Chest radiograph and AI may predict need for hospitalization, supplemental oxygen in COVID patients: Study

USA: Deep learning analysis of chest x-ray may predict the need for supplemental oxygen and hospitalization in COVID-19 patients, finds a recent study.

The result, published in the journal Academic Radiology, suggests that further and validation and extension of this methodology is warranted.

Researchers created an AI program that first identified comorbid conditions such as chronic obstructive pulmonary disease (COPD) and cardiac arrhythmias on frontal chest x-rays of COVID-19 patients. The algorithm then predicted the likelihood of whether those patients would require full hospital admission and supplemental oxygen within 14 days.

In the study, Ayis Pyrros, DuPage Medical Group, Radiology, and colleagues aimed to determine the prognostic value of an outpatient chest radiograph, together with an ensemble of deep learning algorithms predicting comorbidities and airspace disease to identify patients at a higher risk of hospitalization from COVID-19 infection.

The retrospective study included 413 outpatients with COVID-19 confirmed by reverse transcription-polymerase chain reaction testing who received an ambulatory chest radiography between 3/17/2020 and 10/24/2020. Full admission was defined as hospitalization within 14 days of the COVID-19 test for >2 days with supplemental oxygen. Univariate analysis and machine learning algorithms were used to evaluate the relationship between the deep learning model predictions and hospitalization for >2 days.