Prediction of factors causing death in Covid 19 patients with machine and ensemble learning models

Year 2025, Volume: 6 Issue: 2, 46 - 52, 29.12.2025

Fatih Üçkardeş , Ercan Çil , Fahrettin Kaya , Hakan Sezgin Sayiner , Önder Yumrutaş

https://doi.org/10.51539/biotech.1739101

https://izlik.org/JA54AP69JJ

Abstract

The aim of study was aimed to predict the prognostic factors that cause mortality related to the Covid 19 with machine and ensemble learning model. Patient information was collected from the Adıyaman Education and Research Hospital between 01 January 2020 and 31 December 2021.Totally, 487 patients were included in the study. Random Forest (rf), Support Vector Machine with a Radial Basis Kernel Function (svmRadial), C5.0, Ranger and Gradient Boosting Machine (Gbm) models and the ensemble model were used as machine learning models. Ibreakdown plot was used to individualize the results. According to the machine classification criteria, although all models performed strongly, the Gbm model had the highest classification criteria. Consequently, it is thought that it may play an important role not only for Covid 19, but also for the classification of other diseases, making individual risk estimations and creating patient-specific personal treatment programs.

Keywords

Personalized medicine , Ensemble learning , machine learning , ibreakdown

References

• Ali I, Alharbi OML (2020) COVID-19: Disease, management, treatment, and social impact. Sci Total Environ 728:138861
• Biecek P (2018) DALEX: Explainers for complex predictive models in R. J Mach Learn Res 19:1–5
• Chicco D, Jurman G (2020) The advantages of the Matthews correlation coefficient (MCC) over F1 score and accuracy in binary classification evaluation. BMC Genomics 21:6
• Fleitas PE, Paz JA, Simoy MI, Vargas CCRO, Krolewiecki AJ, Aparicio JP (2021) Clinical diagnosis of COVID-19: A multivariate logistic regression analysis of symptoms at presentation. J Infect Public Health 11:221–37
• George B, Seals S, Aban I (2014) Survival analysis and regression models. J Nucl Cardiol 21(4):686–94
• Hashim D, Weiderpass E (2017) Cancer survival and survivorship. In: Schwab M (ed) Encyclopedia of Cancer. 3rd ed. Springer, Berlin, pp 250–9
• Kaya F, Korkmaz F, Efe E (2019) R ile istatiksel hesaplama için bir web sayfası uygulaması: Tek yönlü anova örneği. In: Proc Int Symp Adv Eng Technol (ISADET); Kahramanmaraş, Turkey, pp 1–5
• Li X, Xu S, Yu M, Wang K, Yu T, Zhou Y, Shi J, Zhou M, Wu B, Yang Z, Zhang C, Yue J, Zhang Z, Renz H, Liu X, Xie J, Xie M, Zhang J (2020) Risk factors for severity and mortality in adult COVID-19 inpatients in Wuhan. J Allergy Clin Immunol 146(1):110–8
• Liu Z, Hu D, Li J, Xia Q, Gong Y, Li Z, Wu Q, Yi M, Huang Y, Wu M, Guo L, Wu X (2021) Prognostic potential of liver enzymes in patients with COVID-19 at the Leishenshan Hospital in Wuhan. Front Cell Infect Microbiol 11:636999
• Mahendra M, Nuchin A, Kumar R, S S, Mahesh PA (2021) Predictors of mortality in patients with severe COVID-19 pneumonia—A retrospective study. Adv Respir Med 89(2):135–44
• Önal U, Özge AG, Akalın H, Acet A, Semet C, Demirdöğen E, Dilektaşlı AG, Sağlık İ, Kazak E, Özkaya G, Çoşkun F, Ediger D, Heper Y, Ursavaş A, Yılmaz E, Uzaslan E, Karadağ M (2022) Prognostic factors for COVID-19 patients. J Infect Dev Ctries 16:409–17
• Powers DMW (2007) Evaluation: From precision, recall and F-factor to ROC, informedness, markedness and correlation. Flinders Univ Tech Rep SIE-07-001
• Puri N, Gupta P, Agarwal P, Verma S, Krishnamurthy B (2018) MAGIX: Model agnostic globally interpretable explanations. arXiv 1706.07160
• Rastogi P, Singh BK (2019) A multivariate binary logistic regression modeling for assessing various risk factors that affect diabetes. Int J Sci Technol Res 8(8):589–99
• Ribeiro MT, Singh S, Guestrin C (2016) “Why should I trust you?”: Explaining the predictions of any classifier. Proc 22nd ACM SIGKDD Int Conf Knowl Discov Data Min, pp 1135–44
• Sanzo DM, Cipolloni L, Borro M, La Russa R, et al (2017) Clinical applications of personalized medicine: A new paradigm and challenge. Curr Pharm Biotechnol 18(3):194–203
• Staniak M, Biecek P (2018) Explanations of model predictions with live and breakDown packages. R J 10(2):395–409
• Trevethan R (2017) Sensitivity, specificity, and predictive values: foundations, pliabilities, and pitfalls in research and practice. Front Public Health 5:307
• Türk D, Kökver Y (2022) Application with deep learning models for COVID-19. Sakarya Univ J Comput Inform Sci 5(2):169–80
• Wang P, Zheng X, Li J, Zhu B (2020) Prediction of epidemic trends in COVID-19 with logistic model and machine learning technics. Chaos Solitons Fractals 139:110058
• Zhang Z, Chen L, Xu P, Hong Y (2022) Predictive analytics with ensemble modeling in laparoscopic surgery: a technical note. Laparosc Endosc Robot Surg 5(1):25–34
• Zhou F, Yu T, Du R, Fan G, Liu Y, Liu Z, Xiang J, Wang Y, Song B, Gu X, Guan L, Wei Y, Li H, Wu X, Hu J, Tu S, Zhang Y, Chen H, Cao B (2020) Clinical course and risk factors for mortality of adult inpatients with COVID-19 in Wuhan, China: a retrospective cohort study. Lancet 395:1054–62