Background: Risk stratification of COVID-19 patients can support therapeutic decisions, planning and resource allocation in the hospital. In times of high incidence, a prognostic model based on data efficiently retrieved from one source can enable fast decision support. Methods: A model was developed to identify patients at risk of developing severe COVID-19 within one month based on their age, sex and imaging features extracted from the thoracic computed tomography (CT). The model was trained on publicly available data from the Study of Thoracic CT in COVID-19 (STOIC) challenge and validated on unseen data from the same study and an external, multicentric dataset. The model, trained on data acquired before any variant of concern dominated, was assessed separately on data collected at later stages of the pandemic when the delta and omicron variants were most prevalent. Results: A logistic regression based on handcrafted features was found to perform on par with a direct deep learning approach, and the former was selected for simplicity. Volumetric and intensity-based features of lesions and healthy lung parenchyma proved most predictive, in addition to patient age and sex. The model reached an area under the curve of 0.78 on the challenge test set and 0.74 on the external test set. The performance did not drop for the subset acquired at a later stage of the pandemic. Conclusions: A logistic regression utilizing features from thoracic CT and its metadata can provide rapid decision support by estimating short-term COVID-19 severity. Its stable performance underscores its potential for real-world clinical integration. By enabling rapid risk stratification using readily available imaging data, this approach can support early clinical decision-making, optimize resource allocation, and improve patient management, particularly during surges in COVID-19 cases. Furthermore, this study provides a foundation for future research on prognostic modelling in respiratory infections.
Dirks, I, Bossa Bossa, MN, Diaz Berenguer, A, Mukherjee, T, Sahli, H, Deligiannis, N, Verelst, E, Ilsen, B, Van Eyndhoven, S, Seyler, L, Witdouck, A, Darcis, G, Guiot, J, Giannakis, A & Vandemeulebroucke, J 2025, 'Development and multicentric external validation of a prognostic COVID-19 severity model based on thoracic CT', BMC Medical Informatics and Decision Making, vol. 25, no. 1, 156, pp. 1-15. https://doi.org/10.1186/s12911-025-02983-z
Dirks, I., Bossa Bossa, M. N., Diaz Berenguer, A., Mukherjee, T., Sahli, H., Deligiannis, N., Verelst, E., Ilsen, B., Van Eyndhoven, S., Seyler, L., Witdouck, A., Darcis, G., Guiot, J., Giannakis, A., & Vandemeulebroucke, J. (2025). Development and multicentric external validation of a prognostic COVID-19 severity model based on thoracic CT. BMC Medical Informatics and Decision Making, 25(1), 1-15. Article 156. https://doi.org/10.1186/s12911-025-02983-z
@article{481c9af4093d4d6aadc66f94b844b248,
title = "Development and multicentric external validation of a prognostic COVID-19 severity model based on thoracic CT",
abstract = "Background: Risk stratification of COVID-19 patients can support therapeutic decisions, planning and resource allocation in the hospital. In times of high incidence, a prognostic model based on data efficiently retrieved from one source can enable fast decision support. Methods: A model was developed to identify patients at risk of developing severe COVID-19 within one month based on their age, sex and imaging features extracted from the thoracic computed tomography (CT). The model was trained on publicly available data from the Study of Thoracic CT in COVID-19 (STOIC) challenge and validated on unseen data from the same study and an external, multicentric dataset. The model, trained on data acquired before any variant of concern dominated, was assessed separately on data collected at later stages of the pandemic when the delta and omicron variants were most prevalent. Results: A logistic regression based on handcrafted features was found to perform on par with a direct deep learning approach, and the former was selected for simplicity. Volumetric and intensity-based features of lesions and healthy lung parenchyma proved most predictive, in addition to patient age and sex. The model reached an area under the curve of 0.78 on the challenge test set and 0.74 on the external test set. The performance did not drop for the subset acquired at a later stage of the pandemic. Conclusions: A logistic regression utilizing features from thoracic CT and its metadata can provide rapid decision support by estimating short-term COVID-19 severity. Its stable performance underscores its potential for real-world clinical integration. By enabling rapid risk stratification using readily available imaging data, this approach can support early clinical decision-making, optimize resource allocation, and improve patient management, particularly during surges in COVID-19 cases. Furthermore, this study provides a foundation for future research on prognostic modelling in respiratory infections.",
author = "Ine Dirks and \{Bossa Bossa\}, \{Mat{\'i}as Nicol{\'a}s\} and \{Diaz Berenguer\}, Abel and Tanmoy Mukherjee and Hichem Sahli and Nikos Deligiannis and Emma Verelst and Bart Ilsen and \{Van Eyndhoven\}, Simon and Lucie Seyler and Arne Witdouck and Gilles Darcis and Julien Guiot and Athanasios Giannakis and Jef Vandemeulebroucke",
note = "Funding Information: The Authors acknowledge financial support by \textbackslash{}u201CNUM 2.0\textbackslash{}u201D (FKZ:01KX2121) and from the following European Union\textbackslash{}u2019s research and innovation programs. The DRAGON project has received funding from the Innovative Medicines Initiative 2 Joint Undertaking (JU) under grant agreement No. 101005122. The JU receives support from the European Union\textbackslash{}u2019s Horizon 2020 research and innovation program and EFPIA. The iCOVID project has received funding from the European Union\textbackslash{}u2019s Horizon 2020 research and innovation program under grant agreement No. 101016131. Publisher Copyright: {\textcopyright} The Author(s) 2025.",
year = "2025",
month = apr,
day = "1",
doi = "10.1186/s12911-025-02983-z",
language = "English",
volume = "25",
pages = "1--15",
journal = "BMC Medical Informatics and Decision Making",
issn = "1472-6947",
publisher = "Springer Verlag",
number = "1",
}