Enterocutaneous Fistula–Associated Sepsis and Mortality: Development and Validation of a Multimodal Artificial Intelligence Prediction Model
Sepsis und Mortalität bei enterokutaner Fistel: Entwicklung und Validierung eines multimodalen KI-Prognosemodells
JMIR Medical Informatics · 2026-04-30 · 14 · e79985
DOI: 10.2196/79985 ↗Auf einen Blick
Eine multimodale KI aus klinischen, bildgebenden und transkriptomischen Daten sagte ECF-assoziierte Sepsis und 28-Tage-Mortalität mit AUC 0,89 voraus. Sie war besser als unimodale Modelle.
Fragestellung
Lässt sich ein multimodales KI-Modell aus klinischen, bildgebenden und transkriptomischen Daten zur frühen Vorhersage von ECF-assoziierter Sepsis und 28-Tage-Mortalität entwickeln?
Methode
Entwicklung eines multimodalen Fusionsmodells mit MIMIC-III, eICU und The Cancer Genome Atlas; klinische Daten mit Extreme Gradient Boosting, Bilddaten mit CNN, Transkriptomik mit VAE; Validierung per Cross-validation und externem Test.
Ergebnisse
Das multimodale Modell erreichte eine AUC von 0,89 für Sepsis und 28-Tage-Mortalität. Klinisches Modell: AUC 0,72; bildgebendes Modell: AUC 0,78. Wichtige Prädiktoren waren SOFA-Score, Laktat, freie intraabdominale Flüssigkeit, PD-L1 und IDO1.
Schlussfolgerung der Autor:innen
Das multimodale KI-Modell ermöglicht laut Autor:innen eine präzise frühe Risikostratifizierung bei ECF-assoziierter Sepsis und liefert interpretierbare Einblicke in immuninflammatorische Signalwege.
Kernaussagen
- AUC 0,89 für Sepsis und 28-Tage-Mortalität
- Besser als klinisches Modell (AUC 0,72) und Bildmodell (AUC 0,78)
- Wichtige Prädiktoren: SOFA, Laktat, freie Flüssigkeit, PD-L1, IDO1
Deutsche Zusammenfassung: KI-gestützt aus dem Original-Abstract erstellt; alle Zahlen wurden automatisch mit dem Original abgeglichen. Maßgeblich ist der Original-Abstract.
At a glance
Journal article in JMIR Medical Informatics, published online on 2026-04-30. Written by Hui Li and 5 co-authors. Institution: Department of Emergency Medicine, The Sixth Affiliated Hospital of Sun Yat-zen University, Guangzhou, Guangdong, China. Major MEDLINE topics: Sepsis, Intestinal Fistula, Artificial Intelligence. Cited 3 times so far (Crossref); 33 references. The full text is freely available in PubMed Central.
Abstract (original language)
Background
Predicting enterocutaneous fistula (ECF)–associated sepsis and mortality poses significant challenges in digital health care due to the disease’s complexity and heterogeneous clinical manifestations. Current approaches that rely on single-modal data or traditional scoring systems often fail to capture the intricate immune-inflammatory dynamics and multisystem involvement in patients with ECF.
Objective
This study aims to develop an artificial intelligence (AI)–driven multimodal fusion model integrating clinical, imaging, and transcriptomic data for early prediction of ECF-associated sepsis and 28-day mortality, addressing the limitations of conventional single-dimensional models.
Methods
This study leveraged publicly available datasets (Medical Information Mart for Intensive Care III [MIMIC-III], electronic Intensive Care Unit [eICU], and The Cancer Genome Atlas) to construct a multimodal framework. Clinical parameters were processed using Extreme Gradient Boosting, abdominal imaging features were extracted via convolutional neural networks, and transcriptomic profiles were analyzed with variational autoencoders. A Transformer-based fusion network was employed for joint prediction and validated through cross-validation and external testing. Key features were identified using Shapley Additive Explanations and Local Interpretable Model-Agnostic Explanations interpretability algorithms, while immune regulatory mechanisms were explored via weighted gene co-expression network analysis.
Results
The multimodal model achieved an area under the curve (AUC) of 0.89 for predicting sepsis and 28-day mortality, outperforming unimodal models (clinical-only model, AUC 0.72, and imaging-only model, AUC 0.78). Critical predictors included Sequential Organ Failure Assessment score, lactate levels, intra-abdominal free fluid on imaging, and immunoregulatory genes (programmed death-ligand 1 [PD-L1] and indoleamine 2,3-dioxygenase 1 [IDO1]). Mechanistic analysis revealed distinct immune reprogramming in patients with sepsis, characterized by increased regulatory T cells and M2 macrophages, along with downregulated cluster of differentiation 8+ (CD8+) T cells.
Conclusions
This multimodal AI model offers an innovative digital solution in medical informatics, enabling precise early risk stratification for ECF-associated sepsis. By integrating multisource data and providing interpretable insights into immune-inflammatory pathways, the model enhances health care quality for patients with ECF and paves the way for personalized intervention strategies.
Subjects
MeSH terms (MEDLINE)
Author keywords
Authors and institutions
- Department of Emergency Medicine, The Sixth Affiliated Hospital of Sun Yat-zen University, Guangzhou, Guangdong, China
- Biomedical InnovationCenter, The Sixth Affiliated Hospital, Sun Yat-sen University, Guangzhou, China
ORCID profiles: Hui Li, Jing Chen, Peijun Lin, Youmei Pan, Yawen Cao, Wenfeng Xie
Cite
APA
Li, H., Chen, J., Lin, P., Pan, Y., Cao, Y., & Xie, W. (2026). Enterocutaneous Fistula–Associated Sepsis and Mortality: Development and Validation of a Multimodal Artificial Intelligence Prediction Model. JMIR Medical Informatics, 14, e79985. https://doi.org/10.2196/79985
Vancouver
Li H, Chen J, Lin P, Pan Y, Cao Y, Xie W. Enterocutaneous Fistula–Associated Sepsis and Mortality: Development and Validation of a Multimodal Artificial Intelligence Prediction Model. JMIR Medical Informatics. 2026;14:e79985. doi:10.2196/79985
BibTeX
@article{Li2026,
author = {Li, Hui and Chen, Jing and Lin, Peijun and Pan, Youmei and Cao, Yawen and Xie, Wenfeng},
title = {Enterocutaneous Fistula–Associated Sepsis and Mortality: Development and Validation of a Multimodal Artificial Intelligence Prediction Model},
journal = {JMIR Medical Informatics},
year = {2026},
volume = {14},
pages = {e79985},
doi = {10.2196/79985}
}
EUVIMED