Development of a Prognostic Model for the Outcome of Viral Lung Disease Using Machine Learning Algorithms

Background: During periods of increasing respiratory infections, stratifying patient care for virus-associated lung injury is crucial.

Objective: To develop a prognostic model for the outcome of viral lung injury using machine learning algorithms.

Materials and methods: The study included 295 patients with COVID-associated pneumonia, divided into two groups: 1) deceased (n=78) and 2) survivors (n=217). Data processing was performed using IDE R Studio (Version 4.3.1). The prognostic model was created using potential predictors and machine learning algorithms: multivariate logistic regression, random forest, and stochastic gradient boosting. A 5-fold cross-validation method (KFold) was used. Prediction models for mortality were implemented in Google Colaboratory with Python. Model quality was assessed by metrics such as ROC-AUC and confusion matrix, which provided measures like precision, recall, sensitivity, specificity, and F1-score.

Results: The prognostic outcome model was based on mortality predictors, demonstrating a high level of statistical significance between the predicted groups, with significant predictors including the presence of two or more comorbidities, respiratory failure above grade 2, pronounced myalgia and dyspnea, neutrophil-to-lymphocyte ratio >5.1, a critical decrease in eosinophil count accompanied by elevated ESR, glucose, AST, CRP, urea levels, and decreased hemoglobin (p<0.05).

Conclusion: The mortality risk prediction model developed using machine learning methods, particularly the random forest algorithm (AUC=0.99), demonstrates high accuracy and enables the assessment of mortality risk at hospital admission, guiding management decisions and optimizing treatment strategies.

1. Ershov FI. Why may the 21st century become the «century of pandemics»? А question for discussion. Problems of Virology. 2024;69(1):88–90. (In Russ.). https://doi.org/10.36233/0507-4088-227

2. Martyanova AE, Azhmukhamedov IM. SEIRD model describing the dynamics of spread viral infections considering the appearence of new strains. Caspian journal: Control and High Technologies. 2022;4(60):38-46. (In Russ.). https://doi.org/10.54398/20741707_2022_4_38

3. Azimova NN, Bedoidze MV, Kholodova SN, et al. Statistical assessment of biogenic risk to the human population from new viral infections based on COVID-19. Safety of technogenic and natural systems. 2023;1:4-15. (In Russ.). https://doi.org/10.23947/2541-9129-2023-1-4-15

4. Ipekci AM, Buitrago-Garcia D, Meili KW, et al. Outbreaks of publications about emerging infectious diseases: the case of SARS-CoV-2 and Zika virus. BMC Med Res Methodol. 2021;21(1):50. PMID: 33706715. PMCID: PMC7948668. https://doi.org/10.1186/s12874-021-01244-7

5. Wynants L, Van Calster B, Collins GS, et al. Prediction models for diagnosis and prognosis of covid-19: systematic review and critical appraisal. BMJ. 2020;369:m1328. PMID: 32265220. PMCID: PMC7222643. https://doi.org/10.1136/bmj.m1328

6. Mareev VYu, Begrambekova YuL, Mareev YuV. How evaluate results of treatment in patients with COVID-19? Symptomatic Hospital and Outpatient Clinical Scale for COVID-19 (SHOCS-COVID). Kardiologiia. 2020;60(11):35-41. (In Russ.). https://doi.org/10.18087/cardio.2020.11.n1439

7. Dvoretsky LI, Komarova IS, Mukhina NV, Cherkasova NA, Dyatlov MV. New coronaviral infection (COVID-19) in patients of elderly and senile age. Medical Bulletin of the North Caucasus. 2022;3(17):335-341. (In Russ.). https://doi.org/10.14300/mnnc.2022.17082

8. Vdoushkina ES, Borodulina EA, Povalyaeva LV, Sukhanova AV, Zhilinskaya KV, Sutyagin AV. The timing of referral and the severity of condition in patients with lung damage and suspected novel coronavirus infection on admission to hospital during the beginning of the pandemic. Vrach. 2020;31(11):60-63. (In Russ.). https://doi.org/10.29296/25877305-2020-11-12.

