TY - JOUR
T1 - Predicting Prolonged Hospitalization and Supplemental Oxygenation in Patients with COVID-19 Infection from Ambulatory Chest Radiographs using Deep Learning
AU - Pyrros, Ayis
AU - Flanders, Adam Eugene
AU - Rodríguez-Fernández, Jorge Mario
AU - Chen, Andrew
AU - Cole, Patrick
AU - Wenzke, Daniel
AU - Hart, Eric
AU - Harford, Samuel
AU - Horowitz, Jeanne
AU - Nikolaidis, Paul
AU - Muzaffar, Nadir
AU - Boddipalli, Viveka
AU - Nebhrajani, Jai
AU - Siddiqui, Nasir
AU - Willis, Melinda
AU - Darabi, Houshang
AU - Koyejo, Oluwasanmi
AU - Galanter, William
N1 - Publisher Copyright:
© 2021 The Association of University Radiologists
PY - 2021/8
Y1 - 2021/8
N2 - Rationale and Objectives: The clinical prognosis of outpatients with coronavirus disease 2019 (COVID-19) remains difficult to predict, with outcomes including asymptomatic, hospitalization, intubation, and death. Here we determined 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. Materials and Methods: This retrospective study included outpatients with COVID-19 confirmed by reverse transcription-polymerase chain reaction testing who received an ambulatory chest radiography between March 17, 2020 and October 24, 2020. In this study, 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. Results: The study included 413 patients, 222 men (54%), with a median age of 51 years (interquartile range, 39–62 years). Fifty-one patients (12.3%) required full admission. A boosted decision tree model produced the best prediction. Variables included patient age, frontal chest radiograph predictions of morbid obesity, congestive heart failure and cardiac arrhythmias, and radiographic opacity, with an internally validated area under the curve (AUC) of 0.837 (95% CI: 0.791–0.883) on a test cohort. Conclusion: Deep learning analysis of single frontal chest radiographs was used to generate combined comorbidity and pneumonia scores that predict the need for supplemental oxygen and hospitalization for > 2 days in patients with COVID-19 infection with an AUC of 0.837 (95% confidence interval: 0.791–0.883). Comorbidity scoring may prove useful in other clinical scenarios.
AB - Rationale and Objectives: The clinical prognosis of outpatients with coronavirus disease 2019 (COVID-19) remains difficult to predict, with outcomes including asymptomatic, hospitalization, intubation, and death. Here we determined 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. Materials and Methods: This retrospective study included outpatients with COVID-19 confirmed by reverse transcription-polymerase chain reaction testing who received an ambulatory chest radiography between March 17, 2020 and October 24, 2020. In this study, 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. Results: The study included 413 patients, 222 men (54%), with a median age of 51 years (interquartile range, 39–62 years). Fifty-one patients (12.3%) required full admission. A boosted decision tree model produced the best prediction. Variables included patient age, frontal chest radiograph predictions of morbid obesity, congestive heart failure and cardiac arrhythmias, and radiographic opacity, with an internally validated area under the curve (AUC) of 0.837 (95% CI: 0.791–0.883) on a test cohort. Conclusion: Deep learning analysis of single frontal chest radiographs was used to generate combined comorbidity and pneumonia scores that predict the need for supplemental oxygen and hospitalization for > 2 days in patients with COVID-19 infection with an AUC of 0.837 (95% confidence interval: 0.791–0.883). Comorbidity scoring may prove useful in other clinical scenarios.
KW - COVID-19
KW - chest radiography
KW - convolutional neural networks
KW - deep learning
KW - multi-task learning
UR - http://www.scopus.com/inward/record.url?scp=85107949055&partnerID=8YFLogxK
UR - http://www.scopus.com/inward/citedby.url?scp=85107949055&partnerID=8YFLogxK
U2 - 10.1016/j.acra.2021.05.002
DO - 10.1016/j.acra.2021.05.002
M3 - Article
C2 - 34134940
AN - SCOPUS:85107949055
SN - 1076-6332
VL - 28
SP - 1151
EP - 1158
JO - Academic Radiology
JF - Academic Radiology
IS - 8
ER -