The role of artificial intelligence in burn assessment, complication diagnosis, and outcome prediction: a narrative review

Abstract

Burn injury remains a major global health challenge, causing an estimated 180 000 deaths annually. The marked heterogeneity in burn severity, complications, and outcomes highlights the need for more objective and efficient evaluation strategies. Artificial intelligence (AI) has emerged as a promising approach to support clinical decision-making and improve patient care in this field. In this narrative review, we summarize the growing applications of AI in burn care, including the assessment of burn depth and total body surface area, monitoring of wound healing, prediction of postburn complications, and estimation of clinical outcomes. AI-based models have demonstrated strong performance in automating wound assessment, optimizing fluid resuscitation, and predicting complications such as sepsis, inhalation injury, and acute kidney injury. Furthermore, AI-driven prediction of mortality risk and hospital length of stay has shown potential to inform early interventions and improve resource allocation. Despite encouraging progress, most studies to date rely on small, single-center datasets and limited model validation, underscoring the need for larger, multi-institutional efforts, and standardized data sharing. Integrating AI into burn management holds great promise for enhancing diagnostic precision, forecasting outcomes, and personalizing treatment strategies. As these technologies advance, clinician familiarity and collaboration with AI tools will be critical to fully realize their potential in transforming burn care.

Keywords

Artificial intelligence / Machine learning / Deep learning / Burn injury / Complications / Sepsis / Inhalation injury / Acute kidney injury / Predictive models

References

[1] Yakupu A, Zhang J, Dong W, Song F, Dong J, Lu S. The epidemiological characteristic and trends of burns globally. BMC Public Health 2022; 22:1596. https://doi.org/10.1186/s12889-022-13887-2.

[2] Jeschke MG, van Baar ME, Choudhry MA, Chung KK, Gibran NS, Logsetty S. Burn injury. Nat Rev Dis Primers 2020; 6:11. https://doi.org/10.1038/s41572-020-0145-5.

[3] Greener JG, Kandathil SM, Moffat L, Jones DT. A guide to machine learning for biologists. Nat Rev Mol Cell Biol 2022; 23:40-55. https://doi.org/10.1038/s41580-021-00407-0.

[4] de Hond AAH, Leeuwenberg AM, Hooft L, Kant IMJ, Nijman SWJ, van Os HJA, et al. Guidelines and quality criteria for artificial intelligence-based prediction models in healthcare: a scoping review. NPJ Digit Med 2022; 5:2. https://doi.org/10.1038/s41746-021-00549-7.

[5] E Moura FS, Amin K, Ekwobi C. Artificial intelligence in the management and treatment of burns: a systematic review. Burns Trauma 2021; 9:tkab022. https://doi.org/10.1093/burnst/tkab022.

[6] Liu Y, Chen P-HC, Krause J, Peng L. How to read articles that use machine learning: users’ guides to the medical literature. JAMA 2019; 322:1806-16. https://doi.org/10.1001/jama.2019.16489.

[7] AbdelWahab ME, Sadaka MS, Elbana EA, Hendy AA. Evaluation of prognostic factors affecting length of stay in hospital and mortality rates in acute burn patients. Ann Burns Fire Disasters 2018; 31:83-8.

[8] Kraft R, Herndon DN, Al-Mousawi AM, Williams FN, Finnerty CC, Jeschke MG. Burn size and survival probability in paediatric patients in modern burn care: a prospective observational cohort study. Lancet 2012; 379:1013-21. https://doi.org/10.1016/S0140-6736(11)61345-7.

[9] Jeschke MG, Pinto R, Kraft R, Nathens AB, Finnerty CC, Gamelli RL, et al. Morbidity and survival probability in burn patients in modern burn care. Crit Care Med 2015; 43:808-15. https://doi.org/10.1097/CCM.0000000000000790.

[10] Wallace AB. The exposure treatment of burns. Lancet 1951; 1:501-4. https://doi.org/10.1016/s0140-6736(51)91975-7.

[11] García-Ballesteros DI, Rivera-Martínez DDC, García-Pérez MM, Valdés-Flores E, Castro-Govea Y, Chacón-Moreno HJ. Evaluation and optimization of the Wallace rule of nines for the estimation of total body surface area in obese and nonobese populations. J Emerg Med 2023; 65:e320-7. https://doi.org/10.1016/j.jemergmed.2023.05.017.

