Integrating deep learning CT-scan model, biological and clinical variables to predict severity of COVID-19 patients

Nathalie Lassau; Samy Ammari; Emilie Chouzenoux; Hugo Gortais; Paul Herent; Matthieu Devilder; Samer Soliman; Olivier Meyrignac; Marie Pauline Talabard; Jean Philippe Lamarque; Remy Dubois; Nicolas Loiseau; Paul Trichelair; Etienne Bendjebbar; Gabriel Garcia; Corinne Balleyguier; Mansouria Merad; Annabelle Stoclin; Simon Jegou; Franck Griscelli; Nicolas Tetelboum; Yingping Li; Sagar Verma; Matthieu Terris; Tasnim Dardouri; Kavya Gupta; Ana Neacsu; Frank Chemouni; Meriem Sefta; Paul Jehanno; Imad Bousaid; Yannick Boursin; Emmanuel Planchet; Mikael Azoulay; Jocelyn Dachary; Fabien Brulport; Adrian Gonzalez; Olivier Dehaene; Jean Baptiste Schiratti; Kathryn Schutte; Jean Christophe Pesquet; Hugues Talbot; Elodie Pronier; Gilles Wainrib; Thomas Clozel; Fabrice Barlesi; Marie France Bellin; Michael G.B. Blum

doi:10.1038/s41467-020-20657-4

Integrating deep learning CT-scan model, biological and clinical variables to predict severity of COVID-19 patients

Nathalie Lassau, Samy Ammari, Emilie Chouzenoux, Hugo Gortais, Paul Herent, Matthieu Devilder, Samer Soliman, Olivier Meyrignac, Marie Pauline Talabard, Jean Philippe Lamarque, Remy Dubois, Nicolas Loiseau, Paul Trichelair, Etienne Bendjebbar, Gabriel Garcia, Corinne Balleyguier, Mansouria Merad, Annabelle Stoclin, Simon Jegou, Franck GriscelliNicolas Tetelboum, Yingping Li, Sagar Verma, Matthieu Terris, Tasnim Dardouri, Kavya Gupta, Ana Neacsu, Frank Chemouni, Meriem Sefta, Paul Jehanno, Imad Bousaid, Yannick Boursin, Emmanuel Planchet, Mikael Azoulay, Jocelyn Dachary, Fabien Brulport, Adrian Gonzalez, Olivier Dehaene, Jean Baptiste Schiratti, Kathryn Schutte, Jean Christophe Pesquet, Hugues Talbot, Elodie Pronier, Gilles Wainrib, Thomas Clozel, Fabrice Barlesi, Marie France Bellin, Michael G.B. Blum

Résultats de recherche: Contribution à un journal › Article › Revue par des pairs

124 Citations (Scopus)

Résumé

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.

langue originale	Anglais
Numéro d'article	634
journal	Nature Communications
Volume	12
Numéro de publication	1
Les DOIs	https://doi.org/10.1038/s41467-020-20657-4
état	Publié - 1 déc. 2021

Accès au document

10.1038/s41467-020-20657-4

Autres fichiers et liens

Lien vers la publication dans Scopus

Contient cette citation

Lassau, N., Ammari, S., Chouzenoux, E., Gortais, H., Herent, P., Devilder, M., Soliman, S., Meyrignac, O., Talabard, M. P., Lamarque, J. P., Dubois, R., Loiseau, N., Trichelair, P., Bendjebbar, E., Garcia, G., Balleyguier, C., Merad, M., Stoclin, A., Jegou, S., ... Blum, M. G. B. (2021). Integrating deep learning CT-scan model, biological and clinical variables to predict severity of COVID-19 patients. Nature Communications, 12(1), Article 634. https://doi.org/10.1038/s41467-020-20657-4

@article{e304a0a575d242e39987510188737eab,

title = "Integrating deep learning CT-scan model, biological and clinical variables to predict severity of COVID-19 patients",

