SARS-CoV-2 severity prediction in young adults using artificial intelligence

   Aim: to build a predictive model for severe COVID-19 prediction in young adults using deep learning methods.
   Materials and methods: data from 906 medical records of patients aged 18 to 44 years with laboratory-confirmed SARS-CoV-2 infection during 2020–2021 period was analyzed. Evaluation of laboratory and instrumental data was carried out using the Mann-Whitney U-test. The level of statistical significance was p≤0,05. The neural network was trained using the Pytorch framework.
   Results: in patients with mild to moderate SARS-CoV-2 infection, peripheral oxygen saturation, erythrocytes, hemoglobin, total protein, albumin, hematocrit, serum iron, transferrin, and absolute peripheral blood eosinophil and lymphocyte counts were significantly higher than in patients with severe СOVID-19 (p< 0,001). The values of the absolute number of neutrophils, ESR, glucose, ALT, AST, CPK, urea, LDH, ferritin, CRP, fibrinogen, D-dimer, respiration rate, heart rate, blood pressure in the group of patients with mild and moderate severity were statistically significantly lower than in the group of severe patients (p < 0.001). Eleven indicators were identified as predictors of severe COVID-19 (peripheral oxygen level, peripheral blood erythrocyte count, hemoglobin level, absolute eosinophil count, absolute lymphocyte count, absolute neutrophil count, LDH, ferritin, C-reactive protein, D-dimer levels) and their threshold values. A model intended to predict COVID-19 severity in young adults was built.
   Conclusion. The values of laboratory and instrumental indicators obtained in patients with SARS-CoV-2 infection upon admission significantly differ. Among them eleven indicators were significantly associated with the development of a severe COVID-19. A predictive model based on artificial intelligence method with high accuracy predicts the likelihood of severe SARS-CoV-2 course development in young adults.

1. Crevier, D. A. I.: the tumultuous history of the search for artificial intelligence / D. Crevier – DOI: 10.3233/AIC-1995-8108. – Text: electronic // Basic Books, Inc. – 1993. – URL: https://www.researchgate.net/publication/233820788_AI_The_Tumultuous_History_of_the_Search_for_Artificial_Intelligence (data obrashhenija: 05. 09. 2022).

2. Mitchell, T. M. Machine learning / T. M. Mitchell. – Text: electronic // Burr Ridge, IL: McGraw Hill. – 1997. – № 45 (37). – P. 870-877. – URL: https://www.cin.ufpe.br/~cavmj/Machine%20-%20Learning%20-%20Tom%20Mitchell.pdf (data obrashhenija: 05. 09. 2022).

3. Shortliffe, E. Computer-based medical consultations: MYCIN / E. Shortliffe – DOI: 10.1016/B978-0-444-00179-5.X5001-X. – Text: electronic // Elsevier. – 2012. – № 2. – URL: https://books.google.ru/books/about/Computer_Based_Medical_Consultations_MYC.html?id=i9QXugPQw6oC&redir_esc=y (data obrashhenija: 05. 09. 2022).

4. Hinton, G. Deep learning—a technology with the potential to transform health care / G. Hinton – DOI: 10.1001/jama.2018.11100. – Text: electronic // Jama. – 2018. – № 320 (11). – P. 1101-1102. – URL: https://jamanetwork.com/journals/jama/article-abstract/2701666 (data obrashhenija: 05. 09. 2022).

5. Silkina, U. I. Discriminant analysis of variational pulsometry parameters / U. I. Silkina, V. A. Balandin // Russian Technological Journal. – 2020. – № 8 (3). – P. 81-91. (In Russ.) doi: 10.32362/2500-316X-2020-8-3-81-91

6. Rawson, T. M. A systematic review of clinical decision support systems for antimicrobial management: are we failing to investigate these interventions appropriately / T. M. Rawson, L. S. Moore, B. Hernandez [et. al.]. – DOI: 10.1016/j.cmi.2017.02.028. – Text: electronic // Clinical Microbiology and Infection. – 2017. – № 23 (8). – P. 524-532. – URL: https://www.clinicalmicrobiologyandinfection.com/article/S1198-743X(17)30125-8/fulltext (data obrashhenija: 05. 09. 2022).

7. Martínez-Agüero, S. Machine learning techniques to identify antimicrobial resistance in the intensive care unit / S. Martínez-Agüero, I. Mora-Jiménez, J. Lérida-García [et. al.]. – DOI: 10.3390/e21060603. – Text: electronic // Entropy. – 2019. – № 21 (6). – URL: https://www.mdpi.com/1099-4300/21/6/603 (data obrashhenija: 05. 09. 2022).