[12] Chang CW, Lai F, Christian M, Chen YC, Hsu C, Chen YS, et al. Deep learning-assisted burn wound diagnosis: diagnostic model development study. JMIR Med Inform 2021; 9:e22798. https://doi.org/10.2196/22798.

[13] Harish V, Raymond AP, Issler AC, Lajevardi SS, Chang L-Y, Maitz PKM, et al. Accuracy of burn size estimation in patients transferred to adult burn units in Sydney, Australia: an audit of 698 patients. Burns 2015; 41:91-9. https://doi.org/10.1016/j.burns.2014.05.005.

[14] Chang CW, Ho CY, Lai F, Christian M, Huang SC, Chang DH, et al. Application of multiple deep learning models for automatic burn wound assessment. Burns 2023; 49:1039-51. https://doi.org/10.1016/j.burns.2022.07.006.

[15] Xu X, Bu Q, Xie J, Li H, Xu F, Li J. On-site burn severity assessment using smartphone-captured color burn wound images. Comput Biol Med 2024; 182:109171. https://doi.org/10.1016/j.compbiomed.2024.109171.

[16] Evers LH, Bhavsar D, Mailänder P. The biology of burn injury. Exp Dermatol 2010; 19:777-83. https://doi.org/10.1111/j.1600-0625.2010.01105.x.

[17] Jaskille AD, Shupp JW, Jordan MH, Jeng JC. Critical review of burn depth assessment techniques: part I. Historical review. J Burn Care Res 2009; 30:937-47. https://doi.org/10.1097/BCR.0b013e3181c07f21.

[18] Monstrey S, Hoeksema H, Verbelen J, Pirayesh A, Blondeel P. Assessment of burn depth and burn wound healing potential. Burns 2008; 34:761-9. https://doi.org/10.1016/j.burns.2008.01.009.

[19] Jaspers MEH, van Haasterecht L, van Zuijlen PPM, Mokkink LB. A systematic review on the quality of measurement techniques for the assessment of burn wound depth or healing potential. Burns 2019; 45:261-81. https://doi.org/10.1016/j.burns.2018.05.015.

[20] Thatcher JE, Squiers JJ, Kanick SC, King DR, Lu Y, Wang Y, et al. Imaging techniques for clinical burn assessment with a focus on multispectral imaging. Adv Wound Care (New Rochelle) 2016; 5:360-78. https://doi.org/10.1089/wound.2015.0684.

[21] Resch TR, Drake RM, Helmer SD, Jost GD, Osland JS. Estimation of burn depth at burn centers in the United States: a survey. J Burn Care Res 2014; 35:491-7. https://doi.org/10.1097/BCR.0000000000000031.

[22] Thatcher JE, Yi F, Nussbaum AE, DiMaio JM, Dwight J, Plant K, et al. Clinical investigation of a rapid non-invasive multispectral imaging device utilizing an artificial intelligence algorithm for improved burn assessment. J Burn Care Res 2023; 44:969-81. https://doi.org/10.1093/jbcr/irad051.

[23] Lee JJ, Abdolahnejad M, Morzycki A, Freeman T, Chan H, Hong C, et al. Comparing artificial intelligence guided image assessment to current methods of burn assessment. J Burn Care Res 2024; 46:6-13. https://doi.org/10.1093/jbcr/irae121.

[24] Khalaf F, Barayan D, Saldanha S, Jeschke MG. Metabolaging: a new geroscience perspective linking aging pathologies and metabolic dysfunction. Metab Clin Exp 2025; 166:156158. https://doi.org/10.1016/j.metabol.2025.156158.

[25] Singer AJ, Boyce ST. Burn wound healing and tissue engineering. J Burn Care Res 2017; 38:e605-13. https://doi.org/10.1097/BCR.0000000000000538.

[26] Xiao-Wu W, Herndon DN, Spies M, Sanford AP, Wolf SE . Effects of delayed wound excision and grafting in severely burned children. Arch Surg 2002; 137:1049-54. https://doi.org/10.1001/archsurg.137.9.1049.

