Test0.863 (0.703-1.000)0.7420.6110.9230.9170.632
Model 4Train0.773 (0.656-0.889)0.7470.7250.7740.8060.895
Test0.731 (0.533-0.928)0.6450.6110.6920.7330.615
Model 5Train0.910 (0.845-0.975)0.8450.9250.7420.8220.885
Test0.872 (0.744-1.000)0.8070.7780.8460.8750.733
Model 6Train0.980 (0.955-1.000)0.9440.9750.9030.9290.966
Test0.915 (0.808-1.000)0.7740.8330.6920.7900.750
Model 7Train0.860 (0.778-0.942)0.8030.9250.8710.8820.896
Test0.812 (0.668-0.956)0.7740.9440.7690.8240.833
Model ATrain0.873 (0.803-0.944)0.8190.8050.8460.9120.659
Test0.827 (0.716-0.938)0.7060.6180.8820.9130.647
Model BTrain0.756 (0.674-0.839)0.6750.7140.6150.7220.522
Test0.636 (0.518-0.754)0.6180.4120.8820.6180.429
Model CTrain0.951 (0.915-0.988)0.9220.9610.8460.9250.917
Test0.866 (0.748-0.984)0.8040.8820.6470.8330.733
Model DTrain0.739 (0.636-0.842)0.7760.8960.7440.7930.724
Test0.687 (0.501-0.873)0.7650.8820.7650.7900.692
Model ETrain0.919 (0.870-0.968)0.8360.7920.9230.9530.784
Test0.819 (0.682-0.957)0.7200.6970.7650.8520.667
Model FTrain0.951 (0.916-0.987)0.8970.8960.8970.9450.814
Test0.922 (0.843-1.000)0.8800.9090.8240.9090.824
Model GTrain0.950 (0.912-0.988)0.8710.8440.9230.9560.750
Test0.908 (0.822-0.994)0.8200.7880.8820.9290.682
Table 5 Delong test comparison between models of area under the curves in the testing set
ModelsP value
Clinical
Radiomics
Pathomics
Radiomics and clinical
Pathomics and clinical
Radiomics and pathomics
Combined
ClinicalIleal0.2590.1210.6230.0290.0030.001
Ileocolonic0.0040.0060.6350.012< 0.001< 0.001
RadiomicsIleal0.2590.4960.4950.2270.0940.114
Ileocolonic0.0040.6260.0870.9050.2090.297
PathomicsIleal0.1210.4960.2450.8900.5030.203
Ileocolonic0.0060.6260.1120.2180.4460.464
Radiomics and clinicalIleal0.6230.4950.2450.1220.0440.119
Ileocolonic0.6350.0870.1120.2340.0070.017
Pathomics and clinicalIleal0.0290.2270.8900.1220.3211.000
Ileocolonic0.0120.9050.2180.2340.1420.107
Radiomics and pathomicsIleal0.0030.0940.5030.0440.3211.000
Ileocolonic< 0.0010.2090.4460.0070.1420.629
CombinedIleal0.0010.1140.2030.1191.0001.000
Ileocolonic< 0.0010.2970.4640.0170.1070.629


Write to the Help Desk