EUVIMEDEUVIMED entdecken
Crossref

Machine Learning Models for Predicting In-Hospital Mortality in Burn Patients

Samet Şahin, Burak Yavuz, Onur Karaca, Merve Akın, Ali Emre Akgün

Annali Italiani di Chirurgia · 14.07.2025 · 96 (8)

DOI: 10.62713/aic.3944 ↗

Kurz gefasst

Fachartikel in der Zeitschrift Annali Italiani di Chirurgia, online erschienen am 14.07.2025. Verfasst von Samet Şahin und 4 weiteren Autor:innen. Beteiligte Einrichtung: Department of General Surgery, Muğla Sıtkı Koçman University, 48000 Muğla, Turkey. Hauptthemen laut MEDLINE: Burns, Machine Learning, Hospital Mortality. Die Arbeit wurde bisher 2-mal zitiert (Crossref).

AbstractSchlagwörterBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

AIM: To develop and evaluate predictive models for in-hospital mortality in burn patients using machine learning (ML) techniques. METHODS: A retrospective cohort study was conducted using data from burn patients admitted to Ankara Bilkent City Hospital Burn Treatment Center between 2015 and 2020. Key variables including age, gender, total body surface area burned, burn depth, burn type, inhalation injury, inflammatory markers and inflammatory indexes were collected. Seven ML models—Logistic Regression, Random Forest, Support Vector Machine, Decision Tree, K-Nearest Neighbors, Naive Bayes, and Gradient Boosting—were trained and evaluated. RESULTS: The cohort included 218 patients (mean age 42.5 ± 18.5 years; 69.7% male, 30.3% female), with an in-hospital mortality rate of 18.8% (n = 41). Logistic Regression had the best performance (accuracy: 88.6%, Receiver Operating Characteristic (ROC)-Area Under Curve (AUC): 0.906), while Random Forest achieved the highest accuracy (90.9%) and recall (97.2%). K-Nearest Neighbors excelled in recall (99.0%), Gradient Boosting balanced precision and recall (91.6% each, ROC-AUC: 0.744), and Support Vector Machine showed moderate results (accuracy: 84.0%, ROC-AUC: 0.864). CONCLUSIONS: ML models, particularly Logistic Regression and Random Forest, demonstrated strong predictive capabilities for mortality in burn patients. This study supports the potential for ML in burn care, offering a data-driven approach for personalized prognosis and clinical decision-making. Further multicenter validation is recommended.

Schlagwörter

MeSH-Schlagwörter (MEDLINE)

BurnsMachine LearningHospital MortalityHumansMaleRetrospective StudiesFemaleAdultMiddle AgedSupport Vector MachineLogistic ModelsPrognosis

Stichwörter der Autor:innen

burns/mortalitymachine learningrisk assessment

Autor:innen und Institutionen

  • Department of General Surgery, Muğla Sıtkı Koçman University, 48000 Muğla, Turkey.
  • Department of General Surgery, Kozan State Hospital, 01510 Adana, Turkey.
  • Department of General Surgery, Koç University Hospital, 34010 İstanbul, Turkey.
  • Department of General Surgery, Bilkent City Hospital, 06800 Ankara, Turkey.

Zitieren

APA

Şahin, S., Yavuz, B., Karaca, O., Akın, M., & Akgün, A. E. (2025). Machine Learning Models for Predicting In-Hospital Mortality in Burn Patients. Annali Italiani di Chirurgia, 96(8). https://doi.org/10.62713/aic.3944

Vancouver

Şahin S, Yavuz B, Karaca O, Akın M, Akgün AE. Machine Learning Models for Predicting In-Hospital Mortality in Burn Patients. Annali Italiani di Chirurgia. 2025;96(8). doi:10.62713/aic.3944

BibTeX
@article{ahin2025,
  author = {Şahin, Samet and Yavuz, Burak and Karaca, Onur and Akın, Merve and Akgün, Ali Emre},
  title = {Machine Learning Models for Predicting In-Hospital Mortality in Burn Patients},
  journal = {Annali Italiani di Chirurgia},
  year = {2025},
  volume = {96},
  number = {8},
  doi = {10.62713/aic.3944}
}
Kostenlos starten →