Journal DOI 10.68956/journal.human-performance-futures

Creative Commons source reading · Machine learning for performance

Artificial intelligence in gangrenous cholecystitis: advances in risk factor identification and preoperative prediction—a scoping review

Ping Wang; Xingyu Chen; Tianjiao Hao; Jisong Chen

Originally published in Front Surg · 2026-09-03

From the article

Selected source text. JournalOS removes markup and shortens excerpts where indicated. The full article provides the complete context.

Abstract

BackgroundGangrenous cholecystitis (GC) is a severe pathological subtype of acute cholecystitis, yet its preoperative diagnostic rate remains below 10%. Conventional scoring systems based on logistic regression demonstrate limited predictive performance. Artificial intelligence (AI) approaches may offer improved risk stratification, but the evidence base remains limited.MethodsA scoping review was conducted across PubMed, Web of Science, Embase, and CNKI databases for publications from January 2020 to June 2026. The search combined MeSH terms and free-text keywords related to gangrenous cholecystitis and artificial intelligence. After screening 412 records, 18 studies were included: 3 direct GC AI prediction studies, 3 traditional GC scoring systems, and 12 indirect or methodologically related studies. A narrative synthesis was…

Conclusions

This scoping review examined the application of AI technologies in GC risk factor identification and preoperative prediction. A comparison of traditional scoring systems and AI models is provided in Table 3. Three studies directly addressed AI-based GC prediction, all employing retrospective designs. Machine learning models using structured clinical data achieved temporal or external validation AUCs of 0.818–0.944, while deep learning models integrating non-contrast and contrast-enhanced CT achieved independent validation AUCs of 0.879 and 0.887 (training-set AUC 0.965). Explainable AI methods identified model-associated predictors, including hypokalemia/hyponatremia, though these findings require pathophysiological validation and should not be interpreted as causal risk factors. However, the evidence base remains insufficient for…

Editorial reading guide

  • What data created and tested the model, and was evaluation independent?
  • What is the cost of a false positive, false negative or out-of-distribution decision?