Application of Artificial Intelligence in Pancreatic Cyst Management: A Systematic Review
Anwendung von Künstlicher Intelligenz in der Behandlung von Pankreaszysten: ein systematisches Review
Cancers · 02.08.2025 · 17 (15) · 2558
DOI: 10.3390/cancers17152558 ↗Auf einen Blick
31 Studien zeigen ein hohes Potenzial von KI-Modellen für Diagnose und Risikostratifizierung von Pankreaszysten. Die Median-AUC lag bei 0,912.
Fragestellung
Wie gut sind KI-, ML- und DL-Modelle für Diagnose, Klassifikation, Prognose und Management von Pankreaszysten?
Methode
Systematisches Review nach PRISMA; Suche in PubMed, EMBASE, Scopus und Cochrane Library bis März 2025; Bewertung mit PROBAST und TRIPOD.
Ergebnisse
847 Treffer, 31 eingeschlossene Studien. 27 waren retrospektiv, 30 zu prädiktiven Anwendungen; mediane AUC 0,912, 55 % mit AUC ≥ 0,80, 11 Studien besser als Kliniker:innen oder Leitlinien.
Einschränkungen
Hohes Verzerrungsrisiko in 93,5 % der Studien; nur 10 Studien mit externer Validierung; TRIPOD-Übereinstimmung im Mittel 48 %.
Schlussfolgerung der Autor:innen
KI zeigt großes Potenzial zur Verbesserung von Diagnose und Risikostratifizierung von Pankreaszysten, die breite klinische Anwendung wird aber durch hohes Verzerrungsrisiko, fehlende externe Validierung und begrenzte Interpretierbarkeit erschwert.
Kernaussagen
- Median-AUC über alle Studien: 0,912
- 11 Studien zeigten bessere Leistung als Kliniker:innen oder Leitlinien
- Nur 10 Studien nutzten externe Validierung
Deutsche Zusammenfassung: KI-gestützt aus dem Original-Abstract erstellt; alle Zahlen wurden automatisch mit dem Original abgeglichen. Maßgeblich ist der Original-Abstract.
Kurz gefasst
Übersichtsarbeit in der Zeitschrift Cancers, online erschienen am 02.08.2025. Verfasst von Donghyun Lee und 6 weiteren Autor:innen. Beteiligte Einrichtung: Leeds Institute of Medical Research, University of Leeds, Leeds LS2 9JT, UK. Die Arbeit wurde bisher 10-mal zitiert (Crossref) und nennt 69 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY 4.0).
Abstract (Originalsprache)
Background
Pancreatic cystic lesions (PCLs), including intraductal papillary mucinous neoplasms (IPMNs) and mucinous cystic neoplasms (MCNs), pose a diagnostic challenge due to their variable malignant potential. Current guidelines, such as Fukuoka and American Gastroenterological Association (AGA), have moderate predictive accuracy and may lead to overtreatment or missed malignancies. Artificial intelligence (AI), incorporating machine learning (ML) and deep learning (DL), offers the potential to improve risk stratification, diagnosis, and management of PCLs by integrating clinical, radiological, and molecular data. This is the first systematic review to evaluate the application, performance, and clinical utility of AI models in the diagnosis, classification, prognosis, and management of pancreatic cysts.
Methods
A systematic review was conducted in accordance with PRISMA guidelines and registered on PROSPERO (CRD420251008593). Databases searched included PubMed, EMBASE, Scopus, and Cochrane Library up to March 2025. The inclusion criteria encompassed original studies employing AI, ML, or DL in human subjects with pancreatic cysts, evaluating diagnostic, classification, or prognostic outcomes. Data were extracted on the study design, imaging modality, model type, sample size, performance metrics (accuracy, sensitivity, specificity, and area under the curve (AUC)), and validation methods. Study quality and bias were assessed using the PROBAST and adherence to TRIPOD reporting guidelines.
Results
From 847 records, 31 studies met the inclusion criteria. Most were retrospective observational (n = 27, 87%) and focused on preoperative diagnostic applications (n = 30, 97%), with only one addressing prognosis. Imaging modalities included Computed Tomography (CT) (48%), endoscopic ultrasound (EUS) (26%), and Magnetic Resonance Imaging (MRI) (9.7%). Neural networks, particularly convolutional neural networks (CNNs), were the most common AI models (n = 16), followed by logistic regression (n = 4) and support vector machines (n = 3). The median reported AUC across studies was 0.912, with 55% of models achieving AUC ≥ 0.80. The models outperformed clinicians or existing guidelines in 11 studies. IPMN stratification and subtype classification were common focuses, with CNN-based EUS models achieving accuracies of up to 99.6%. Only 10 studies (32%) performed external validation. The risk of bias was high in 93.5% of studies, and TRIPOD adherence averaged 48%.
Conclusions
AI demonstrates strong potential in improving the diagnosis and risk stratification of pancreatic cysts, with several models outperforming current clinical guidelines and human readers. However, widespread clinical adoption is hindered by high risk of bias, lack of external validation, and limited interpretability of complex models. Future work should prioritise multicentre prospective studies, standardised model reporting, and development of interpretable, externally validated tools to support clinical integration.
Schlagwörter
Stichwörter der Autor:innen
Autor:innen und Institutionen
- Leeds Institute of Medical Research, University of Leeds, Leeds LS2 9JT, UK.
- The Pancreato-Biliary Unit, St. James's University Teaching Hospital, Leeds LS9 7TF, UK.
ORCID-Profile: John J Maliekkal, Lewis Goulder, Benjamin Huntly, Yazan S Khaled
Zitieren
APA
Lee, D., Jesry, F., Maliekkal, J. J., Goulder, L., Huntly, B., Smith, A. M., & Khaled, Y. S. (2025). Application of Artificial Intelligence in Pancreatic Cyst Management: A Systematic Review. Cancers, 17(15), 2558. https://doi.org/10.3390/cancers17152558
Vancouver
Lee D, Jesry F, Maliekkal JJ, Goulder L, Huntly B, Smith AM, et al. Application of Artificial Intelligence in Pancreatic Cyst Management: A Systematic Review. Cancers. 2025;17(15):2558. doi:10.3390/cancers17152558
BibTeX
@article{Lee2025,
author = {Lee, Donghyun and Jesry, Fadel and Maliekkal, John J and Goulder, Lewis and Huntly, Benjamin and Smith, Andrew M and Khaled, Yazan S},
title = {Application of Artificial Intelligence in Pancreatic Cyst Management: A Systematic Review},
journal = {Cancers},
year = {2025},
volume = {17},
number = {15},
pages = {2558},
doi = {10.3390/cancers17152558}
}
EUVIMED