Pulmonary fibrosis is one of the most severe long-term consequences of COVID-19. Corticosteroid treatment increases the chances of recovery; unfortunately, it can also have side effects. Therefore, we aimed to develop prediction models for a personalized selection of patients benefiting from corticotherapy. The experiment utilized various algorithms, including Logistic Regression, k-NN, Decision Tree, XGBoost, Random Forest, SVM, MLP, AdaBoost, and LGBM. In addition easily human-interpretable model is presented. All algorithms were trained on a dataset consisting of a total of 281 patients. Every patient conducted an examination at the start and three months after the post-COVID treatment. The examination comprised a physical examination, blood tests, functional lung tests, and an assessment of health state based on X-ray and HRCT. The Decision tree algorithm achieved balanced accuracy (BA) of 73.52%, ROC-AUC of 74.69%, and 71.70% F1 score. Other algorithms achieving high accuracy included Random Forest (BA 70.00%, ROC-AUC 70.62%, 67.92% F1 score) and AdaBoost (BA 70.37%, ROC-AUC 63.58%, 70.18% F1 score). The experiments prove that information obtained during the initiation of the post-COVID-19 treatment can be used to predict whether the patient will benefit from corticotherapy. The presented predictive models can be used by clinicians to make personalized treatment decisions.

Centre for Advanced Studies Dr A P J Abdul Kalam Technical University Jankipuram Vistar Lucknow 226021 India

Czech National e Health Center University Hospital Olomouc 1 P Pavlova 6 779 00 Olomouc Czech Republic

Department of Respiratory Diseases and Tuberculosis University Hospital Brno and Faculty of Medicine and Dentistry Masaryk University Brno Jihlavska 340 20 625 00 Brno Czech Republic

Department of Respiratory Medicine University Hospital Olomouc and Faculty of Medicine and Dentistry Palacky University Olomouc 1 P Pavlova 6 779 00 Olomouc Czech Republic

Department of Telecommunications Faculty of Electrical Engineering and Communications Brno University of Technology Technicka 12 616 00 Brno Czech Republic

Zobrazit více v PubMed

Afshar Z.M., Ebrahimpour S., Javanian M., Koppolu V., Vasigala V.K.R., Hasanpour A.H., Babazadeh A. Coronavirus disease 2019 (COVID-19), MERS and SARS: Similarity and difference. J. Acute Dis. 2020;9:194

Parums D.V. Long COVID, or Post-COVID Syndrome, and the Global Impact on Health Care. Med. Sci. Monit. 2021;27:e933446. doi: 10.12659/MSM.933446. PubMed DOI PMC

Dixit N.M., Churchill A., Nsair A., Hsu J.J. Post-Acute COVID-19 Syndrome and the cardiovascular system: What is known? Am. Heart J. Plus Cardiol. Res. Pract. 2021;5:100025. doi: 10.1016/j.ahjo.2021.100025. PubMed DOI PMC

Nalbandian A., Sehgal K., Gupta A., Madhavan M.V., McGroder C., Stevens J.S., Cook J.R., Nordvig A.S., Shalev D., Sehrawat T.S., et al. Post-acute COVID-19 syndrome. Nat. Med. 2021;27:601–615. doi: 10.1038/s41591-021-01283-z. PubMed DOI PMC

Cioboata R., Nicolosu D., Streba C.T., Vasile C.M., Olteanu M., Nemes A., Gheorghe A., Calarasu C., Turcu A.A. Post-COVID-19 Syndrome Based on Disease Form and Associated Comorbidities. Diagnostics. 2022;12:2502. doi: 10.3390/diagnostics12102502. PubMed DOI PMC

Sova M., Doubková M., Solichová L., Šterclová M., Genzor S. Treatment of pulmonary involvement of patients after COVID-19 (Coronovirus disease 2019)—Position document of the Czech Pneumological and Phthisiological Society. [(accessed on 31 September 2021)];Czech Pneumol. Phtiseol. Soc. 2020 :1–11. Available online: http://www.pneumologie.cz/upload/1612528705.1554.docx.

