[en] [en] 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.
Disciplines :
Cardiovascular & respiratory systems
Author, co-author :
Dirks, Ine; Department of Electronics and Informatics (ETRO), Vrije Universiteit Brussel (VUB), Pleinlaan, Brussels, 1050, Belgium. ine.dirks@vub.be ; imec, Kapeldreef, Leuven, 3001, Belgium. ine.dirks@vub.be
Bossa, Matías Nicolás; Department of Electronics and Informatics (ETRO), Vrije Universiteit Brussel (VUB), Pleinlaan, Brussels, 1050, Belgium
Berenguer, Abel Díaz; Department of Electronics and Informatics (ETRO), Vrije Universiteit Brussel (VUB), Pleinlaan, Brussels, 1050, Belgium
Mukherjee, Tanmoy; Department of Electronics and Informatics (ETRO), Vrije Universiteit Brussel (VUB), Pleinlaan, Brussels, 1050, Belgium
Sahli, Hichem; Department of Electronics and Informatics (ETRO), Vrije Universiteit Brussel (VUB), Pleinlaan, Brussels, 1050, Belgium ; imec, Kapeldreef, Leuven, 3001, Belgium
Deligiannis, Nikos; Department of Electronics and Informatics (ETRO), Vrije Universiteit Brussel (VUB), Pleinlaan, Brussels, 1050, Belgium ; imec, Kapeldreef, Leuven, 3001, Belgium
Verelst, Emma; Department of Radiology, Universitair Ziekenhuis Brussel, Vrije Universiteit Brussel (VUB), Laarbeeklaan, Jette, 1090, Belgium
Ilsen, Bart; Department of Radiology, Universitair Ziekenhuis Brussel, Vrije Universiteit Brussel (VUB), Laarbeeklaan, Jette, 1090, Belgium
Eyndhoven, Simon Van; Icometrix, Kolonel Begaultlaan, Leuven, 3012, Belgium
Seyler, Lucie; Department of Internal Medicine and Infectiology, Vitality Research Group (MIPI), Universitair Ziekenhuis Brussel, Vrije Universiteit Brussel (VUB), Laarbeeklaan, Jette, 1090, Belgium
Witdouck, Arne; Department of Internal Medicine and Infectiology, Vitality Research Group (MIPI), Universitair Ziekenhuis Brussel, Vrije Universiteit Brussel (VUB), Laarbeeklaan, Jette, 1090, Belgium
Darcis, Gilles ; Université de Liège - ULiège > Département des sciences cliniques > Immunopathologie - Maladies infectieuses et médecine interne générale
Guiot, Julien ; Université de Liège - ULiège > Département des sciences cliniques > Pneumologie - Allergologie
Giannakis, Athanasios; Department of Diagnostic and Interventional Radiology, University Hospital of Heidelberg, Im Neuenheimer Feld, 69120, Heidelberg, Germany ; Translational Lung Research Center (TLRC), German Center for Lung Research (DZL), University of Heidelberg, Im Neuenheimer Feld, 69120, Heidelberg, Germany ; Second Department of Radiology, University General Hospital Attikon, National and Kapodistrian University of Athens, Panepistimiou, Athens, 157 72, Greece
Vandemeulebroucke, Jef; Department of Electronics and Informatics (ETRO), Vrije Universiteit Brussel (VUB), Pleinlaan, Brussels, 1050, Belgium ; imec, Kapeldreef, Leuven, 3001, Belgium ; Department of Radiology, Universitair Ziekenhuis Brussel, Vrije Universiteit Brussel (VUB), Laarbeeklaan, Jette, 1090, Belgium
The Authors acknowledge financial support by \u201CNUM 2.0\u201D (FKZ:01KX2121) and from the following European Union\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\u2019s Horizon 2020 research and innovation program and EFPIA. The iCOVID project has received funding from the European Union\u2019s Horizon 2020 research and innovation program under grant agreement No. 101016131.
World Health Organization. WHO coronavirus dashboard. https://covid19.who.int/. 14 Aug 2023.
J.J.R. Hermans J. Groen E. Zwets B.M. Boxma-De Klerk J.M. Van Werkhoven D.S.Y. Ong et al. Chest CT for triage during COVID-19 on the emergency department: myth or truth? Emerg Radiol. 27 6 641 51 10.1007/s10140-020-01821-1 32691211 7369539
J. Desmet C. Biebaû W. De Wever L. Cockmartin V. Viktor J. Coolen et al. Performance of low-dose chest CT as a triage tool for suspected COVID-19 patients J Belg Soc Radiol. 105 1 1 8 10.5334/jbsr.2319
Esposito G, Ernst B, Henket M, Winandy M, Chatterjee A, Eyndhoven SV, et al. AI-based chest CT analysis for rapid COVID-19 diagnosis and prognosis: a practical tool to flag high-risk patients and lower healthcare costs. Diagnostics. 2022;12(7). https://doi.org/10.3390/diagnostics12071608.
