Artificial Intelligence in Burn Care: A Review of Early Warning Systems and Clinical Outcome Prediction
DOI:
https://doi.org/10.58445/tjcc0s14Keywords:
Artificial Inteligence, Burn care, Mortality, Clinical descision making, triage algorithimsAbstract
Burn patients are at high risk for poor outcomes, including infection, prolonged hospital stays, and mortality. Early identification of high-risk patients is important for guiding clinical decisions and preventing serious complications. This literature review examined the use of artificial intelligence (AI) to predict mortality, complications, and length of hospital stay in burn patients compared with traditional clinical methods. We reviewed seven studies published between 2022 and 2026 identified through PubMed that examined AI models for predicting patient outcomes, assessing burn severity, and supporting clinical decision-making. The studies found that AI models, including artificial neural networks and Random Forest models, demonstrated high accuracy in predicting mortality, with some models achieving approximately 96% accuracy or an area under the receiver operating characteristic curve (AUC) of 0.922. However, AI did not significantly outperform traditional methods, such as the Baux score, in the study that directly compared them. One study also found that most healthcare providers perceived AI as helpful for making treatment decisions, including determining the timing of surgery. Overall, AI shows promise as a tool for identifying high-risk burn patients and supporting clinical decision-making. However, research remains limited, and it is unclear whether the use of AI improves patient outcomes in clinical practice. Future studies should investigate AI's ability to predict specific complications, such as infections, and evaluate whether implementing these tools in clinical settings leads to improved patient outcomes.
References
Çinar MA, Ölmez E, Erkiliç A, Bayramlar K, Er O. Machine learning models for early prediction of mortality risk in patients with burns: a single center experience. J Plast Reconstr Aesthet Surg. 2024;89:14-20. doi:10.1016/j.bjps.2023.11.048
Fransén J, Lundin J, Fredén F, Huss F. A proof-of-concept study on mortality prediction with machine learning algorithms using burn intensive care data. Scars Burn Heal. 2022;8:20595131211066585. doi:10.1177/20595131211066585
Lee JJ, Abdolahnejad M, Morzycki A, et al. Comparing artificial intelligence guided image assessment to current methods of burn assessment. J Burn Care Res. 2025;46(1):6-13. doi:10.1093/jbcr/irae121
Motamedi M, Mohseni Moallemkolaei N, Hesamirostami M, Ghorbani M, Shokrizadeh Arani L. Simultaneous prediction of early and delayed mortality in burn patients: a comparative machine learning analysis of feature importance in a single-center retrospective study. BMC Med Inform Decis Mak. 2026;26:7. doi:10.1186/s12911-025-03311-1
Park C, Loza-Avalos SE, Harvey J, et al. A real-time automated machine learning algorithm for predicting mortality in trauma patients: survey says it's ready for prime-time. Am Surg. 2024;90(4):655-661. doi:10.1177/00031348231207299
Park JH, Cho Y, Shin D, Choi SS. Prediction of mortality after burn surgery in critically ill burn patients using machine learning models. J Pers Med. 2022;12(8):1293. doi:10.3390/jpm12081293
Yazıcı H, Ugurlu O, Aygul Y, Yildirim M, Uçar AD. The effect of well-known burn-related features on machine learning algorithms in burn patients' mortality prediction. Ulus Travma Acil Cerrahi Derg. 2023;29(10):1130-1137. doi:10.14744/tjtes.2023.79968
Downloads
Posted
Categories
License
Copyright (c) 2026 Research Archive of Rising Scholars

This work is licensed under a Creative Commons Attribution 4.0 International License.