EUVIMEDEUVIMED entdecken
Open Access · CC BY 4.0

AI-Powered Early Detection of Sepsis in Emergency Medicine

Sergey Aityan, Rolando Herrero iD, Abdolreza Mosaddegh iD, Haitham Tayyar iD, Ebunoluwa Adebesin iD, Sai Pranavi Jeedigunta iD, Hangyeol Kim iD, Manuel Mersini iD, Rita Lazzaro, Nicola Iacovazzo, Ciro Gargiulo Isacco

Life · 10.10.2025 · 15 (10) · 1576

DOI: 10.3390/life15101576 ↗

Kurz gefasst

Fachartikel in der Zeitschrift Life, online erschienen am 10.10.2025. Verfasst von Sergey Aityan und 10 weiteren Autor:innen. Beteiligte Einrichtung: Department of Multidisciplinary Engineering, Northeastern University, Oakland, CA 94613, USA. Die Arbeit wurde bisher 3-mal zitiert (Crossref) und nennt 27 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY 4.0).

AbstractSchlagwörterBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

Sepsis remains a critical medical emergency caused by a dysregulated immune response to infection, with timely detection and intervention being essential for improving survival rates. Traditional methods often rely on clinician intuition and structured scoring systems, which may be time-intensive and prone to variability. To address these limitations, Machine Learning (ML) offers a powerful alternative, bringing precision and efficiency to sepsis detection. This study investigates both white-box and complex black-box ML models applied to patient data collected across the continuum of care, including monitoring at the urgent care, en route in ambulances, and diagnostics conducted within hospital emergency department settings themselves. White-box models, such as logistic regression and decision trees, are valued for their interpretability, allowing healthcare providers to understand and trust the reasoning behind predictions. Meanwhile, black-box models like deep neural networks and support vector machines deliver superior accuracy but pose challenges in clinical transparency. This trade-off between explainability and performance is explored in detail, supported by experimental results aimed at identifying the most effective computational strategies for early sepsis recognition across diverse healthcare environments.

Schlagwörter

Stichwörter der Autor:innen

ambulance-based detectionblack-box MLhospital settingmachine learningsepsisurgent carewhite-box ML

Autor:innen und Institutionen

  • Department of Multidisciplinary Engineering, Northeastern University, Oakland, CA 94613, USA.
  • Department of Multidisciplinary Engineering, Northeastern University, Boston, MA 02115, USA.
  • Biovitalage S.R.L., 70010 Valenzano, Italy.
  • Territorial Emergency System, SET 118, 74121 Taranto, Italy.
  • Territorial Center for Medical Assistance, 74121 Taranto, Italy.
  • Department of Interdisciplinary Medicine (DIM), Aldo Moro University of Bari, 70121 Bari, Italy.

ORCID-Profile: Rolando Herrero, Abdolreza Mosaddegh, Haitham Tayyar, Ebunoluwa Adebesin, Sai Pranavi Jeedigunta, Hangyeol Kim, Manuel Mersini

Zitieren

APA

Aityan, S., Herrero, R., Mosaddegh, A., Tayyar, H., Adebesin, E., Jeedigunta, S. P., Kim, H., Mersini, M., Lazzaro, R., Iacovazzo, N., & Isacco, C. G. (2025). AI-Powered Early Detection of Sepsis in Emergency Medicine. Life, 15(10), 1576. https://doi.org/10.3390/life15101576

Vancouver

Aityan S, Herrero R, Mosaddegh A, Tayyar H, Adebesin E, Jeedigunta SP, et al. AI-Powered Early Detection of Sepsis in Emergency Medicine. Life. 2025;15(10):1576. doi:10.3390/life15101576

BibTeX
@article{Aityan2025,
  author = {Aityan, Sergey and Herrero, Rolando and Mosaddegh, Abdolreza and Tayyar, Haitham and Adebesin, Ebunoluwa and Jeedigunta, Sai Pranavi and Kim, Hangyeol and Mersini, Manuel and Lazzaro, Rita and Iacovazzo, Nicola and Isacco, Ciro Gargiulo},
  title = {AI-Powered Early Detection of Sepsis in Emergency Medicine},
  journal = {Life},
  year = {2025},
  volume = {15},
  number = {10},
  pages = {1576},
  doi = {10.3390/life15101576}
}
Kostenlos starten →