Esposito G, Guiot J, Ernst B, Louis R, Meunier P, Kolh P. (Early) Economic Evaluation of the AI-based software ‘icolung’ for the detection and prognosis of COVID cases from CT scans. Eur Respir J. 2022;60(suppl 66).
Guiot J, Ernst B, Henket M, Louis R, Meunier P, Smeets D, et al. COVID-19 diagnosis and disease severity prediction assessment through an innovative AI-based model. Eur Respir J. 2022;60(suppl 66).
W. Cai T. Liu X. Xue G. Luo X. Wang Y. Shen et al. CT quantification and machine-learning models for assessment of disease severity and prognosis of COVID-19 patients Acad Radiol. 27 12 1665 78 10.1016/j.acra.2020.09.004 33046370 7505599
L. Meng D. Dong L. Li M. Niu Y. Bai M. Wang et al. A deep learning prognosis model help alert for COVID-19 patients at high-risk of death: a multi-center study IEEE J Biomed Health Inform. 24 12 3576 84 10.1109/JBHI.2020.3034296 33108303
W. Ning S. Lei J. Yang Y. Cao P. Jiang Q. Yang et al. Open resource of clinical data from patients with pneumonia for the prediction of COVID-19 outcomes via deep learning Nat Biomed Eng. 4 12 1197 207 1:CAS:528:DC%2BB3cXisVertrvO 10.1038/s41551-020-00633-5 33208927 7723858
L. Fu Y. Li A. Cheng P.P. Pang Z. Shu A novel machine learning-derived radiomic signature of the whole lung differentiates stable from Progressive COVID-19 infection: a retrospective Cohort study J Thoracic Imaging. 35 6 361 68 10.1097/RTI.0000000000000544 32555006
C. Li D. Dong L. Li W. Gong X. Li Y. Bai et al. Classification of severe and critical covid-19 using deep learning and radiomics IEEE J Biomed Health Inform. 24 3585 94 33166256
H. Yue Q. Yu C. Liu Y. Huang Z. Jiang C. Shao et al. Machine learning-based CT radiomics method for predicting hospital stay in patients with pneumonia associated with SARS-CoV-2 infection: a multicenter study Ann Transl Med. 8 14 859 859 1:CAS:528:DC%2BB3cXitF2ns7zL 10.21037/atm-20-3026 32793703 7396749
Wu G, Yang P, Xie Y, Woodruff HC, Rao X, Guiot J, et al. Development of a clinical decision support system for severity risk prediction and triage of COVID-19 patients at hospital admission: an international multicentre study. Eur Respir J. 2020;56(2). https://doi.org/10.1183/13993003.01104-2020.
C. Fang S. Bai Q. Chen Y. Zhou L. Xia L. Qin et al. Deep learning for predicting COVID-19 malignant progression Med Image Anal. 72 102096 34051438 8112895
R. Wang Z. Jiao L. Yang J.W. Choi Z. Xiong K. Halsey et al. Artificial intelligence for prediction of COVID-19 progression using CT imaging and clinical data Eur Radiol. 32 1 205 12 1:CAS:528:DC%2BB3MXhsFGhtrnJ 10.1007/s00330-021-08049-8 34223954
D. Wang C. Huang S. Bao T. Fan Z. Sun Y. Wang et al. Study on the prognosis predictive model of COVID-19 patients based on CT radiomics Sci Rep. 11 1 1 9 1:CAS:528:DC%2BB3MXht12jsLnE 10.1038/s41598-021-90991-0
Revel MP, Boussouar S, de Margerie-mellon C, Saab I, Lapotre T, Mompoint D, et al. Study of thoracic CT in COVID-19: the STOIC project. Radiology. 2021;301(1).
Grand Challenge.: STOIC2021. https://stoic2021.grand-challenge.org/stoic2021/. 14 Aug 2023.
