TRACKING AND PREDICTING COVID-19 RADIOLOGICAL TRAJECTORY USING DEEP LEARNING ON CHEST X-RAYS: INITIAL ACCURACY TESTING

  1. S. Duchesne
  2. D. Gourdeau
  3. P. Archambault
  4. C. Chartrand-Lefebvre
  5. L. Dieumegarde
  6. R. Forghani
  7. C. Gagné
  8. A. Hains
  9. D. Hornstein
  10. H. Le
  11. S. Lemieux
  12. M.H. Lévesque
  13. D. Martin
  14. L. Rosenbloom
  15. A. Tang
  16. F. Vecchio
  17. O. Potvin
  18. N. Duchesne
1 evaluations Published on
Read the full article Related papers
This article on Sciety

Abstract

Background

Decision scores and ethically mindful algorithms are being established to adjudicate mechanical ventilation in the context of potential resources shortage due to the current onslaught of COVID-19 cases. There is a need for a reproducible and objective method to provide quantitative information for those scores.

Purpose

Towards this goal, we present a retrospective study testing the ability of a deep learning algorithm at extracting features from chest x-rays (CXR) to track and predict radiological evolution.

Materials and Methods

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 two open-source datasets (last accessed on April 9, 2020)(Italian Society for Medical and Interventional Radiology and MILA). Data collected form 60 pairs of sequential CXRs from 40 COVID patients (mean age ± standard deviation: 56 ± 13 years; 23 men, 10 women, seven not reported) and were categorized in three categories: “Worse”, “Stable”, or “Improved” on the basis of radiological evolution ascertained from images and reports. Receiver operating characteristic analyses, Mann-Whitney tests were performed.

Results

On patients from the CheXnet dataset, the area under ROC curves ranged from 0.71 to 0.93 for seven imaging features and one diagnosis. Deep learning features between “Worse” and “Improved” outcome categories 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 82.7% accuracy.

Conclusion

CXR deep learning features show promise for classifying the disease trajectory. Once validated in studies incorporating clinical data and with larger sample sizes, this information may be considered to inform triage decisions.

Related articles

Related articles are currently not available for this article.