©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
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 model | Para-umbilical CT feature maps | 0.78 (0.72-0.84) | 63.9 | 60.0 | 66.7 |
| Multimodal model | CT features + γ-GTP, total bilirubin | 0.83 (0.78-0.88) | 68.5 | 70.0 | 67.8 |
- 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