[27] Kirn DS, Luce EA. Early excision and grafting versus conservative management of burns in the elderly. Plast Reconstr Surg 1998; 102:1013-7. https://doi.org/10.1097/00006534-199809040-00013.

[28] Saaiq M, Zaib S, Ahmad S. Early excision and grafting versus delayed excision and grafting of deep thermal burns up to 40% total body surface area: a comparison of outcome. Ann Burns Fire Disasters 2012; 25:143-7.

[29] Ong YS, Samuel M, Song C. Meta-analysis of early excision of burns. Burns 2006; 32:145-50. https://doi.org/10.1016/j.burns.2005.09.005.

[30] Ethier O, Chan HO, Abdolahnejad M, Morzycki A, Fansi Tchango A, Joshi R, et al. Using computer vision and artificial intelligence to track the healing of severe burns. J Burn Care Res 2024; 45:700-8. https://doi.org/10.1093/jbcr/irad197.

[31] Singer M, Deutschman CS, Seymour CW, Shankar-Hari M, Annane D, Bauer M, et al. The third international consensus definitions for sepsis and septic shock (Sepsis-3). JAMA 2016; 315:801. https://doi.org/10.1001/jama.2016.0287.

[32] Greenhalgh DG, Saffle JR, Holmes JH, Gamelli RL, Palmieri TL, Horton JW, et al. American burn association consensus conference to define sepsis and infection in burns. J Burn Care Res 2007; 28:776-90. https://doi.org/10.1097/BCR.0b013e3181599bc9.

[33] Tran NK, Albahra S, Pham TN, Holmes JH, Greenhalgh D, Palmieri TL, et al. Novel application of an automated-machine learning development tool for predicting burn sepsis: proof of concept. Sci Rep 2020; 10:12354. https://doi.org/10.1038/s41598-020-69433-w.

[34] Zhang Z, Chen L, Sun B, Ruan Z, Pan P, Zhang W, et al. Identifying septic shock subgroups to tailor fluid strategies through multi-omics integration. Nat Commun 2024; 15:9028. https://doi.org/10.1038/s41467-024-53239-9.

[35] Liang W, Jia J. Reinforcement learning using neural networks in estimating an optimal dynamic treatment regime in patients with sepsis. Comput Methods Prog Biomed 2025; 266:108754. https://doi.org/10.1016/j.cmpb.2025.108754.

[36] Nunez Lopez O, Cambiaso-Daniel J, Branski LK, Norbury WB, Herndon DN . Predicting and managing sepsis in burn patients: current perspectives. Ther Clin Risk Manag 2017; 13:1107-17. https://doi.org/10.2147/TCRM.S119938.

[37] Polk RE, Mayhall CG, Smith J, Hall G, Kline BJ, Swensson E, et al. Gentamicin and tobramycin penetration into burn eschar. Pharmacokinetics and microbiological effects. Arch Surg 1983; 118:295-302. https://doi.org/10.1001/archsurg.1983.01390030027005.

[38] Yamamura S, Kawada K, Takehira R, Nishizawa K, Katayama S, Hirano M, et al. Artificial neural network modeling to predict the plasma concentration of aminoglycosides in burn patients. Biomed Pharmacother 2004; 58:239-44. https://doi.org/10.1016/j.biopha.2003.12.012.

[39] Yamamura S, Kawada K, Takehira R, Nishizawa K, Katayama S, Hirano M, et al. Prediction of aminoglycoside response against methicillin-resistant Staphylococcus aureus infection in burn patients by artificial neural network modeling. Biomed Pharmacother 2008; 62:53-8. https://doi.org/10.1016/j.biopha.2007.11.004.

[40] Shirani KZ, Pruitt BA, Mason AD. The influence of inhalation injury and pneumonia on burn mortality. Ann Surg 1987; 205:82-7. https://doi.org/10.1097/00000658-198701000-00015.

[41] Deutsch CJ, Tan A, Smailes S, Dziewulski P. The diagnosis and management of inhalation injury: an evidence based approach. Burns 2018; 44:1040-51. https://doi.org/10.1016/j.burns.2017.11.013.

