Machine Learning-Based Prediction of COVID-19 Severity and Progression to Critical Illness Using CT Imaging and Clinical Data
- PMID: 33739635
- PMCID: PMC8236359
- DOI: 10.3348/kjr.2020.1104
Machine Learning-Based Prediction of COVID-19 Severity and Progression to Critical Illness Using CT Imaging and Clinical Data
Abstract
Objective: To develop a machine learning (ML) pipeline based on radiomics to predict Coronavirus Disease 2019 (COVID-19) severity and the future deterioration to critical illness using CT and clinical variables.
Materials and methods: Clinical data were collected from 981 patients from a multi-institutional international cohort with real-time polymerase chain reaction-confirmed COVID-19. Radiomics features were extracted from chest CT of the patients. The data of the cohort were randomly divided into training, validation, and test sets using a 7:1:2 ratio. A ML pipeline consisting of a model to predict severity and time-to-event model to predict progression to critical illness were trained on radiomics features and clinical variables. The receiver operating characteristic area under the curve (ROC-AUC), concordance index (C-index), and time-dependent ROC-AUC were calculated to determine model performance, which was compared with consensus CT severity scores obtained by visual interpretation by radiologists.
Results: Among 981 patients with confirmed COVID-19, 274 patients developed critical illness. Radiomics features and clinical variables resulted in the best performance for the prediction of disease severity with a highest test ROC-AUC of 0.76 compared with 0.70 (0.76 vs. 0.70, p = 0.023) for visual CT severity score and clinical variables. The progression prediction model achieved a test C-index of 0.868 when it was based on the combination of CT radiomics and clinical variables compared with 0.767 when based on CT radiomics features alone (p < 0.001), 0.847 when based on clinical variables alone (p = 0.110), and 0.860 when based on the combination of visual CT severity scores and clinical variables (p = 0.549). Furthermore, the model based on the combination of CT radiomics and clinical variables achieved time-dependent ROC-AUCs of 0.897, 0.933, and 0.927 for the prediction of progression risks at 3, 5 and 7 days, respectively.
Conclusion: CT radiomics features combined with clinical variables were predictive of COVID-19 severity and progression to critical illness with fairly high accuracy.
Keywords: COVID-19; CT; Machine learning; Radiomics; Severity.
Copyright © 2021 The Korean Society of Radiology.
Conflict of interest statement
The authors have no potential conflicts of interest to disclose.
Figures
![Fig. 1](https://www.ncbi.nlm.nih.gov/pmc/articles/instance/8236359/bin/kjr-22-1213-g001.gif)
![Fig. 2](https://www.ncbi.nlm.nih.gov/pmc/articles/instance/8236359/bin/kjr-22-1213-g002.gif)
![Fig. 3](https://www.ncbi.nlm.nih.gov/pmc/articles/instance/8236359/bin/kjr-22-1213-g003.gif)
Similar articles
-
CT radiomics facilitates more accurate diagnosis of COVID-19 pneumonia: compared with CO-RADS.J Transl Med. 2021 Jan 7;19(1):29. doi: 10.1186/s12967-020-02692-3. J Transl Med. 2021. PMID: 33413480 Free PMC article.
-
Computed Tomography Radiomics Can Predict Disease Severity and Outcome in Coronavirus Disease 2019 Pneumonia.J Comput Assist Tomogr. 2020 Sep/Oct;44(5):640-646. doi: 10.1097/RCT.0000000000001094. J Comput Assist Tomogr. 2020. PMID: 32842058
-
Screening of COVID-19 based on the extracted radiomics features from chest CT images.J Xray Sci Technol. 2021;29(2):229-243. doi: 10.3233/XST-200831. J Xray Sci Technol. 2021. PMID: 33612539
-
Benchmarking of Machine Learning classifiers on plasma proteomic for COVID-19 severity prediction through interpretable artificial intelligence.Artif Intell Med. 2023 Mar;137:102490. doi: 10.1016/j.artmed.2023.102490. Epub 2023 Jan 18. Artif Intell Med. 2023. PMID: 36868685 Free PMC article. Review.
-
The accuracy of machine learning approaches using non-image data for the prediction of COVID-19: A meta-analysis.Int J Med Inform. 2022 Aug;164:104791. doi: 10.1016/j.ijmedinf.2022.104791. Epub 2022 May 13. Int J Med Inform. 2022. PMID: 35594810 Free PMC article. Review.
Cited by
-
Innovative applications of artificial intelligence during the COVID-19 pandemic.Infect Med (Beijing). 2024 Feb 21;3(1):100095. doi: 10.1016/j.imj.2024.100095. eCollection 2024 Mar. Infect Med (Beijing). 2024. PMID: 38586543 Free PMC article. Review.
-
Reporting Quality of Research Studies on AI Applications in Medical Images According to the CLAIM Guidelines in a Radiology Journal With a Strong Prominence in Asia.Korean J Radiol. 2023 Dec;24(12):1179-1189. doi: 10.3348/kjr.2023.1027. Korean J Radiol. 2023. PMID: 38016678 Free PMC article. Review.
-
Prognostic models in COVID-19 infection that predict severity: a systematic review.Eur J Epidemiol. 2023 Apr;38(4):355-372. doi: 10.1007/s10654-023-00973-x. Epub 2023 Feb 25. Eur J Epidemiol. 2023. PMID: 36840867 Free PMC article. Review.
-
Radiomics analysis in medical imaging research.J Med Radiat Sci. 2023 Mar;70(1):3-7. doi: 10.1002/jmrs.662. Epub 2023 Feb 10. J Med Radiat Sci. 2023. PMID: 36762402 Free PMC article.
-
Prediction of potential severe coronavirus disease 2019 patients based on CT radiomics: A retrospective study.Med Phys. 2022 Sep;49(9):5886-5898. doi: 10.1002/mp.15841. Epub 2022 Jul 28. Med Phys. 2022. PMID: 35837868 Free PMC article. Clinical Trial.
References
Publication types
MeSH terms
Grants and funding
- MH120811/NH/NIH HHS/United States
- DK117297/NH/NIH HHS/United States
- R01 MH120811/MH/NIMH NIH HHS/United States
- National Institutes of Health/National Cancer Institute R03 grant
- Amazon Web Services Diagnostic Development Initiative
- R03 CA249554/CA/NCI NIH HHS/United States
- CA223358/NH/NIH HHS/United States
- R21 CA223358/CA/NCI NIH HHS/United States
- EB022573/NH/NIH HHS/United States
- R01 EB022573/EB/NIBIB NIH HHS/United States
- RSNA Research Scholar Grant
- Brown COVID-19 Research Seed Award
- R21 DK117297/DK/NIDDK NIH HHS/United States
- R03CA249554/National Institutes of Health/National Cancer Institute R03 grant
LinkOut - more resources
Full Text Sources
Other Literature Sources
Medical