8. Hartvigsen, T. Early Prediction of MRSA Infections using Electronic Health Records / T. Hartvigsen, C. Sen, S. Brownell [et. al.]. – DOI: 10.5220/0006599601560167. – Text: electronic // HEALTHINF. – 2018. – P. 156-167. – URL: https://www.scitepress.org/Link.aspx?doi=10.5220/0006599601560167 (data obrashhenija: 05. 09. 2022).

9. Revuelta-Zamorano, P. Prediction of healthcare associated infections in an intensive care unit using machine learning and big data tools / P. Revuelta-Zamorano, A. Sánchez, J. L. Rojo-Álvarez [et. al.]. – DOI: 10.1007/978-3-319-32703-7_163. – Text: electronic // XIV Mediterranean conference on medical and biological engineering and computing, Springer International Publishing. – 2016. – № 57. – P. 840–845. – URL: https://link.springer.com/chapter/10.1007/978-3-319-32703-7_163 (data obrashhenija: 05. 09. 2022).

10. Hernandez, B. Supervised learning for infection risk inference using pathology data / B. Hernandez, P. Herrero, T. M. Rawson [et. al.]. – DOI: 10.1186/s12911-017-0550-1. – Text: electronic // BMC medical informatics and decision making. – 2017. – № 17 (168). – P. 1-12. – URL: https://bmc-medinformdecismak.biomedcentral.com/articles/10.1186/s12911-017-0550-1 (data obrashhenija: 05. 09. 2022).

11. Agbehadji, I. E. Review of big data analytics, artificial intelligence and nature-inspired computing models towards accurate detection of COVID-19 pandemic cases and contact tracing / I. E. Agbehadji, B. O. Awuzie, A. B. Ngowi [et. al.]. – DOI: 10.3390/ijerph17155330. – Text: electronic // Int J Environ Res Publ Health. – 2020. – № 17 (15). – P. 5330. – URL: https://www.mdpi.com/1660-4601/17/15/5330 (data obrashhenija: 05. 09. 2022).

12. Naudé, W. Artificial intelligence vs Covid-19: limitations, constraints and pitfalls / W. Naudé – DOI: 10.1007/s00146-020-00978-0. – Text: electronic // AI Soc. – 2020. – № 35. – P. 761–765. – URL: https://link.springer.com/article/10.1007/s00146-020-00978-0#citeas (data obrashhenija: 05. 09. 2022).

13. Vaid, A. Machine learning to predict mortality and critical events in covid-19 positive New York city patients: a cohort study / A. Vaid, S. Somani, A. J. Russak [et. al.]. – DOI: 10.2196/24018. – Text: electronic // J Med Internet Res. – 2020. – № 22 (11). – URL: https://www.jmir.org/2020/11/e24018 (data obrashhenija: 05. 09. 2022).

14. Rechtman, E. Vital signs assessed in initial clinical encounters predict covid-19 mortality in an NYC hospital system / E. Rechtman, P. Curtin, E. Navarro [et. al.]. – DOI: 10.1038/s41598-020-78392-1. – Text: electronic // Sci Rep. – 2020. – № 10 (21545). – P. 1-6. – URL: https://www.nature.com/articles/s41598-020-78392-1 (data obrashhenija: 05. 09. 2022).

15. Cabitza, F. Development, evaluation, and validation of machine learning models for covid-19 detection based on routine blood tests / F. Cabitza, A. Campagner, D. Ferrari [et. al.]. – DOI: 10.1515/cclm-2020-1294. – Text: electronic // Clin Chem Lab Med. – 2020. – № 59 (2). – P. 421-431. – URL: https://www.degruyter.com/document/doi/10.1515/cclm-2020-1294/html (data obrashhenija: 05. 09. 2022).

16. Goodman-Meza, D. A machine learning algorithm to increase COVID-19 inpatient diagnostic capacity / D. Goodman-Meza, A. Rudas, J. N. Chiang [et. al.]. – DOI: 10.1371/journal.pone.0239474. – Text: electronic // PloS One. – 2020. – № 15 (9). – URL: https://journals.plos.org/plosone/article?id=10.1371/journal.pone.0239474 (data obrashhenija: 05. 09. 2022).

17. AlJame, M. Ensemble learning model for diagnosing COVID-19 from routine blood tests / M. Al Jame, I. Ahmad, A. Imtiaz [et. al.]. – DOI: 10.1016/j.imu.2020.100449. – Текст: электронный // Inform Med Unlocked. – 2020. – № 21 (100449). – URL: https://www.sciencedirect.com/science/article/pii/S2352914820305992?via%3Dihub (data obrashhenija: 05. 09. 2022).

18. Polyakov, A. S. Prognostic Significance of Some Hematological Syndromes in SARS-CoV-2 Infection / A. S. Polyakov, K. V. Kozlov // Hematology. Transfusiology. Eastern Europe. – 2020. – № 6 (2). – P. 161-171. (In Russ.)

