EUVIMEDEUVIMED entdecken
ÜbersichtsarbeitOpen Access · CC BY 4.0

The Potential of Artificial Intelligence in the Diagnosis and Prognosis of Sepsis: A Narrative Review

Das Potenzial von Artificial Intelligence in der Diagnose und Prognose von Sepsis: Narrative Review

George Țocu iD, Elena Lăcrămioara Lisă iD, Dana Tutunaru, Raul Mihailov iD, Cristina Șerban, Valerii Luțenco iD, Florentin Dimofte, Mădălin Guliciuc, Iulia Chiscop, Bogdan Ioan Ștefănescu, Elena Niculeț iD, Gabriela Gurău iD und 3 weitere

Diagnostics · 27.08.2025 · 15 (17) · 2169

DOI: 10.3390/diagnostics15172169 ↗

Auf einen Blick

Die narrative Review beschreibt KI-Modelle zur Diagnose und Prognose von Sepsis. Viele Modelle erzielten AUC-Werte über 0,90 und lagen damit über konventionellen klinischen Scores.

Fragestellung

Wie wird künstliche Intelligenz für Diagnose und Prognose von Sepsis genutzt, und welche Modelle, Algorithmen sowie Herausforderungen sind relevant?

Methode

Strukturierte Literaturrecherche für eine narrative Review zu Studien von 2016 bis 2024 in PubMed/Medline, Scopus, Web of Science, IEEE Xplore und Google Scholar.

Ergebnisse

Viele KI-Modelle übertrafen qSOFA und SIRS. AUC-Werte lagen über 0,90 für Sepsis- und Mortalitätsprognose. TREWS und InSight wurden klinisch validiert und verkürzten die Zeit bis zum Therapiebeginn.

Einschränkungen

Es fehlen externe Validierungen in multizentrischen Settings; zudem bestehen Probleme mit Transparenz, algorithmischem Bias und der Integration in klinische Abläufe.

Schlussfolgerung der Autor:innen

KI hat das Potenzial, das Sepsis-Management durch frühe Diagnose, Risikostratifizierung und personalisierte Behandlung zu verändern. Erforderlich sind klinische Validierung, bessere Interpretierbarkeit und Schulung des Personals.

Kernaussagen

  • KI-Modelle erreichten AUC-Werte über 0,90
  • TREWS und InSight verkürzten die Zeit bis zum Therapiebeginn
  • Genannt werden fehlende Transparenz, Bias und mangelnde 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 Diagnostics, online erschienen am 27.08.2025. Verfasst von George Țocu und 14 weiteren Autor:innen. Beteiligte Einrichtung: Department of Pharmaceutical Sciences, Faculty of Medicine and Pharmacy, "Dunarea de Jos" University, 800008 Galati, Romania. Die Arbeit wurde bisher 16-mal zitiert (Crossref) und nennt 83 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY 4.0).

Auf einen BlickAbstractSchlagwörterBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

Background/Objectives: Sepsis is a severe medical condition characterized by a dysregulated host response to infection, with potentially fatal outcomes, requiring early diagnosis and rapid intervention. The limitations of traditional sepsis identification methods, as well as the complexity of clinical data generated in intensive care, have driven increased interest in applying artificial intelligence in this field. The aim of this narrative review article is to analyze how artificial intelligence is being used in the diagnosis and prognosis of sepsis, to present the most relevant current models and algorithms, and to discuss the challenges and opportunities related to integrating these technologies into clinical practice.

Methods

We conducted a structured literature search for this narrative review, covering studies published between 2016 and 2024 in databases such as PubMed/Medline, Scopus, Web of Science, IEEE Xplore, and Google Scholar. The review covered models based on machine learning (ML), deep neural networks (DNNs), Recurrent Neural Networks (RNNs), and clinical alert systems implemented in hospitals. The clinical data sources used, algorithms applied, system architectures, and performance outcomes are presented.

Results

Numerous artificial intelligence models demonstrated superior performance compared to conventional clinical scores (qSOFA, SIRS), achieving AUC values above 0.90 in predicting sepsis and mortality. Systems such as Targeted Real-Time Early Warning System (TREWS) and InSight have been clinically validated and have significantly reduced the time to treatment initiation. However, challenges remain, such as a lack of model transparency, algorithmic bias, difficulties integrating into clinical workflows, and the absence of external validation in multicenter settings.

Conclusions

Artificial intelligence has the potential to transform sepsis management through early diagnosis, risk stratification, and personalized treatment. A responsible, multidisciplinary approach is necessary, including rigorous clinical validation, enhanced interpretability, and training of healthcare personnel to effectively integrate these technologies into everyday practice.

Schlagwörter

Stichwörter der Autor:innen

artificial intelligencediagnosismachine learningnatural language processingprognosissepsis

Autor:innen und Institutionen

  • Department of Pharmaceutical Sciences, Faculty of Medicine and Pharmacy, "Dunarea de Jos" University, 800008 Galati, Romania.
  • Department of Clinical Surgery, Faculty of Medicine and Pharmacy, "Dunarea de Jos" University, 800008 Galati, Romania.
  • Department of Morphological and Functional Sciences, Faculty of Medicine and Pharmacy, "Dunarea de Jos" University, 800008 Galati, Romania.
  • Department of Clinical Medicine, Faculty of Medicine and Pharmacy, "Dunarea de Jos" University, 800008 Galati, Romania.

ORCID-Profile: George Țocu, Elena Lăcrămioara Lisă, Raul Mihailov, Valerii Luțenco, Elena Niculeț, Gabriela Gurău, Loredana Stavăr Matei

Zitieren

APA

Țocu, G., Lisă, E. L., Tutunaru, D., Mihailov, R., Șerban, C., Luțenco, V., Dimofte, F., Guliciuc, M., Chiscop, I., Ștefănescu, B. I., Niculeț, E., Gurău, G., Berbece, S. I., Mihailov, O. M., & Stavăr Matei, L. (2025). The Potential of Artificial Intelligence in the Diagnosis and Prognosis of Sepsis: A Narrative Review. Diagnostics, 15(17), 2169. https://doi.org/10.3390/diagnostics15172169

Vancouver

Țocu G, Lisă EL, Tutunaru D, Mihailov R, Șerban C, Luțenco V, et al. The Potential of Artificial Intelligence in the Diagnosis and Prognosis of Sepsis: A Narrative Review. Diagnostics. 2025;15(17):2169. doi:10.3390/diagnostics15172169

BibTeX
@article{ocu2025,
  author = {Țocu, George and Lisă, Elena Lăcrămioara and Tutunaru, Dana and Mihailov, Raul and Șerban, Cristina and Luțenco, Valerii and Dimofte, Florentin and Guliciuc, Mădălin and Chiscop, Iulia and Ștefănescu, Bogdan Ioan and Niculeț, Elena and Gurău, Gabriela and Berbece, Sorin Ion and Mihailov, Oana Mariana and Stavăr Matei, Loredana},
  title = {The Potential of Artificial Intelligence in the Diagnosis and Prognosis of Sepsis: A Narrative Review},
  journal = {Diagnostics},
  year = {2025},
  volume = {15},
  number = {17},
  pages = {2169},
  doi = {10.3390/diagnostics15172169}
}
Kostenlos starten →