A Deep Learning Model to Predict the Need for Mechanical Ventilation Using Chest X-Ray Images in Hospitalized COVID-19 Patients
Abstract
Purpose
Early identification of a potentially deteriorating clinical course in hospitalized COVID-19 patients is critical since there exists a resource-demand gap for the ventilators.
Materials
We aimed to develop and validate a deep learning-based approach to predict the need for mechanical ventilation as early as at the time of initial radiographic evaluation. We exploited the well-established DenseNet121 deep learning architecture for this purpose on 663 X-ray images derived from 528 hospitalized COVID-19 patients. Two Pulmonary and Critical Care experts blindly and independently evaluated the same X-ray images for purpose of validation.
Results
We found that our deep learning model predicted the need for ventilation with a high accuracy, sensitivity and specificity (90.06%, 86.34% and 84.38%, respectively). This prediction was done approximately three days ahead of the actual intubation event. Our model also outperformed two Pulmonary and Critical Care experts who evaluated the same X-ray images and provided an incremental accuracy of 7.24–13.25%.
Conclusion
Our deep learning model accurately predicted the need for mechanical ventilation early during hospitalization of COVID-19 patients. Until effective preventive or treatment measures become widely available for COVID-19 patients, prognostic stratification as provided by our model is likely to be highly valuable.
Related articles
Related articles are currently not available for this article.