EUVIMEDEUVIMED entdecken
Open Access · CC BY-NC 4.0

Deep learning-based prediction of acute pancreatitis severity from abdominal CT with multicenter external validation

Yanqi Xu, Brigitta Teutsch, Weicheng Zeng, Yang Hu, Shikhar Rastogi, Emmy Yuebi Hu, Isabella DeGregorio, Wan Fung Chui, Benjamin I Richter, Ryan Cummings, Julia E Goldberg, Edwin Mathieu und 16 weitere

Radiology Advances · 11.05.2026 · 3 (3)

DOI: 10.1093/radadv/umag020 ↗

Kurz gefasst

Fachartikel in der Zeitschrift Radiology Advances, online erschienen am 03.04.2026. Verfasst von Yanqi Xu und 27 weiteren Autor:innen. Beteiligte Einrichtung: Center for Data Science, New York University, New York, New York, 10011, United States. Die Arbeit wurde bisher 3-mal zitiert (Crossref) und nennt 38 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY-NC 4.0). Gefördert von: National Science Foundation, Society of Abdominal Radiology GE Healthcare Research and Innovation.

AbstractSchlagwörterBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

Background

Acute pancreatitis (AP) is a common gastrointestinal disease with a rising global incidence. While most cases are mild, severe AP (SAP) carries high mortality. Early and accurate severity prediction facilitates management optimization. However, existing clinical severity prediction models, such as Bedside Index of Severity in Acute Pancreatitis (BISAP) and Modified CT Severity Index (mCTSI), have modest accuracy and often rely on data unavailable at admission.

Purpose

This study proposes a deep learning (DL) model to predict AP severity using abdominal contrast-enhanced CT scans acquired within 24 hours of admission. Materials and Methods We collected 10 130 studies from 8335 patients across a multi-site U.S. health system and 3488 studies from public datasets. The DL model was trained in 2 stages: (1) self-supervised pretraining on 11 896 unlabeled studies and (2) fine-tuning on 550 labeled studies. Performance was evaluated against mCTSI on a hold-out internal test set (n = 100 patients) and against both mCTSI and BISAP on an external Hungarian AP registry (n = 518 patients).

Results

On the internal test set, the model achieved areas under receiver operating curve (AUROCs) of 0.888 (95% CI: 0.800-0.960, sensitivity 0.50, specificity 0.92) for SAP and 0.888 (95% CI: 0.819-0.946, sensitivity 0.75, specificity 0.85) for mild AP (MAP), outperforming mCTSI (P = .002). External validation showed AUROCs of 0.887 (95% CI: 0.825-0.941, sensitivity 0.73, specificity 0.88) for SAP and 0.858 (95% CI: 0.826-0.888, sensitivity 0.38, specificity 0.98) for MAP, surpassing mCTSI (P = .024) and BISAP (P = .002). In retrospective triage analysis, the model correctly identified 50%-73% of patients who progressed to SAP and 40%-73% of those with MAP.

Conclusion

The proposed DL model achieved performance comparable to or better than established prognostic tools and maintained robust external performance. These findings suggest that AI-assisted CT analysis may support early, automated risk stratification of AP.

Schlagwörter

Stichwörter der Autor:innen

acute pancreatitisartificial intelligencecontrast-enhanced computed tomographydeep learningseverity prediction

Autor:innen und Institutionen

  • Center for Data Science, New York University, New York, New York, 10011, United States.
  • Centre for Translational Medicine, Semmelweis University, Budapest, 1085, Hungary.
  • Department of Radiology, Medical Imaging Centre, Semmelweis University, Budapest, 1082, Hungary.
  • Institute for Translational Medicine, University of Pécs, Pécs, 7624, Hungary.
  • Gallatin School of Individualized Study, New York University, New York, New York , 10003, United States.
  • Department of Radiology, NYU Langone Health, New York, New York, 10016, United States.

ORCID-Profile: Yiqiu Shen

Förderung

  • National Science Foundation
  • Society of Abdominal Radiology GE Healthcare Research and Innovation

Zitieren

APA

Xu, Y., Teutsch, B., Zeng, W., Hu, Y., Rastogi, S., Hu, E. Y., DeGregorio, I., Chui, W. F., Richter, B. I., Cummings, R., Goldberg, J. E., Mathieu, E., Asare, B. A., Hegedűs, P., Gurza, K. B., Szabó, I. V., Tarján, H., Szentesi, A., Borbély, R., …, & Shen, Y. (2026). Deep learning-based prediction of acute pancreatitis severity from abdominal CT with multicenter external validation. Radiology Advances, 3(3). https://doi.org/10.1093/radadv/umag020

Vancouver

Xu Y, Teutsch B, Zeng W, Hu Y, Rastogi S, Hu EY, et al. Deep learning-based prediction of acute pancreatitis severity from abdominal CT with multicenter external validation. Radiology Advances. 2026;3(3). doi:10.1093/radadv/umag020

BibTeX
@article{Xu2026,
  author = {Xu, Yanqi and Teutsch, Brigitta and Zeng, Weicheng and Hu, Yang and Rastogi, Shikhar and Hu, Emmy Yuebi and DeGregorio, Isabella and Chui, Wan Fung and Richter, Benjamin I and Cummings, Ryan and Goldberg, Julia E and Mathieu, Edwin and Asare, Belinda Appiah and Hegedűs, Péter and Gurza, Kriszta-Beáta and Szabó, István Viktor and Tarján, Hedvig and Szentesi, Andrea and Borbély, Ruben and Molnár, Dorottya and Faluhelyi, Nándor and Vincze, Áron and Márta, Katalin and Hegyi, Péter and Lei, Qi and Gonda, Tamas and Huang, Chenchan and Shen, Yiqiu},
  title = {Deep learning-based prediction of acute pancreatitis severity from abdominal CT with multicenter external validation},
  journal = {Radiology Advances},
  year = {2026},
  volume = {3},
  number = {3},
  doi = {10.1093/radadv/umag020}
}
Kostenlos starten →