abstract = "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.",

author = "Nathalie Lassau and Samy Ammari and Emilie Chouzenoux and Hugo Gortais and Paul Herent and Matthieu Devilder and Samer Soliman and Olivier Meyrignac and Talabard, {Marie Pauline} and Lamarque, {Jean Philippe} and Remy Dubois and Nicolas Loiseau and Paul Trichelair and Etienne Bendjebbar and Gabriel Garcia and Corinne Balleyguier and Mansouria Merad and Annabelle Stoclin and Simon Jegou and Franck Griscelli and Nicolas Tetelboum and Yingping Li and Sagar Verma and Matthieu Terris and Tasnim Dardouri and Kavya Gupta and Ana Neacsu and Frank Chemouni and Meriem Sefta and Paul Jehanno and Imad Bousaid and Yannick Boursin and Emmanuel Planchet and Mikael Azoulay and Jocelyn Dachary and Fabien Brulport and Adrian Gonzalez and Olivier Dehaene and Schiratti, {Jean Baptiste} and Kathryn Schutte and Pesquet, {Jean Christophe} and Hugues Talbot and Elodie Pronier and Gilles Wainrib and Thomas Clozel and Fabrice Barlesi and Bellin, {Marie France} and Blum, {Michael G.B.}",

note = "Publisher Copyright: {\textcopyright} 2021, The Author(s).",

year = "2021",

month = dec,

day = "1",

doi = "10.1038/s41467-020-20657-4",

language = "English",

volume = "12",

journal = "Nature Communications",

issn = "2041-1723",

number = "1",

}

Lassau, N, Ammari, S, Chouzenoux, E, Gortais, H, Herent, P, Devilder, M, Soliman, S, Meyrignac, O, Talabard, MP, Lamarque, JP, Dubois, R, Loiseau, N, Trichelair, P, Bendjebbar, E, Garcia, G, Balleyguier, C, Merad, M, Stoclin, A, Jegou, S, Griscelli, F, Tetelboum, N, Li, Y, Verma, S, Terris, M, Dardouri, T, Gupta, K, Neacsu, A, Chemouni, F, Sefta, M, Jehanno, P, Bousaid, I, Boursin, Y, Planchet, E, Azoulay, M, Dachary, J, Brulport, F, Gonzalez, A, Dehaene, O, Schiratti, JB, Schutte, K, Pesquet, JC, Talbot, H, Pronier, E, Wainrib, G, Clozel, T, Barlesi, F, Bellin, MF & Blum, MGB 2021, 'Integrating deep learning CT-scan model, biological and clinical variables to predict severity of COVID-19 patients', Nature Communications, VOL. 12, Numéro 1, 634. https://doi.org/10.1038/s41467-020-20657-4

TY - JOUR

T1 - Integrating deep learning CT-scan model, biological and clinical variables to predict severity of COVID-19 patients

AU - Lassau, Nathalie

AU - Ammari, Samy

AU - Chouzenoux, Emilie

AU - Gortais, Hugo

AU - Herent, Paul

AU - Devilder, Matthieu

AU - Soliman, Samer

AU - Meyrignac, Olivier

AU - Talabard, Marie Pauline

AU - Lamarque, Jean Philippe

AU - Dubois, Remy

AU - Loiseau, Nicolas

AU - Trichelair, Paul

AU - Bendjebbar, Etienne

AU - Garcia, Gabriel

AU - Balleyguier, Corinne

AU - Merad, Mansouria

AU - Stoclin, Annabelle

AU - Jegou, Simon

AU - Griscelli, Franck

AU - Tetelboum, Nicolas

AU - Li, Yingping

AU - Verma, Sagar

AU - Terris, Matthieu

AU - Dardouri, Tasnim

AU - Gupta, Kavya

AU - Neacsu, Ana

AU - Chemouni, Frank

AU - Sefta, Meriem

AU - Jehanno, Paul

AU - Bousaid, Imad

AU - Boursin, Yannick

AU - Planchet, Emmanuel

AU - Azoulay, Mikael

AU - Dachary, Jocelyn

AU - Brulport, Fabien

AU - Gonzalez, Adrian

AU - Dehaene, Olivier

AU - Schiratti, Jean Baptiste

AU - Schutte, Kathryn

AU - Pesquet, Jean Christophe

AU - Talbot, Hugues

AU - Pronier, Elodie

AU - Wainrib, Gilles

AU - Clozel, Thomas

AU - Barlesi, Fabrice

AU - Bellin, Marie France

AU - Blum, Michael G.B.

PY - 2021/12/1

Y1 - 2021/12/1

N2 - 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.

AB - 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.

UR - http://www.scopus.com/inward/record.url?scp=85099926480&partnerID=8YFLogxK

U2 - 10.1038/s41467-020-20657-4

DO - 10.1038/s41467-020-20657-4

M3 - Article

C2 - 33504775

AN - SCOPUS:85099926480

SN - 2041-1723

VL - 12

JO - Nature Communications

JF - Nature Communications

IS - 1

M1 - 634

ER -