BPG is committed to discovery and dissemination of knowledge
Observational Study
©The Author(s) 2025.
World J Gastroenterol. Sep 14, 2025; 31(34): 108807
Published online Sep 14, 2025. doi: 10.3748/wjg.v31.i34.108807
Table 3 Predictive accuracy of computed tomography feature-based models with and without biochemical parameters
Model
Input data
AUC (95%CI)
Accuracy (%)
Sensitivity (%)
Specificity (%)
Image-only modelPara-umbilical CT feature maps0.78 (0.72-0.84)63.960.066.7
Multimodal modelCT features + γ-GTP, total bilirubin0.83 (0.78-0.88)68.570.067.8

  • Citation: Miida S, Kamimura H, Fujiki S, Kobayashi T, Endo S, Maruyama H, Yoshida T, Watanabe Y, Kimura N, Abe H, Sakamaki A, Yokoo T, Tsukada M, Numano F, Kashimura T, Inomata T, Fuzawa Y, Hirata T, Horii Y, Ishikawa H, Nonaka H, Kamimura K, Terai S. Image analysis of cardiac hepatopathy secondary to heart failure: Machine learning vs gastroenterologists and radiologists. World J Gastroenterol 2025; 31(34): 108807
  • URL: https://www.wjgnet.com/1007-9327/full/v31/i34/108807.htm
  • DOI: https://dx.doi.org/10.3748/wjg.v31.i34.108807

Write to the Help Desk