Interpretative machine learning for predicting 60-day mortality in burn patients with suspected infection

doi:10.5847/wjem.j.1920-8642.2026.046

Abstract

Abstract:

BACKGROUND: Traditional burn severity scores have limited accuracy in predicting mortality in burn patients with infection. This study aimed to develop an interpretative machine learning (ML) model to predict 60-day mortality in burn patients with suspected infection.

METHODS: Data on burn patients with suspected infection were extracted from the Dryad database and divided into a training cohort (70%) and a test cohort (30%). Feature selection was conducted by combining the Boruta algorithm and least absolute shrinkage and selection operator (LASSO) regression. Twelve ML models were developed to predict 60-day mortality. Model robustness was evaluated in the training cohort, and the discrimination capacity was assessed in the test cohort. DeLong’s test was performed to compare the area under the curve (AUC) between the optimal model and the traditional scores (abbreviated burn severity index [ABSI] and revised Baux [rBaux]). SHapley Additive exPlanations (SHAP) analysis was used for model interpretation.

RESULTS: A total of 1,391 adult burn patients with suspected infections were included: training cohort (n=973), test cohort (n=418). The overall mortality was 23.7% (n=329). The percentage of total body surface area (%TBSA), Acute Physiology and Chronic Health Evaluation IV (APACHE IV) score, and age were identified as significant predictors of 60-day mortality among burn patients with suspected infections. CatBoost achieved a well-balanced performance and better ability than the ABSI and rBaux did.

CONCLUSION: The ML model incorporating the APACHE IV score improved the predicting performance of 60-day mortality in burn patients with infection. Its high interpretability may facilitates its clinical application for In the future.

Key words: Burns, Machine learning, Mortality prediction, Feature selection

Haitao Ren, Yong’an Xu. Interpretative machine learning for predicting 60-day mortality in burn patients with suspected infection[J]. World Journal of Emergency Medicine, 2026, 17(3): 244-249.

Figures/Tables 3

Figure 1.

Figure 2.

Figure 3.

References 21

1	Yakupu A, Zhang J, Dong W, Song F, Dong JY, Lu SL. The epidemiological characteristic and trends of burns globally. BMC Public Health. 2022; 22(1): 1596.
2	Żwierełło W, Piorun K, Skórka-Majewicz M, Maruszewska A, Antoniewski J, Gutowska I. Burns: classification, pathophysiology, and treatment: a review. Int J Mol Sci. 2023; 24(4): 3749.
3	Dvorak JE, Khandelwal A, Ladhani HA, Claridge JA. Review of sepsis in burn patients in 2020. Surg Infect. 2021; 22(1): 37-43.
4	Sjoberg F, Greenhalgh D, Elmasry M, Abdelrahman I, El-Serafi AT, Steinvall I. High early incidence of sepsis and its impact on organ dysfunction in burn trauma patients: a detailed and hypothesis generating study. Burns Trauma. 2025;13: tkae085.
5	Deng GR, Tang L, Yang Q, Li ZY. Association of the abbreviated burn severity index with mortality in severely burned patients: a meta-analysis. PLoS One. 2025; 20(2): e0319199.
6	Yoshimura Y, Saitoh D, Yamada K, Nakamura T, Terayama T, Ikeuchi H, et al. Comparison of prognostic models for burn patients: a retrospective nationwide registry study. Burns. 2020; 46(8): 1746-55.
7	Christofides C, Moore R, Nel M. Baux score as a predictor of mortality at the CHBAH adult burns unit. J Surg Res. 2020; 251: 53-62.
8	Shah S, Verma R, Mittal RK, Garg R. Better among the two for burn mortality prediction in developing nations: revised baux or modified abbreviated burn severity index? Int J Appl Basic Med Res. 2024; 14(1): 7-11.
9	Tsurumi A, Que YA, Yan SC, Tompkins RG, Rahme LG, Ryan CM. Do standard burn mortality formulae work on a population of severely burned children and adults? Burns. 2015; 41(5): 935-45.
10	Xie JY, Gao JD, Yang MT, Zhang T, Liu YC, Chen YT, et al. Prediction of sepsis within 24 hours at the triage stage in emergency departments using machine learning. World J Emerg Med. 2024; 15(5): 379.
11	Ren HT, Xu YA, Hu H. An integrated deep learning and large language model for burn wound depth recognition. J Burn Care Res. 2026; 47(1): 295-304.
12	Khan K, Weeks AD. Example of retrospective dataset publication through Dryad. BMJ. 2015;350:h1788.
13	Yoon J, Kym D, Hur J, Cho YS, Chun W, Yoon D. Validation of Sepsis-3 using survival analysis and clinical evaluation of quick SOFA, SIRS, and burn-specific SIRS for sepsis in burn patients with suspected infection. PLoS One. 2023; 18(1):e0276597.
14	Rhee TM, Ko YK, Kim HK, Lee SB, Kim BS, Choi HM, et al. Machine learning-based discrimination of cardiovascular outcomes in patients with hypertrophic cardiomyopathy. JACC Asia. 2024; 4(5):375-86.
15	Chang CY, Chen CC, Tsai ML, Hsieh MJ, Chen TH, Chen SW, et al. Predicting mortality and hospitalization in heart failure with preserved ejection fraction by using machine learning. JACC Asia. 2024; 4(12):956-68.
16	Ejiyi CJ, Qin Z, Ukwuoma CC, Nneji GU, Monday HN, Ejiyi MB, et al. Comparative performance analysis of Boruta, SHAP, and Borutashap for disease diagnosis: a study with multiple machine learning algorithms. Network. 2025; 36(3):507-44.
17	Liu Q, Zhang Y, Sun J, Wang K, Wang Y, Wang Y, et al. Early identification of high-risk patients admitted to emergency departments using vital signs and machine learning. World J Emerg Med. 2025; 16(2):113-20.
18	Wu W, Li M, Jiang H, Sun M, Zhu Y, Zhu G, et al. Development of an emergency department length-of-stay prediction model based on machine learning. World J Emerg Med. 2025; 16(3):220-4.
19	Wang SQ, Qiu K, Zheng QR, Zhou BJ, Li MY, Zhong HY, et al. Development and validation of web-based, interpretable predictive models for sepsis and mortality in extensive burns. Front Cell Infect Microbiol. 2025; 15:1586087.
20	Edgar MC, Bond SM, Jiang SH, Scharf IM, Bejarano G, Vrouwe SQ. The Revised Baux Score as a predictor of burn mortality: a systematic review and meta-analysis. J Burn Care Res. 2023; 44(6):1278-88.
21	Fu L, Burns R, Xie Y, Shen J, Zhe S, Estabrooks P, et al. The development and use of AI chatbots for health behavior change: scoping review. J Med Internet Res. 2026; 28:e79677.

