EUVIMEDEUVIMED entdecken
Crossref

Machine Learning versus QNI Score for Predicting Step-Up Therapy After Initial EUS-Guided Drainage of Pancreatic Fluid Collections

M Razpotnik, M Schalberger, T Herta, M Sigal, Ö Çelebi, A Adler, S Leonhardt, F Branchi, J Buchkremer, K Kouladouros, C Engelmann, B Siegmund und 2 weitere

Endoscopy · 01.06.2026 · 58 (S 03 S 03) · S392-S393

DOI: 10.1055/s-0046-1821327 ↗

Kurz gefasst

Fachartikel in der Zeitschrift Endoscopy, erschienen am 01.06.2026. Verfasst von M Razpotnik und 13 weiteren Autor:innen.

AbstractBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

Aims

Pancreatic fluid collections (PFCs) are associated with high healthcare utilization and multiple interventions. However, clinicians still lack reliable baseline risk-stratification tools, leading to reactive decision-making rather than proactive risk-adapted care [ 1 ]. We therefore developed a machine-learning algorithm to predict step-up therapy requirements at index EUS and compared its performance with established clinical predictors.

Methods

Data on EUS-guided drainage of consecutive PFCs performed between 2016 and 2024 across three endoscopy units at Charité Berlin, irrespective of etiology, were retrospectively collected. The primary outcome was need for step-up therapy, defined as endoscopic necrosectomy, percutaneous drainage, or laparoscopic/open surgery performed after the index procedure to achieve clinical success. An extreme gradient boosting (XGBoost) machine learning algorithm was developed and compared with the established QNI score (Quadrant, Necrosis, Infection) to predict need for step-up therapy [ 2 ] [ 3 ]. The cohort was randomly split into training (70%) and validation (30%) sets. Performance was assessed using 10-fold cross-validation, with discrimination quantified by area under the receiver operating characteristic curve. Of 163 evaluated patient-level features, 20 were selected for the final decision-support model based on Gini coefficients, clinical relevance, and practical considerations to preserve predictive performance while minimizing overfitting.

Results

Among 674 consecutive patients, 486 were included in the final analysis (mean age 56.1±14.3 years; 68.9% male). Overall, 199 patients (40.9%) required step-up therapy, including endoscopic necrosectomy (n=145; 29.8%), percutaneous drainage (n=62; 12.8%), multigate technique (n=22; 4.5%), and laparoscopic or open surgery (n=35; 7.2%). Compared with patients managed without step-up therapy, those requiring escalation had significantly larger PFCs (105±46 vs. 67±32 mm; p 60% necrosis (11.6% vs. 2.4%; p

Zitieren

APA

Razpotnik, M., Schalberger, M., Herta, T., Sigal, M., Çelebi, Ö., Adler, A., Leonhardt, S., Branchi, F., Buchkremer, J., Kouladouros, K., Engelmann, C., Siegmund, B., Tacke, F., & Jürgensen, C. (2026). Machine Learning versus QNI Score for Predicting Step-Up Therapy After Initial EUS-Guided Drainage of Pancreatic Fluid Collections. Endoscopy, 58(S 03 S 03), S392-S393. https://doi.org/10.1055/s-0046-1821327

Vancouver

Razpotnik M, Schalberger M, Herta T, Sigal M, Çelebi Ö, Adler A, et al. Machine Learning versus QNI Score for Predicting Step-Up Therapy After Initial EUS-Guided Drainage of Pancreatic Fluid Collections. Endoscopy. 2026;58(S 03 S 03):S392-S393. doi:10.1055/s-0046-1821327

BibTeX
@article{Razpotnik2026,
  author = {Razpotnik, M and Schalberger, M and Herta, T and Sigal, M and Çelebi, Ö and Adler, A and Leonhardt, S and Branchi, F and Buchkremer, J and Kouladouros, K and Engelmann, C and Siegmund, B and Tacke, F and Jürgensen, C},
  title = {Machine Learning versus QNI Score for Predicting Step-Up Therapy After Initial EUS-Guided Drainage of Pancreatic Fluid Collections},
  journal = {Endoscopy},
  year = {2026},
  volume = {58},
  number = {S 03 S 03},
  pages = {S392--S393},
  doi = {10.1055/s-0046-1821327}
}
Kostenlos starten →