[42] Yang S-Y, Huang C-J, Yen C-I, Kao Y-C, Hsiao Y-C, Yang J-Y, et al. Machine learning approach for predicting inhalation injury in patients with burns. Burns 2023; 49:1592-601. https://doi.org/10.1016/j.burns.2023.03.011.

[43] Chen B, Zhao J, Zhang Z, Li G, Jiang H, Huang Y, et al. Clinical characteristics and risk factors for severe burns complicated by early acute kidney injury. Burns 2020; 46:1100-6. https://doi.org/10.1016/j.burns.2019.11.018.

[44] Clark AT, Li X, Kulangara R, Adams-Huet B, Huen SC, Madni TD, et al. Acute kidney injury after burn: a cohort study from the parkland burn intensive care unit. J Burn Care Res 2019; 40:72-8. https://doi.org/10.1093/jbcr/iry046.

[45] Palmieri T, Lavrentieva A, Greenhalgh DG. Acute kidney injury in critically ill burn patients. Risk factors, progression and impact on mortality. Burns 2010; 36:205-11. https://doi.org/10.1016/j.burns.2009.08.012.

[46] Watkins TR. The comprehensive community mental health center as a field placement for graduate social work students. Community Ment Health J 1975; 11:27-32. https://doi.org/10.1007/BF01420461.

[47] Reinhard M, Erlandsen EJ, Randers E . Biological variation of cystatin C and creatinine. Scand J Clin Lab Invest 2009; 69:831-6. https://doi.org/10.3109/00365510903307947.

[48] Legrand M, Payen D. Understanding urine output in critically ill patients. Ann Intensive Care 2011; 1:13. https://doi.org/10.1186/2110-5820-1-13.

[49] Howell E, Sen S, Palmieri T, Godwin Z, Bockhold J, Greenhalgh D, et al. Point-of-care B-type natriuretic peptide and neutrophil gelatinase-associated lipocalin measurements for acute resuscitation: a pilot study. J Burn Care Res 2015; 36:e26-33. https://doi.org/10.1097/BCR.0000000000000098.

[50] Sen S, Godwin ZR, Palmieri T, Greenhalgh D, Steele AN, Tran NK. Whole blood neutrophil gelatinase-associated lipocalin predicts acute kidney injury in burn patients. J Surg Res 2015; 196:382-7. https://doi.org/10.1016/j.jss.2015.03.033.

[51] Rashidi HH, Sen S, Palmieri TL, Blackmon T, Wajda J, Tran NK. Early recognition of burn-and trauma-related acute kidney injury: a pilot comparison of machine learning techniques. Sci Rep 2020; 10:205. https://doi.org/10.1038/s41598-019-57083-6.

[52] Bloemsma GC, Dokter J, Boxma H, Oen IMMH. Mortality and causes of death in a burn centre. Burns 2008; 34:1103-7. https://doi.org/10.1016/j.burns.2008.02.010.

[53] Hasan JA, Eriby QH, Hammoodi SA-K. Causes of mortality in burns, prospective study. International journal of surgery. Science 2019; 3:261-4. https://doi.org/10.33545/surgery.2019.v3.i3e.178.

[54] Patil BM, Joshi RC, Toshniwal D, Biradar S. A new approach: role of data Mining in Prediction of survival of burn patients. J Med Syst 2011; 35:1531-42. https://doi.org/10.1007/s10916-010-9430-2.

[55] Stylianou N, Akbarov A, Kontopantelis E, Buchan I, Dunn KW. Mortality risk prediction in burn injury: comparison of logistic regression with machine learning approaches. Burns 2015; 41:925-34. https://doi.org/10.1016/j.burns.2015.03.016.

[56] 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. https://doi.org/10.1177/20595131211066585.

[57] Yazıcı H. The effect of well-known burn-related features on machine learning algorithms in burn patients’ mortality prediction. Turkish journal of trauma and emergency. Surgery 2023; 29:1130-7. https://doi.org/10.14744/tjtes.2023.79968.

[58] 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. https://doi.org/10.1016/j.bjps.2023.11.048.

[59] Elrod J, Mohr C, Wolff R, Boettcher M, Reinshagen K, Bartels P, et al. Using artificial intelligence to obtain more evidence? Prediction of length of hospitalization in Pediatric burn patients. Front Pediatr 2020; 8:613736. https://doi.org/10.3389/fped.2020.613736.

