Mortality risk prediction in emergency department patients: Modeling approaches and performance analysis with gradient boosting

Year 2025, Volume: 11 Issue: 6, 1204 - 1212, 04.11.2025

Erkan Boğa

https://doi.org/10.18621/eurj.1641700

Abstract

Objectives: The aim of this study is to evaluate the effectiveness of the Gradient Boosting algorithm in predicting mortality risk among emergency department patients and to identify the most critical demographic, clinical, and physiological data for these predictions. This study is designed to support early identification and enhance clinical decision support systems.

Methods: This retrospective study analyzed data from 1,500 patients who visited a state hospital's emergency department between January 1 and August 31, 2024. Data were collected based on multidimensional features such as demographic information, vital signs, laboratory results, and clinical history. The Gradient Boosting algorithm was used to develop the model, and its performance was evaluated using metrics such as accuracy, sensitivity, specificity, and F1 score.

Results: The Gradient Boosting model identified oxygen saturation, age, and heart rate as the most significant predictors of mortality. The CatBoost algorithm demonstrated the highest performance with an accuracy of 88.8% and an F1 score of 85%. The model was proven to be highly accurate in predicting mortality risk.

Conclusions: Gradient Boosting algorithms, particularly CatBoost, emerged as a reliable and effective tool for predicting mortality risk. This model can contribute to the development of clinical decision support systems in emergency department settings.

Keywords

Emergency Department , gradient boosting , mortality prediction , machine learning , clinical decision support

Ethical Statement

The study was approved by the Medipol University Non-Interventional Clinical Research Ethics Committee (Decision no.: 1138 and date: 28.11.2024). It was conducted in accordance with the ethical standards established in the Declaration of Helsinki and all data were anonymized and used solely for scientific purposes.

References

• 1. Wiler JL, Welch S, Pines JM, Schuur JD, Jouriles NJ, Stone-Griffith S. Emergency department performance measures updates: proceedings of the 2014 Emergency Department Benchmarking Alliance Consensus Summit. Acad Emerg Med. 2015;22(5):542-553. doi: 10.1111/acem.12654.
• 2. Hsia RY, Sarkar N, Shen YC. Impact of emergency department crowding on care for severe pain and patient satisfaction. J Emerg Med. 2019;57(3):291-298. doi: 10.1016/j.jemermed.2018.12.023.
• 3. Esteva A, Robicquet A, Ramsundar B, et al. A guide to deep learning in healthcare. Nat Med. 2019;25(1):24-29. doi: 10.1038/s41591-018-0316-z.
• 4. Chen T, Guestrin C. XGBoost: A scalable tree boosting system. Proc 22nd ACM SIGKDD Int Conf Knowl Discov Data Min. 2016;785-794. doi: 10.1145/2939672.2939785.
• 5. Lundberg SM, Lee SI. A unified approach to interpreting model predictions. Adv Neural Inf Process Syst. 2017;30:4768-4777. doi: 10.48550/arXiv.1705.07874.
• 6. van Walraven C, Wong J, Forster AJ. Predicting postdischarge death or readmission: derivation and validation of a clinical prediction tool. BMC Med Inform Decis Mak. 2012;12:89. doi: 10.1186/1472-6947-12-89.
• 7. Komorowski M, Celi LA, Badawi O, Gordon AC, Faisal AA. The Artificial Intelligence Clinician learns optimal treatment strategies for sepsis in intensive care. Nat Med. 2018;24(11):1716-1720. doi: 10.1038/s41591-018-0213-5.
• 8. Sezik S, Cingiz MÖ, İbiş E. Machine Learning-Based Model for Emergency Department Disposition at a Public Hospital. Appl Sci. 2025;15(3):1628. doi: 10.3390/app15031628.
• 9. Obermeyer Z, Emanuel EJ. Predicting the future - big data, machine learning, and clinical medicine. N Engl J Med. 2016;375(13):1216-1219. doi: 10.1056/NEJMp1606181.
• 10. Johnson AE, Pollard TJ, Shen L, et al. MIMIC-III, a freely accessible critical care database. Sci Data. 2016;3:160035. doi: 10.1038/sdata.2016.35.
• 11. Rajkomar A, Dean J, Kohane I. Machine Learning in Medicine. N Engl J Med. 2019;380(14):1347-1358. doi: 10.1056/NEJMra1814259.
• 12 Goldstein BA, Navar AM, Carter RE. Moving beyond regression techniques in cardiovascular risk prediction: applying machine learning to address analytic challenges. Eur Heart J. 2017;38(23):1805-1814. doi: 10.1093/eurheartj/ehw302.
• 13. Topol EJ. High-performance medicine: the convergence of human and artificial intelligence. Nat Med. 2019;25(1):44-56. doi: 10.1038/s41591-018-0300-7.
• 14. Beam AL, Kohan IS. Big data and machine learning in health care. JAMA. 2018;319(13):1317-1318. doi: 10.1001/jama.2017.18391.
• 15. Shickel B, Tighe PJ, Bihorac A, Rashidi P. Deep EHR: A Survey of Recent Advances in Deep Learning Techniques for Electronic Health Record (EHR) Analysis. IEEE J Biomed Health Inform. 2018;22(5):1589-1604. doi: 10.1109/JBHI.2017.2767063.
• 16. Holzinger A, Biemann C, Pattichis CS, Kell DB. What do we need to build explainable AI systems for the medical domain? 2017. arXiv:1712.09923. doi:10.48550/arXiv.1712.09923.
• 17. Miotto R, Wang F, Wang S, Jiang X, Dudley JT. Deep learning for healthcare: Review, opportunities and challenges. Brief Bioinform. 2018;19(6);1236-1246. doi: 10.1093/bib/bbx044.
• 18. Amann J, Blasimme A, Vayena E, Frey D, Madai VI; Precise4Q consortium. Explainability for artificial intelligence in healthcare: a multidisciplinary perspective. BMC Med Inform Decis Mak. 2020;20(1):310. doi: 10.1186/s12911-020-01332-6.
• 19. Sendak MP, Ratliff W, Sarro D, et al. Real-World Integration of a Sepsis Deep Learning Technology Into Routine Clinical Care: Implementation Study. JMIR Med Inform. 2020;15;8(7):e15182. doi: 10.2196/15182.
• 20. Kelly CJ, Karthikesalingam A, Suleyman M, Corrado G, King D. Key challenges for delivering clinical impact with artificial intelligence. BMC Medicine. 2019;17(1):195. doi: 10.1186/s12916-019-1426-2.
• 21. Wiens J, Saria S, Sendak M, et al. Do no harm: A roadmap for responsible machine learning for health care. Nat Med. 2019;25;1337-1340. doi: 10.1038/s41591-019-0548-6.
• 22. Tonekaboni S, Joshi S, McCradden MD, Goldenberg A. What Clinicians Want: Contextualizing Explainable Machine Learning for Clinical End Use. Proceedings of the 4th Machine Learning for Healthcare Conference. Proceedings of Machine Learning Research. 2019;106:359-380. doi: 10.48550/arXiv.1905.05134.
• 23. Lin SY, Mahoney MR, Sinsky CA. Ten Ways Artificial Intelligence Will Transform Primary Care. J Gen Intern Med. 2019;34(8):1626-1630. doi: 10.1007/s11606-019-05035-1.