Bieksiene K., Zaveckiene J., Malakauskas K., Vaguliene N., Zemaitis M., Miliauskas S. Post COVID-19 Organizing Pneumonia: The Right Time to Interfere. Medicina. 2021;57:283. doi: 10.3390/medicina57030283. PubMed DOI PMC

National Institutes of Health. Hospitalized Adults: Therapeutic Management. [(accessed on 19 April 2022)]; Available online: https://www.covid19treatmentguidelines.nih.gov/management/clinical-management/hospitalized-adults–therapeutic-management/

Fadel R., Morrison A.R., Vahia A., Smith Z.R., Chaudhry Z., Bhargava P., Miller J., Kenney R.M., Alangaden G., Ramesh M.S., et al. Early short-course corticosteroids in hospitalized patients with COVID-19. Clin. Infect. Dis. 2020;71:2114–2120. doi: 10.1093/cid/ciaa601. PubMed DOI PMC

Estella Á., Garmendia J.G., de la Fuente C., Casas J.M., Yuste M.E., Villar R.A., Estecha M.A., Mateos L.Y., Bulnes M.C., Loza A., et al. Predictive factors of six-week mortality in critically ill patients with SARS-CoV-2: A multicenter prospective study. Med. Intensiv. 2021;46:179–191. doi: 10.1016/j.medin.2021.02.013. PubMed DOI PMC

Mongardon N., Piagnerelli M., Grimaldi D., Perrot B., Lascarrou J.B. Impact of late administration of corticosteroids in COVID-19 ARDS. Intensive Care Med. 2021;47:110–112. doi: 10.1007/s00134-020-06311-z. PubMed DOI PMC

Monreal E., de la Maza S.S., Natera-Villalba E., Beltrán-Corbellini Á., Rodríguez-Jorge F., Fernández-Velasco J.I., Walo-Delgado P., Muriel A., Zamora J., Alonso-Canovas A., et al. High versus standard doses of corticosteroids in severe COVID-19: A retrospective cohort study. Eur. J. Clin. Microbiol. Infect. Dis. 2021;40:761–769. doi: 10.1007/s10096-020-04078-1. PubMed DOI PMC

Kumar G., Patel D., Hererra M., Jefferies D., Sakhuja A., Meersman M., Dalton D., Nanchal R., Guddati A.K. Do high-dose corticosteroids improve outcomes in hospitalized COVID-19 patients? J. Med. Virol. 2022;94:372–379. doi: 10.1002/jmv.27357. PubMed DOI PMC

Duarte-Millán M.A., Mesa-Plaza N., Guerrero-Santillán M., Morales-Ortega A., Bernal-Bello D., Farfán-Sedano A.I., García de Viedma-García V., Velázquez-Ríos L., Frutos-Pérez B., De Ancos-Aracil C.L., et al. Prognostic factors and combined use of tocilizumab and corticosteroids in a Spanish cohort of elderly COVID-19 patients. J. Med. Virol. 2022;94:1540–1549. doi: 10.1002/jmv.27488. PubMed DOI PMC

Lim P.C., Wong K.L., Rajah R., Chong M.F., Chow T.S., Subramaniam S., Lee C.Y. Comparing the efficacy of tocilizumab with corticosteroid therapy in treating COVID-19 patients: A systematic review and meta-analysis. DARU J. Pharm. Sci. 2022;30:211–228. doi: 10.1007/s40199-021-00430-8. PubMed DOI PMC

Group R.C. Dexamethasone in hospitalized patients with COVID-19. N. Engl. J. Med. 2021;384:693–704. PubMed PMC

Mishra G.P., Mulani J. Corticosteroids for COVID-19: The search for an optimum duration of therapy. Lancet Respir. Med. 2021;9:e8. doi: 10.1016/S2213-2600(20)30530-0. PubMed DOI PMC

Kuno T., Sahashi Y., Kawahito S., Takahashi M., Iwagami M., Egorova N.N. Prediction of in-hospital mortality with machine learning for COVID-19 patients treated with steroid and remdesivir. J. Med. Virol. 2022;94:958–964. doi: 10.1002/jmv.27393. PubMed DOI PMC

Lam C., Siefkas A., Zelin N.S., Barnes G., Dellinger R.P., Vincent J.L., Braden G., Burdick H., Hoffman J., Calvert J., et al. Machine Learning as a Precision-Medicine Approach to Prescribing COVID-19 Pharmacotherapy with Remdesivir or Corticosteroids. Clin. Ther. 2021;43:871–885. doi: 10.1016/j.clinthera.2021.03.016. PubMed DOI PMC