19. Nacional’nyj proekt «Zdravoohranenie». Federal’nyj proekt «Sozdanie edinogo cifrovogo kontura v zdravoohranenii na osnove edinoj gosudarstvennoj informacionnoj sistemy v sfere zdravoohranenija (EGISZ)», utv. Ministerstvom zdravoohranenija Rossii 16. 10. 2019

20. Dyussenbayev, A. (2017). Age Periods Of Human Life / A. Dyussenbayev. – DOI: 10.14738/assrj.46.2924 4(6) 258-263. – Text: electronic // Advances in Social Sciences Research Journal. – 2017. – № 4 (6). – URL: https://journals.scholarpublishing.org/index.php/ASSRJ/article/view/2924 (data obrashhenija: 05. 09. 2022).

21. Vremennye metodicheskie rekomendacii po profilaktike, diagnostike i lecheniju novoj koronavirusnoj infekcii (COVID-19) versija 16 (URL: https://static-0.minzdrav.gov.ru/system/attachments/attaches/000/060/193/original/%D0%92%D0%9C%D0%A0_COVID-19_V16.pdf (data obrashhenija: 05. 09. 2022).

22. Kuhn, M. Feature Engineering and Selection: A Practical Approach for Predictive Models / M. Kuhn , K. Johnson. – Chapman & Hall/CRC, 2019. – 310 p.

23. Voroncov K. V. Mashinnoe obuchenie (kurs lekcij) / K. V. Voroncov. URL: http://www.machinelearning.ru/wiki/index.php?title=Машинное_обучение_%28курс_лекций%2C_К.В.Воронцов%29 (data obrashhenija: 05. 09. 2022).

24. Bruce, P. Practical Statistics for Data Scientists: 50+ Essential Concepts Using R and Python / P. Bruce, A. Bruce, P. Gedek. – O’Reilly, 2020. – 368 p.

25. Svidetel’stvo o gosudarstvennoĭ registracii programmy dlja JeVM No2022665747. Rossiĭskaja Federacija. «CASP(ER) – Covid-19 assisted severity prediction (early reliable)» / K. Kas’janenko; zajavitel’ i pravoobladatel’ Kas’janenko Kristina. – No 2022665747; zajavka 06. 08. 2022; zaregistr. 19. 08. 2022; opubl. 19. 08. 2022, Bjul. No 8. – 1 s.

26. Bayat, V. A severe acute respiratory syndrome coronavirus 2 (SARS-CoV-2) prediction model from standard laboratory tests / V. Bayat, S. Phelps, R. Ryono [et. al.]. – DOI: 10.1093/cid/ciaa1175. – Текст: электронный // Clin Infect Dis. – 2020. – № 73 (9). – P. 2901-2907. – URL: https://academic.oup.com/cid/article/73/9/e2901/5891814?login=false (data obrashhenija: 05. 09. 2022).

27. Kukar, M. Covid-19 diagnosis by routine blood tests using machine learning / M. Kukar, G. Gunčar, T. Vovko [et. al.]. – DOI: 10.1038/s41598-021-90265-9. – Text: electronic // Sci Rep. – 2021. – № 11 (10738). – URL: https://www.nature.com/articles/s41598-021-90265-9#citeas (data obrashhenija: 05. 09. 2022).

28. Wu, J. Rapid and accurate identification of covid-19 infection through machine learning based on clinical available blood test results / J. Wu, P. Zhang, L. Zhang [et. al.]. – DOI: 10.1101/2020.04.02.20051136. – Text: electronic // medRxiv. – 2020. – URL: https://www.medrxiv.org/content/10.1101/2020.04.02.20051136v1 (data obrashhenija: 05. 09. 2022).

29. Brinati, D. Detection of COVID-19 infection from routine blood exams with machine learning: a feasibility study / D. Brinati, A. Campagner, D. Ferrari [et. al.]. – DOI: 10.1007/s10916-020-01597-4. – Text: electronic // J Med Syst. – 2020. – № 44 (135). – URL: https://link.springer.com/article/10.1007/s10916-020-01597-4 (data obrashhenija: 05. 09. 2022).

30. Butt A. A. Rate and risk factors for severe/critical disease among fully vaccinated persons with breakthrough severe acute respiratory syndrome coronavirus 2 (SARS-CoV-2) infection in a high-risk national population / A. A. Butt, P. Yan, O. S. Shaikh [et al]. – DOI: 10.1093/cid/ciab1023. – Text: electronic // Clin Infect Dis. – 2021. – № 75 (1). – URL: https://www.ncbi.nlm.nih.gov/pmc/articles/PMC8689859/ (data obrashhenija: 05. 09. 2022).