Radiologist-AI Collaboration for Ischemia Diagnosis in Small-Bowel Obstruction: Multicentric Development and External Validation of a Multimodal Deep Learning Model
- 29 April 2026
- journal article
- research article
- Published by Springer Nature in Journal of Imaging Informatics in Medicine
- p. 1-11
Abstract
This study aims to develop and externally validate a multimodal AI model for detecting ischemia complicating small-bowel obstruction (SBO). We combined 3D CT data with routine laboratory markers (C-reactive protein, neutrophil count) and, optionally, radiology report indication/history text. From two centers, 1350 CT examinations were curated; 771 confirmed SBO scans were used for model development with patient-level splits. Ischemia labels were defined by surgical confirmation within 24 h of imaging. Models (MViT, ResNet-101, DaViT) were trained as unimodal and multimodal variants. External testing was used for 66 independent cases from a third center. Four radiologists (two residents and two experts) read the test set with and without AI assistance. Performance was assessed using AUC, sensitivity, specificity, and 95% bootstrap confidence intervals; predictions included a confidence score. The image-plus-laboratory model performed best on external testing (AUC 0.69 [0.59–0.79], sensitivity 0.89 [0.76–1.00], and specificity 0.44 [0.35–0.54]). Adding report text improved internal validation but did not generalize externally; image + text and full multimodal variants did not exceed image + laboratory performance. Across readers, baseline AUC ranged from 0.496 [0.361–0.640] to 0.745 [0.589–0.875] and increased with reader experience. With AI assistance, AUC ranged from 0.565 [0.419–0.717] to 0.845 [0.714–0.952] and from 0.519 [0.373–0.669] to 0.845 [0.708–0.954] when confidence scores were displayed, showing consistent but non-significant changes whatever the experience level. A multimodal model combining CT and lab data surpassed unimodal approaches for 24-h ischemia detection; as a triage-support tool, it showed a consistent but non-significant improvement in radiologist performance.Keywords
This publication has 31 references indexed in Scilit:
- Evolving Management Strategies in Patients with Adhesive Small Bowel Obstruction: a Population-Based AnalysisJournal of Gastrointestinal Surgery, 2018
- The future of radiology augmented with Artificial Intelligence: A strategy for successEuropean Journal of Radiology, 2018
- Value of MDCT and Clinical and Laboratory Data for Predicting the Need for Surgical Intervention in Suspected Small-Bowel ObstructionAmerican Journal of Roentgenology, 2017
- Review of Small-Bowel Obstruction: The Diagnosis and When to WorryRadiology, 2015
- Value of CT findings to predict surgical ischemia in small bowel obstruction: A systematic review and meta-analysisEuropean Radiology, 2015
- Serum Procalcitonin for Predicting the Failure of Conservative Management and the Need for Bowel Resection in Patients with Small Bowel ObstructionJournal of the American College of Surgeons, 2013
- Evaluation and management of small-bowel obstructionJournal of Trauma and Acute Care Surgery, 2012
- Small Bowel Obstruction: Outcome and Cost Implications of Admitting ServiceThe American Surgeon™, 2010
- CT of Small-Bowel Ischemia Associated with Obstruction in Emergency Department Patients: Diagnostic Performance EvaluationRadiology, 2006
- CT diagnosis of small-bowel obstruction: efficacy in 60 patients.American Journal of Roentgenology, 1992