Skip to Main content Skip to Navigation
Reports

AI-based multi-modal integration of clinical characteristics, lab tests and chest CTs improves COVID-19 outcome prediction of hospitalized patients

Abstract : With 15% of severe cases among hospitalized patients​, the SARS-COV-2 pandemic has put tremendous pressure on Intensive Care Units, and made the identification of early predictors of future severity a public health priority. We collected​ ​ clinical and biological data, as well as CT scan images and radiology reports from 1,003 coronavirus-infected patients from two French hospitals. Radiologists' manual CT annotations were also available. We first identified 11 clinical variables and 3 types of radiologist-reported features significantly associated with prognosis. Next, focusing on the CT images, we trained deep learning models to automatically segment the scans and reproduce radiologists' annotations. We also built CT image-based deep learning models that predicted future severity better than models based on the radiologists' scan reports. Finally, we showed that including CT scan features alongside the clinical and biological data yielded more accurate predictions than using clinical and biological data alone. These findings show that CT scans provide insightful early predictors of future severity.
Complete list of metadatas

Cited literature [40 references]  Display  Hide  Download

https://hal.archives-ouvertes.fr/hal-02586111
Contributor : Emilie Chouzenoux <>
Submitted on : Monday, May 18, 2020 - 11:48:24 AM
Last modification on : Wednesday, May 20, 2020 - 1:02:37 AM

File

ScancovIA_withsuppmat (1).pdf
Files produced by the author(s)

Identifiers

  • HAL Id : hal-02586111, version 2

Citation

Nathalie Lassau, Samy Ammari, Emilie Chouzenoux, Hugo Gortais, Paul Herent, et al.. AI-based multi-modal integration of clinical characteristics, lab tests and chest CTs improves COVID-19 outcome prediction of hospitalized patients. [Research Report] Inria Saclay Ile de France. 2020. ⟨hal-02586111v2⟩

Share

Metrics

Record views

783

Files downloads

207