N. Lassau S. Ammari E. Chouzenoux H. Gortais P. Herent M. Devilder et al. Integrating deep learning CT-scan model, biological and clinical variables to predict severity of COVID-19 patients Nat Commun. 12 1 1 11 1:CAS:528:DC%2BB3MXis1Kgtr8%3D 10.1038/s41467-020-20657-4
I. Shiri Y. Salimi M. Pakbin G. Hajianfar A.H. Avval A. Sanaat et al. COVID-19 prognostic modeling using CT radiomic features and machine learning algorithms: analysis of a multi-institutional dataset of 14,339 patients: COVID-19 prognostic modeling using CT radiomics and machine learning Comput Biol Med. 145 February 105467 1:CAS:528:DC%2BB38XovFShtLk%3D 10.1016/j.compbiomed.2022.105467 35378436 8964015
Kienzle D, Lorenz J, Schön R, Ludwig K, Lienhart R. COVID detection and severity prediction with 3D-ConvNeXt and custom pretrainings. In: Computer Vision – ECCV 2022 Workshops; 2022.
S. Shakouri M.A. Bakhshali P. Layegh B. Kiani F. Masoumi S. Ataei Nakhaei et al. COVID19-CT-dataset: an open-access chest CT image repository of 1000+ patients with confirmed COVID-19 diagnosis BMC Res Notes. 14 1 178 1:CAS:528:DC%2BB3MXhtFahsb3J 10.1186/s13104-021-05592-x 33980279 8114670
Duan L, Zhang L, Lu G, Guo L, Duan S, Zhou C. A CT-based radiomics model for prediction of prognosis in patients with novel coronavirus disease (COVID-19) pneumonia: a preliminary study. MDPI Diagn. 2023;13(8).
G.S. Collins J.B. Reitsma D.G. Altman K.G.M. Moons Transparent reporting of a multivariable prediction model for individual prognosis or diagnosis (TRIPOD): the TRIPOD statement Ann Intern Med. 162 1 55 63 10.7326/M14-0697 25560714
Boulogne LH, Lorenz J, Kienzle D, Schon R, Ludwig K, Lienhart R, et al. The STOIC2021 COVID-19 AI challenge: applying reusable training methodologies to private data. ArXiv: 2306.10484.
G. Darcis A. Bouquegneau N. Maes M. Thys M. Henket F. Labye et al. Long-term clinical follow-up of patients suffering from moderate-to-severe COVID-19 infection: a monocentric prospective observational cohort study Int J Infect Dis. 109 209 16 1:CAS:528:DC%2BB3MXhs1OhtrnK 34273510 8278829
L. Seyler E. Van Nedervelde D. De Cock C. Mann K. Pien S.D. Allard et al. Surfing the waves: differences in hospitalised COVID-19 patients across 4 variant waves in a Belgian University Hospital Viruses. 15 3 618 10.3390/v15030618 36992327 10057609
JoHof. Automated lung segmentation in CT under presence of severe pathologies. https://github.com/JoHof/lungmask. 14 Aug 2023.
F. Isensee P.F. Jaeger S.A.A. Kohl J. Petersen K.H. Maier-Hein nnU-Net: a self-configuring method for deep learning-based biomedical image segmentation Nat Methods. 18 203 11 1:CAS:528:DC%2BB3cXisFSltL%2FN 10.1038/s41592-020-01008-z 33288961
Project MONAI. Monai. https://monai.io. 24 May 2023.
Grand Challenge. COVID-19 lung CT lesion segmentation challenge. https://covid-segmentation.grand-challenge.org/
icometrix. icovid. https://icovid.ai/. 14 Aug 2023.
Wang G, Liu X, Li C, Xu Z, Ruan J, Zhu H, Meng T, Li K, Huang N, Zhang S. COPLE-Net: COVID-19 pneumonia lesion segmentation network. https://github.com/HiLab-git/COPLE-Net. 14 Aug 2023
Jun M, Cheng G, Yixin W, Xingle A, Jiantao G, Ziqi Y, et al. COVID-19 CT lung and infection segmentation dataset. Zenodo. 2020. https://doi.org/10.5281/zenodo.3757476.
Tarvainen A, Valpola H. Mean teachers are better role models: weight-averaged consistency targets improve semi-supervised deep learning results. In: 31st Conference on Neural Information Processing Systems. 2017. p. 1195–204.
Liu Z, Mao H, Wu CY, Feichtenhofer C, Darrell T, Xie S. A ConvNet for the 2020s. ArXiv: 2201.03545.
