EUVIMEDEUVIMED entdecken
Open Access · CC BY 4.0

Multicenter development of an interpretable machine learning model for prognosis of acute pancreatitis with acute kidney injury

Multizentrische Entwicklung eines interpretierbaren Machine-Learning-Modells zur Prognose bei akuter Pankreatitis mit akutem Nierenversagen

Wei Wang, Tongping Shen

Frontiers in Medicine · 29.10.2026 · 13

DOI: 10.3389/fmed.2026.1955191 ↗

Auf einen Blick

Bei Patient:innen mit akuter Pankreatitis und akutem Nierenversagen wurde ein Random-Forest-Modell zur 60-Tage-Mortalität entwickelt und extern validiert. Es zeigte gute Trennschärfe.

Fragestellung

Kann ein interpretierbares Machine-Learning-Modell die 60-Tage-Sterblichkeit bei AP-AKI-Patient:innen vorhersagen?

Methode

Entwicklung und externe Validierung eines Machine-Learning-Modells mit Daten aus MIMIC-IV und eICU; 24 Modelle wurden verglichen. Primärer Endpunkt war die All-cause-Mortalität nach 60 Tagen.

Ergebnisse

Der Random Forest erzielte im internen Validierungssatz eine AUC von 0,8963 (95 %-KI 0,8479–0,9447) und extern 0,8122 (95 %-KI 0,7139–0,9106). SHAP zeigte nichtlineare Muster der 18 Kernmerkmale.

Einschränkungen

Extreme Klassenungleichheit und Datenheterogenität zwischen Zentren wurden in der externen Validierung erwähnt.

Schlussfolgerung der Autor:innen

Die Autor:innen berichten, dass ein hoch interpretierbares RF-Modell zur präzisen Vorhersage von Überlebensoutcomes bei AP-AKI erfolgreich konstruiert und extern validiert wurde.

Kernaussagen

  • RF-Modell mit AUC 0,8963 intern und 0,8122 extern
  • 18 Kernmerkmale wurden mit SHAP interpretiert
  • Eine Shiny-Webanwendung wurde für die individuelle Risikovorhersage bereitgestellt

Deutsche Zusammenfassung: KI-gestützt aus dem Original-Abstract erstellt; alle Zahlen wurden automatisch mit dem Original abgeglichen. Maßgeblich ist der Original-Abstract.

Kurz gefasst

Fachartikel in der Zeitschrift Frontiers in Medicine, online erschienen am 29.10.2026. Verfasst von Wei Wang und 1 weiteren Autor:innen. Beteiligte Einrichtung: The First Affiliated Hospital of Anhui University of Chinese Medicine, Hefei, China. Die Arbeit nennt 32 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY 4.0).

Auf einen BlickAbstractSchlagwörterBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

Background

Patients with severe acute pancreatitis complicated by acute kidney injury (AP-AKI) face extremely high mortality rates; therefore, early and precise risk stratification is crucial for optimizing individualized treatment strategies. However, traditional linear prognostic models have inherent limitations in capturing the non-linear associations between complex clinical features and patient outcomes, and they often lack sufficient clinical generalizability. This study aimed to develop, externally validate, and deploy a highly accurate and interpretable machine learning model to predict the survival outcome of AP-AKI patients.

Methods

Early clinical data of AP-AKI patients were extracted from the large intensive care database MIMIC-IV, with all-cause mortality at 60 days serving as the primary observation endpoint. The study utilized three algorithms (Boruta, LASSO, and MRMR) to screen 18 core features, subsequently constructing and systematically comparing 24 machine learning models. The models underwent comprehensive evaluation through the Area Under the Receiver Operating Characteristic Curve (AUC), calibration metrics, and Decision Curve Analysis (DCA), while external validation was accomplished in the independent eICU database. Additionally, the SHAP method was applied to deeply clarify the complex non-linear interaction patterns among prognostic factors, and a convenient interactive online application was developed based on the optimal model.

Results

Among the 24 included models, the Random Forest (RF) model demonstrated the best holistic performance. It achieved an AUC of 0.8963 (0.8479, 0.9447) in the internal validation set. Despite facing extreme class imbalance and cross-center data heterogeneity in the eICU external validation set, the model maintained excellent discrimination with an AUC of 0.8122 (0.7139, 0.9106). Compared with numerous traditional and machine learning baseline models, the RF model exhibited optimal overall calibration, and DCA confirmed that it achieved highly valuable clinical net benefit across a wide range of decision thresholds. SHAP analysis profoundly revealed multiple non-linear driving patterns, such as step-wise or “S-shaped” threshold effects of the 18 core features (prominently including aki_kdigo_stage, charlson_comorbidity_index, rdw, ast, and sapsii_score) on mortality risk. The successfully deployed interactive Shiny web application ( https://medicalpredictor.shinyapps.io/Online_Prediction_of_60-Day_Survival_Status_in_Patients ) enables code-free individualized risk prediction and feature attribution interpretation.

Conclusions

This study successfully constructed and externally validated a highly interpretable RF model for the precise prediction of survival outcomes in AP-AKI patients. The online interactive application deployed based on this model provides a convenient, intuitive, and evidence-based decision support tool for early clinical risk stratification and individualized precision intervention. Future multi-center, prospective randomized controlled studies are urgently needed to further validate its real-world clinical utility, along with exploring the inclusion of time-series data to develop more comprehensive longitudinal dynamic predictive models.

Schlagwörter

Stichwörter der Autor:innen

acute kidney injuryacute pancreatitisclinical prognostic factorsmachine learningshiny applicationsurvival prediction

Autor:innen und Institutionen

  • The First Affiliated Hospital of Anhui University of Chinese Medicine, Hefei, China.
  • School of Information Engineering, Anhui University of Chinese Medicine, Hefei, China.

Zitieren

APA

Wang, W., & Shen, T. (2026). Multicenter development of an interpretable machine learning model for prognosis of acute pancreatitis with acute kidney injury. Frontiers in Medicine, 13. https://doi.org/10.3389/fmed.2026.1955191

Vancouver

Wang W, Shen T. Multicenter development of an interpretable machine learning model for prognosis of acute pancreatitis with acute kidney injury. Frontiers in Medicine. 2026;13. doi:10.3389/fmed.2026.1955191

BibTeX
@article{Wang2026,
  author = {Wang, Wei and Shen, Tongping},
  title = {Multicenter development of an interpretable machine learning model for prognosis of acute pancreatitis with acute kidney injury},
  journal = {Frontiers in Medicine},
  year = {2026},
  volume = {13},
  doi = {10.3389/fmed.2026.1955191}
}
Kostenlos starten →