Integrating deep learning CT-scan model, biological and clinical variables to predict severity of COVID-19 patients
| Autor: | Paul Trichelair, Kathryn Schutte, Etienne Bendjebbar, Thomas Clozel, Nathalie Lassau, Sagar Verma, Gilles Wainrib, Simon Jégou, Remy Dubois, Frank Chemouni, Gabriel Garcia, Yingping Li, Annabelle Stoclin, Samer Soliman, Imad Bousaid, Paul Jehanno, Fabien Brulport, Hugo Gortais, Olivier Meyrignac, Jocelyn Dachary, Marie-Pauline Talabard, Emilie Chouzenoux, Ana Neacsu, Matthieu Terris, Fabrice Barlesi, Matthieu Devilder, Mikael Azoulay, Hugues Talbot, Kavya Gupta, Paul Herent, Olivier Dehaene, Franck Griscelli, Jean-Baptiste Schiratti, Michael G. B. Blum, Adrian Gonzalez, Jean-Christophe Pesquet, Nicolas Tetelboum, Corinne Balleyguier, Nicolas Loiseau, Marie-France Bellin, Samy Ammari, Elodie Pronier, Tasnim Dardouri, Emmanuel Planchet, Yannick Boursin, Meriem Sefta, Jean-Philippe Lamarque, Mansouria Merad |
|---|---|
| Přispěvatelé: | Unité BioMaps (BIOMAPS), Service Hospitalier Frédéric Joliot (SHFJ), Direction de Recherche Fondamentale (CEA) (DRF (CEA)), Commissariat à l'énergie atomique et aux énergies alternatives (CEA)-Commissariat à l'énergie atomique et aux énergies alternatives (CEA)-Université Paris-Saclay-Direction de Recherche Fondamentale (CEA) (DRF (CEA)), Commissariat à l'énergie atomique et aux énergies alternatives (CEA)-Commissariat à l'énergie atomique et aux énergies alternatives (CEA)-Université Paris-Saclay-Institut National de la Santé et de la Recherche Médicale (INSERM)-Centre National de la Recherche Scientifique (CNRS), Département d'imagerie médicale [Gustave Roussy], Institut Gustave Roussy (IGR), OPtimisation Imagerie et Santé (OPIS), Inria Saclay - Ile de France, Institut National de Recherche en Informatique et en Automatique (Inria)-Institut National de Recherche en Informatique et en Automatique (Inria)-Centre de vision numérique (CVN), Institut National de Recherche en Informatique et en Automatique (Inria)-CentraleSupélec-Université Paris-Saclay-CentraleSupélec-Université Paris-Saclay, Département de Radiologie [AP-HP Hôpital Bicêtre], AP-HP Hôpital Bicêtre (Le Kremlin-Bicêtre), Owkin, Inc. [New York, NY, États-Unis], Département interdisciplinaire d’organisation des parcours patients (DIOPP), Département de biologie et pathologie médicales [Gustave Roussy], Centre de vision numérique (CVN), Institut National de Recherche en Informatique et en Automatique (Inria)-CentraleSupélec-Université Paris-Saclay, Heriot-Watt University [Edinburgh] (HWU), Direction de la Transformation Numérique et des Systèmes d’Information, Owkin France, Département de médecine oncologique [Gustave Roussy], LaBoratoire d'Imagerie biOmédicale MultimodAle Paris-Saclay (BIOMAPS), Université Paris-Saclay-Direction de Recherche Fondamentale (CEA) (DRF (CEA)), Commissariat à l'énergie atomique et aux énergies alternatives (CEA)-Commissariat à l'énergie atomique et aux énergies alternatives (CEA)-Institut National de la Santé et de la Recherche Médicale (INSERM)-Centre National de la Recherche Scientifique (CNRS) |
| Jazyk: | angličtina |
| Rok vydání: | 2021 |
| Předmět: |
medicine.medical_specialty
Multivariate analysis Clinical variables Coronavirus disease 2019 (COVID-19) Science MEDLINE General Physics and Astronomy macromolecular substances Models Biological Severity of Illness Index Article General Biochemistry Genetics and Molecular Biology 030218 nuclear medicine & medical imaging 03 medical and health sciences Deep Learning 0302 clinical medicine Text mining Artificial Intelligence Intensive care Radiologists Machine learning Severity of illness Humans Medicine 030212 general & internal medicine Multidisciplinary business.industry Deep learning COVID-19 General Chemistry Prognosis 3. Good health Risk factors Viral infection Multivariate Analysis Emergency medicine Neural Networks Computer Artificial intelligence Tomography X-Ray Computed business [SPI.SIGNAL]Engineering Sciences [physics]/Signal and Image processing |
| Zdroj: | Nature Communications, Vol 12, Iss 1, Pp 1-11 (2021) Nature Communications Nature Communications, Nature Publishing Group, In press, 12 (634), ⟨10.1038/s41467-020-20657-4⟩ Nature Communications, In press, 12 (634), ⟨10.1038/s41467-020-20657-4⟩ Nature Communications, inPress, 12 (634), ⟨10.1038/s41467-020-20657-4⟩ |
| ISSN: | 2041-1723 |
| DOI: | 10.1038/s41467-020-20657-4⟩ |
| Popis: | The SARS-COV-2 pandemic has put pressure on intensive care units, so that identifying predictors of disease severity is a priority. We collect 58 clinical and biological variables, and chest CT scan data, from 1003 coronavirus-infected patients from two French hospitals. We train a deep learning model based on CT scans to predict severity. We then construct the multimodal AI-severity score that includes 5 clinical and biological variables (age, sex, oxygenation, urea, platelet) in addition to the deep learning model. We show that neural network analysis of CT-scans brings unique prognosis information, although it is correlated with other markers of severity (oxygenation, LDH, and CRP) explaining the measurable but limited 0.03 increase of AUC obtained when adding CT-scan information to clinical variables. Here, we show that when comparing AI-severity with 11 existing severity scores, we find significantly improved prognosis performance; AI-severity can therefore rapidly become a reference scoring approach. The SARS-COV-2 pandemic has put pressure on intensive care units, so that predicting severe deterioration early is a priority. Here, the authors develop a multimodal severity score including clinical and imaging features that has significantly improved prognostic performance in two validation datasets compared to previous scores. |
| Databáze: | OpenAIRE |
| Externí odkaz: |
|