Gao Y., Xiong X., Jiao X., Yu Y., Chi J., Chen L., Li S., Gao Q. Development and Validation of a Machine Learning Model for Prediction of Response to Corticosteroid Therapy In COVID-19 Patients. SSRN. 2021:1–21. doi: 10.2139/ssrn.3834263. PubMed DOI PMC

Chen H., Xie J., Su N., Wang J., Sun Q., Li S., Jin J., Zhou J., Mo M., Wei Y., et al. Corticosteroid therapy is associated with improved outcome in critically ill coronavirus disease 2019 patients with hyperinflammatory phenotype. Chest. 2021;159:1793–1802. doi: 10.1016/j.chest.2020.11.050. PubMed DOI PMC

Ahmad J., Saudagar A.K.J., Malik K.M., Khan M.B., AlTameem A., Alkhathami M., Hasanat M.H.A. Prognosis Prediction in COVID-19 Patients through Deep Feature Space Reasoning. Diagnostics. 2023;13:1387. doi: 10.3390/diagnostics13081387. PubMed DOI PMC

Whitaker M., Elliott J., Chadeau-Hyam M., Riley S., Darzi A., Cooke G., Ward H., Elliott P. Persistent symptoms following SARS-CoV-2 infection in a random community sample of 508,707 people. medRxiv. 2021 doi: 10.1101/2021.06.28.21259452. DOI

Myall K.J., Mukherjee B., Castanheira A.M., Lam J.L., Benedetti G., Mak S.M., Preston R., Thillai M., Dewar A., Molyneaux P.L., et al. Persistent Post–COVID-19 Interstitial Lung Disease. An Observational Study of Corticosteroid Treatment. Ann. Am. Thorac. Soc. 2021;18:799–806. doi: 10.1513/AnnalsATS.202008-1002OC. PubMed DOI PMC

National Institutes of Health. Nonhospitalized Adults: Therapeutic Management. [(accessed on 12 May 2022)]; Available online: https://www.covid19treatmentguidelines.nih.gov/management/clinical-management-of-adults/nonhospitalized-adults–therapeutic-management/

Le Bon S.D., Konopnicki D., Pisarski N., Prunier L., Lechien J.R., Horoi M. Efficacy and safety of oral corticosteroids and olfactory training in the management of COVID-19-related loss of smell. Eur. Arch.-Oto-Rhino-Laryngol. 2021;278:3113–3117. doi: 10.1007/s00405-020-06520-8. PubMed DOI PMC

Touisserkani S.K., Ayatollahi A. Oral corticosteroid relieves post-COVID-19 anosmia in a 35-year-old patient. Case Rep. Otolaryngol. 2020;2020:5892047. doi: 10.1155/2020/5892047. PubMed DOI PMC

Lundberg S.M., Erion G., Chen H., DeGrave A., Prutkin J.M., Nair B., Katz R., Himmelfarb J., Bansal N., Lee S.I. From local explanations to global understanding with explainable AI for trees. Nat. Mach. Intell. 2020;2:2522–5839. doi: 10.1038/s42256-019-0138-9. PubMed DOI PMC

Rhys H. Machine Learning with R, the Tidyverse, and Mlr. Simon and Schuster; New York, NY, USA: 2020.

Taud H., Mas J. Geomatic Approaches for Modeling Land Change Scenarios. Springer; Berlin/Heidelberg, Germany: 2018. Multilayer perceptron (MLP) pp. 451–455.

Ke G., Meng Q., Finley T., Wang T., Chen W., Ma W., Ye Q., Liu T.Y. Advances in Neural Information Processing Systems 30. NeurIPS; Long Beach, CA, USA: 2017. Lightgbm: A highly efficient gradient boosting decision tree.

Hossin M., Sulaiman M.N. A review on evaluation metrics for data classification evaluations. Int. J. Data Min. Knowl. Manag. Process. 2015;5:1–11.

Tharwat A. Classification assessment methods. Appl. Comput. Inform. 2021;17:168–192. doi: 10.1016/j.aci.2018.08.003. DOI

Williamson E.J., Walker A.J., Bhaskaran K., Bacon S., Bates C., Morton C.E., Curtis H.J., Mehrkar A., Evans D., Inglesby P., et al. Factors associated with COVID-19-related death using OpenSAFELY. Nature. 2020;584:430–436. doi: 10.1038/s41586-020-2521-4. PubMed DOI PMC

Corticosteroid treatment prediction using chest X-ray and clinical data

The effectiveness of glucocorticoid treatment in post-COVID-19 pulmonary involvement