H.J. Chen L. Mao Y. Chen L. Yuan F. Wang X. Li et al. Machine learning-based CT radiomics model distinguishes COVID-19 from non-COVID-19 pneumonia BMC Infect Dis. 21 1 1 13 1:CAS:528:DC%2BB3MXhvFyrsb3L 10.1186/s12879-021-06614-6
Y. Huang Z. Zhang S. Liu X. Li Y. Yang J. Ma et al. CT-based radiomics combined with signs: a valuable tool to help radiologist discriminate COVID-19 and influenza pneumonia BMC Med Imaging. 21 1 1 12 10.1186/s12880-021-00564-w
E. DeLong D. DeLong D. Clarke-Pearson Comparing the areas under two or more correlated receiver operating characteristic curves: a nonparametric approach Biometrics. 44 837 45 1:STN:280:DyaL1M%2Fns12ksQ%3D%3D 3203132
X. Sun W. Xu Fast implementation of DeLong’s algorithm for comparing the areas under correlated receiver operating characteristic curves IEEE Signal Process Lett. 21 11 1389 93 10.1109/LSP.2014.2337313
Maastricht University and Comunicare. MyPatientCheck. https://mypatientcheck.web.app/home. 14 Aug 2023.
R. Shwartz-Ziv A. Armon Tabular data: deep learning is not all you need Inf Fusion. 81 June 2021 84 90 10.1016/j.inffus.2021.11.011
L.H. Boulogne J. Lorenz D. Kienzle R. Schön K. Ludwig R. Lienhart et al. The STOIC2021 COVID-19 AI challenge: applying reusable training methodologies to private data Med Image Anal. 97 103230 38875741
Ke G, Meng Q, Finley T, Wang T, Chen W, Ma W, et al. LightGBM: a highly efficient gradient boosting decision tree. In: Proceedings of the 31st International Conference on Neural Information Processing Systems. NIPS’17. Red Hook, NY, USA: Curran Associates Inc.; 2017. p. 3149–57.
Chen T, Guestrin C. XGBoost: a Scalable Tree Boosting System. In: Proceedings of the 22nd ACM SIGKDD International Conference on Knowledge Discovery and Data Mining. KDD’16. New York, NY, USA: Association for Computing Machinery; 2016. p. 785–94. https://doi.org/10.1145/2939672.2939785.
Borisov V, Leemann T, Seßler K, Haug J, Pawelczyk M, Kasneci G. Deep neural networks and tabular data: a survey. In: IEEE Transactions on Neural Networks and Learning Systems. 2022. p. 1–21. https://doi.org/10.1109/TNNLS.2022.3229161.
T. Iba J.M. Connors J.H. Levy The coagulopathy, endotheliopathy, and vasculitis of COVID-19 Inflammation Res. 69 12 1181 89 1:CAS:528:DC%2BB3cXhvVOrtrfM 10.1007/s00011-020-01401-6
K. Wong M.U. Farooq Alam Shah M. Khurshid I. Ullah M.J. Tahir Z. Yousaf COVID-19 associated vasculitis: a systematic review of case reports and case series Ann Med Surg. 74 103249 10.1016/j.amsu.2022.103249
Delli Pizzi A, Chiarelli AM, Chiacchiaretta P, Valdesi C, Croce P, Mastrodicasa D, et al. Radiomics-based machine learning differentiates “ground-glass” opacities due to COVID-19 from acute non-COVID-19 lung disease. Sci Rep. 2021;11(1):17237.https://doi.org/10.1038/s41598-021-96755-0.
I. Shiri S. Mostafaei A. Haddadi Avval Y. Salimi A. Sanaat A. Akhavanallaf et al. High-dimensional multinomial multiclass severity scoring of COVID-19 pneumonia using CT radiomics features and machine learning algorithms Sci Rep. 12 1 14817 1:CAS:528:DC%2BB38XitlWmsrrN 10.1038/s41598-022-18994-z 36050434 9437017
Kim AY, Gandhi RT. Wolters Kluwer UpToDate. COVID-19: management in hospitalized adults. https://www.uptodate.com/contents/covid-19-management-in-hospitalized-adults?sectionName=COVID-19-SPECIFICTHERAPYtopicRef=127454anchor=H3855514466source=see_link#. 14 Jul 2023.
National Institutes of Health. COVID-19 treatment guidelines panel. Coronavirus disease 2019 (COVID-19) treatment guidelines. https://files.covid19treatmentguidelines.nih.gov/guidelines/covid19treatmentguidelines.pdf. 14 Jul 2023.
Cascella M, Rajnik M, Aleem A, Dulebohn SC, Napoli RD. Features, evaluation, and treatment of coronavirus (COVID-19). https://www.statpearls.com/ArticleLibrary/viewarticle/52171. 14 Jul 2023.