[1]	Hui Chen, Yuanhua Lu, Songjie Bai, Yang Li, Tao Wang, Long Cai, Xinyi Yang, Yang Fang, Jianguo Wan, Yaqun Tang, Wenqiang Tao, Meiling Huang, Wei Zhong, Fen Liu, Kejian Qian. Stress-hyperglycemia ratio and glycemic variability predict severity and mortality in sepsis-associated acute respiratory distress syndrome [J]. World Journal of Emergency Medicine, 2026, 17(3): 250-257.
[2]	Yuanwei Fu, Yilan Yang, Hua Zhang, Daidai Wang, Qiangrong Zhai, Lanfang Du, Nijiati Muyesai, Yanxia Gao, Qingbian Ma. Development and validation of machine learning-based in-hospital mortality predictive models for acute aortic syndrome in emergency departments [J]. World Journal of Emergency Medicine, 2026, 17(1): 43-49.
[3]	Xing Luo, Jinzhao Zhang, Fanrong Lin, Siqi Liu, Zhengfei Yang. Beyond the chain of survival: a scoping review of artificial intelligence applications in cardiac arrest [J]. World Journal of Emergency Medicine, 2026, 17(1): 7-14.
[4]	Weiming Wu, Min Li, Huilin Jiang, Min Sun, Yongcheng Zhu, Gongxu Zhu, Yanling Li, Yunmei Li, Junrong Mo, Xiaohui Chen, Haifeng Mao. Development of an emergency department length-of-stay prediction model based on machine learning [J]. World Journal of Emergency Medicine, 2025, 16(3): 220-224.
[5]	Zhongshu Kuang, Runrong Li, Su Lu, Yusong Wang, Yue Luo, Yongqi Shen, Li Yuan, Yilin Yang, Zhenju Song, Ning Jiang, Chaoyang Tong. Uncovering host response in adults with severe community-acquired pneumonia: a proteomics and metabolomics perspective study [J]. World Journal of Emergency Medicine, 2025, 16(3): 248-255.
[6]	Qingyuan Liu, Yixin Zhang, Jian Sun, Kaipeng Wang, Yueguo Wang, Yulan Wang, Cailing Ren, Yan Wang, Jiashan Zhu, Shusheng Zhou, Mengping Zhang, Yinglei Lai, Kui Jin. Early identification of high-risk patients admitted to emergency departments using vital signs and machine learning [J]. World Journal of Emergency Medicine, 2025, 16(2): 113-120.
[7]	Jingyuan Xie, Jiandong Gao, Mutian Yang, Ting Zhang, Yecheng Liu, Yutong Chen, Zetong Liu, Qimin Mei, Zhimao Li, Huadong Zhu, Ji Wu. Prediction of sepsis within 24 hours at the triage stage in emergency departments using machine learning [J]. World Journal of Emergency Medicine, 2024, 15(5): 379-385.