TY - JOUR
T1 - Tracking and predicting COVID-19 radiological trajectory on chest X-rays using deep learning
AU - Gourdeau, Daniel
AU - Potvin, Olivier
AU - Archambault, Patrick
AU - Chartrand-Lefebvre, Carl
AU - Dieumegarde, Louis
AU - Forghani, Reza
AU - Gagné, Christian
AU - Hains, Alexandre
AU - Hornstein, David
AU - Le, Huy
AU - Lemieux, Simon
AU - Lévesque, Marie Hélène
AU - Martin, Diego
AU - Rosenbloom, Lorne
AU - Tang, An
AU - Vecchio, Fabrizio
AU - Yang, Issac
AU - Duchesne, Nathalie
AU - Duchesne, Simon
N1 - Funding Information:
This study has been financed by a COVID-19 Pilot Project grant from the Quebec Bio-Imaging Network as well as concurrent funding from a Discovery Award to the senior investigator (S.D.) from the National Science and Engineering Research Council of Canada. The study was also funded by a National Science and Engineering Research Council of Canada fellowship to the first author (Grant Number: 534769). These funding sources had no role in the design of the study.
Funding Information:
We would like to sincerely thank all patients, members of the Italian Society for Medical and Interventional Radiology and MILA groups for aggregating and/or releasing data. We would further like to thank K. Duchesne (CERVO Brain Center), as well as F. Alù, F. Miraglia, and A. Orticoni from the Brain Connectivity Laboratory of IRCCS San Raffaele Pisana, Rome, Italy for help in data collection and translation. We would also like to thank Dr. Henry Jason Diem for his help in data labeling.
Publisher Copyright:
© 2022, The Author(s).
PY - 2022/12
Y1 - 2022/12
N2 - Radiological findings on chest X-ray (CXR) have shown to be essential for the proper management of COVID-19 patients as the maximum severity over the course of the disease is closely linked to the outcome. As such, evaluation of future severity from current CXR would be highly desirable. We trained a repurposed deep learning algorithm on the CheXnet open dataset (224,316 chest X-ray images of 65,240 unique patients) to extract features that mapped to radiological labels. We collected CXRs of COVID-19-positive patients from an open-source dataset (COVID-19 image data collection) and from a multi-institutional local ICU dataset. The data was grouped into pairs of sequential CXRs and were categorized into three categories: ‘Worse’, ‘Stable’, or ‘Improved’ on the basis of radiological evolution ascertained from images and reports. Classical machine-learning algorithms were trained on the deep learning extracted features to perform immediate severity evaluation and prediction of future radiological trajectory. Receiver operating characteristic analyses and Mann-Whitney tests were performed. Deep learning predictions between “Worse” and “Improved” outcome categories and for severity stratification were significantly different for three radiological signs and one diagnostic (‘Consolidation’, ‘Lung Lesion’, ‘Pleural effusion’ and ‘Pneumonia’; all P < 0.05). Features from the first CXR of each pair could correctly predict the outcome category between ‘Worse’ and ‘Improved’ cases with a 0.81 (0.74–0.83 95% CI) AUC in the open-access dataset and with a 0.66 (0.67–0.64 95% CI) AUC in the ICU dataset. Features extracted from the CXR could predict disease severity with a 52.3% accuracy in a 4-way classification. Severity evaluation trained on the COVID-19 image data collection had good out-of-distribution generalization when testing on the local dataset, with 81.6% of intubated ICU patients being classified as critically ill, and the predicted severity was correlated with the clinical outcome with a 0.639 AUC. CXR deep learning features show promise for classifying disease severity and trajectory. Once validated in studies incorporating clinical data and with larger sample sizes, this information may be considered to inform triage decisions.
AB - Radiological findings on chest X-ray (CXR) have shown to be essential for the proper management of COVID-19 patients as the maximum severity over the course of the disease is closely linked to the outcome. As such, evaluation of future severity from current CXR would be highly desirable. We trained a repurposed deep learning algorithm on the CheXnet open dataset (224,316 chest X-ray images of 65,240 unique patients) to extract features that mapped to radiological labels. We collected CXRs of COVID-19-positive patients from an open-source dataset (COVID-19 image data collection) and from a multi-institutional local ICU dataset. The data was grouped into pairs of sequential CXRs and were categorized into three categories: ‘Worse’, ‘Stable’, or ‘Improved’ on the basis of radiological evolution ascertained from images and reports. Classical machine-learning algorithms were trained on the deep learning extracted features to perform immediate severity evaluation and prediction of future radiological trajectory. Receiver operating characteristic analyses and Mann-Whitney tests were performed. Deep learning predictions between “Worse” and “Improved” outcome categories and for severity stratification were significantly different for three radiological signs and one diagnostic (‘Consolidation’, ‘Lung Lesion’, ‘Pleural effusion’ and ‘Pneumonia’; all P < 0.05). Features from the first CXR of each pair could correctly predict the outcome category between ‘Worse’ and ‘Improved’ cases with a 0.81 (0.74–0.83 95% CI) AUC in the open-access dataset and with a 0.66 (0.67–0.64 95% CI) AUC in the ICU dataset. Features extracted from the CXR could predict disease severity with a 52.3% accuracy in a 4-way classification. Severity evaluation trained on the COVID-19 image data collection had good out-of-distribution generalization when testing on the local dataset, with 81.6% of intubated ICU patients being classified as critically ill, and the predicted severity was correlated with the clinical outcome with a 0.639 AUC. CXR deep learning features show promise for classifying disease severity and trajectory. Once validated in studies incorporating clinical data and with larger sample sizes, this information may be considered to inform triage decisions.
UR - http://www.scopus.com/inward/record.url?scp=85127498566&partnerID=8YFLogxK
UR - http://www.scopus.com/inward/citedby.url?scp=85127498566&partnerID=8YFLogxK
U2 - 10.1038/s41598-022-09356-w
DO - 10.1038/s41598-022-09356-w
M3 - Article
C2 - 35379856
AN - SCOPUS:85127498566
SN - 2045-2322
VL - 12
JO - Scientific Reports
JF - Scientific Reports
IS - 1
M1 - 5616
ER -