9. Bakhitov VV, Aliev SR, Marcinkevich VM, Dmitrieva KV, Maslennikov RV, Vasilieva EV. Structure of mortality among patients of an outpatient center during the pandemic of the new coronavirus infection (COVID-19) Current problems of health care and medical statistics. 2022;S2:67-76. (In Russ.). https://doi.org/10.24412/2312-2935-2022-2-67-76

10. Korakas E, Ikonomidis I, Kousathana F, et al. Obesity and COVID-19: immune and metabolic derangement as a possible link to adverse clinical outcomes. Am J Physiol Endocrinol Metab. 2020;319(1):E105-E109. PMID: 32459524. PMCID: PMC7322508. https://doi.org/10.1152/ajpendo.00198.2020

11. Giamarellos-Bourboulis EJ, Netea MG, Rovina N, et al. Complex Immune Dysregulation in COVID-19 Patients with Severe Respiratory Failure. Cell Host Microbe. 2020;27(6):992-1000.e3. PMID: 32320677. PMCID: PMC7172841. https://doi.org/10.1016/j.chom.2020.04.009

12. Yokota SH, Kuroiwa E, Nishioka K. Novel coronavirus disease (COVID-19) and cytokine storms. For more effective treatment from the viewpoints of an inflammatory pathophysiology perspective. Infectious diseases: news, opinions, training. 2020;9(4):13-25. (In Russ.). https://doi.org/10.33029/2305-3496-2020-9-4-13-25

13. Zhang C, Wu Z, Li JW, Zhao H, Wang GQ. Cytokine release syndrome in severe COVID-19: interleukin-6 receptor antagonist tocilizumab may be the key to reduce mortality. Int J Antimicrob Agents. 2020;55(5):105954. PMID: 32234467. PMCID: PMC7118634. https://doi.org/10.1016/j.ijantimicag.2020.105954

14. Zhumabaeva TT, Tursunbaeva AT, Kadyrbaeva AA. Changes in biochemical indicators of the blood of patients with fatal COVID-19. Bulletin of science and practice. 2023;9(4.):256-264. (In Russ.). https://doi.org/10.33619/2414-2948/89/29

15. Bilichenko TN. Risk factors, immunologic mechanisms and biological markers of severe course of COVID-19 course (study overview). Russian Medical Journal. 2021;5(5):237-244. (In Russ.). https://doi.org/10.32364/2587-6821-2021-5-5-237-244

16. Tian S, Hu W, Niu L, Liu H, Xu H, Xiao SY. Pulmonary Pathology of Early-Phase 2019 Novel Coronavirus (COVID-19) Pneumonia in Two Patients With Lung Cancer. J Thorac Oncol. 2020;15(5):700-704. PMID: 32114094. PMCID: PMC7128866. https://doi.org/10.1016/j.jtho.2020.02.010

17. Lagunas-Rangel FA. Neutrophil-to-lymphocyte ratio and lymphocyte-to-C-reactive protein ratio in patients with severe coronavirus disease 2019 (COVID-19): A meta-analysis. J Med Virol. 2020;92(10):1733-1734. PMID: 32242950. PMCID: PMC7228336. https://doi.org/10.1002/jmv.25819

18. Liu Y, Du X, Chen J, et al. Neutrophil-to-lymphocyte ratio as an independent risk factor for mortality in hospitalized patients with COVID-19. J Infect. 2020;81(1):e6-e12. PMID: 32283162. PMCID: PMC7195072. https://doi.org/10.1016/j.jinf.2020.04.002

19. Borukaeva I.H., Abazova Z.H., Temirzhanova F.H., Yusupova M.M. COVID-19: Observations on standard treatment algorithms. Medical Immunology (Russia). 2021;23(4):909-914. (In Russ.). https://doi/org/10.15789/1563-0625-COO-2265