[60] Hussain A, Dunn KW. Predicting length of stay in thermal burns: a systematic review of prognostic factors. Burns 2013; 39:1331-40. https://doi.org/10.1016/j.burns.2013.04.026.

[61] Gravante G, Montone A, Esposito G. Length of hospitalization: an important parameter for burned patients. J Burn Care Res 2007; 28:537-8. https://doi.org/10.1097/BCR.0b013e318053db44.

[62] Jiménez R, López L, Dominguez D, Fariñas H. Difference between observed and predicted length of stay as an indicator of inpatient care inefficiency. Int J Qual Health Care 1999; 11:375-84. https://doi.org/10.1093/intqhc/11.5.375.

[63] Johnson LS, Shupp JW, Pavlovich AR, Pezzullo JC, Jeng JC, Jordan MH. Hospital length of stay-does 1% TBSA really equal 1 day? J Burn Care Res 2011; 32:13-9. https://doi.org/10.1097/BCR.0b013e318204b3ab.

[64] Saffle JR, Davis B, Williams P. Recent outcomes in the treatment of burn injury in the United States: a report from the American burn association patient registry. J Burn Care Rehabil 1995; 16:219-32. https://doi.org/10.1097/00004630-199505000-00002.

[65] Taylor SL, Sen S, Greenhalgh DG, Lawless M, Curri T, Palmieri TL. Not all patients meet the 1day per percent burn rule: a simple method for predicting hospital length of stay in patients with burn. Burns 2017; 43:282-9. https://doi.org/10.1016/j.burns.2016.10.021.

[66] Tan T, Wong DSY. Is the target of 1 day of stay per 1% total body surface area burned achieved in chemical burns? Ann Plast Surg 2016; 77:S39-42. https://doi.org/10.1097/SAP.0000000000000716.

[67] Yeh C-C, Lin Y-S, Chen C-C, Liu C-F. Implementing AI models for prognostic predictions in high-risk burn patients. Diagnostics 2023; 13:2984. https://doi.org/10.3390/diagnostics13182984.

[68] Johnson AEW, Bulgarelli L, Shen L, Gayles A, Shammout A, Horng S, et al. MIMIC-IV, a freely accessible electronic health record dataset. Sci Data 2023; 10:1. https://doi.org/10.1038/s41597-022-01899-x.

[69] She H, Du Y, Du Y, Tan L, Yang S, Luo X, et al. Metabolomics and machine learning approaches for diagnostic and prognostic biomarkers screening in sepsis. BMC Anesthesiol 2023; 23:367. https://doi.org/10.1186/s12871-023-02317-4.

[70] Fortino V, Wisgrill L, Werner P, Suomela S, Linder N, Jalonen E, et al. Machine-learning-driven biomarker discovery for the discrimination between allergic and irritant contact dermatitis. Proc Natl Acad Sci USA 2020; 117:33474-85. https://doi.org/10.1073/pnas.2009192117.

[71] Bifarin OO, Gaul DA, Sah S, Arnold RS, Ogan K, Master VA, et al. Machine learning-enabled renal cell carcinoma status prediction using multiplatform urine-based metabolomics. J Proteome Res 2021; 20:3629-41. https://doi.org/10.1021/acs.jproteome.1c00213.

[72] Shen X, Wang C, Liang N, Liu Z, Li X, Zhu Z-J, et al. Serum metabolomics identifies dysregulated pathways and potential metabolic biomarkers for hyperuricemia and gout. Arthritis Rheumatol 2021; 73:1738-48. https://doi.org/10.1002/art.41733.

[73] Rong J, Sun G, Zhu J, Zhu Y, Chen Z. Combination of plasma-based lipidomics and machine learning provides a useful diagnostic tool for ovarian cancer. J Pharm Biomed Anal 2025; 253:116559. https://doi.org/10.1016/j.jpba.2024.116559.

[74] Hsu N-W, Chou K-C, Wang Y-TT, Hung C-L, Kuo C-F, Tsai S-Y. Building a model for predicting metabolic syndrome using artificial intelligence based on an investigation of whole-genome sequencing. J Transl Med 2022; 20:190. https://doi.org/10.1186/s12967-022-03379-7.