1. Predicting Prolonged Hospitalization and Supplemental Oxygenation in Patients with COVID-19 Infection from Ambulatory Chest Radiographs using Deep Learning
- Author
-
Nadir Muzaffar, Ayis Pyrros, Oluwasanmi Koyejo, William L. Galanter, Melinda Willis, Adam E. Flanders, Paul Nikolaidis, Viveka Boddipalli, Jai Nebhrajani, Eric M. Hart, Daniel R. Wenzke, Andrew C. Chen, Jorge Mario Rodríguez-Fernández, Jeanne M. Horowitz, Patrick Cole, Samuel Harford, Nasir Siddiqui, and Houshang Darabi
- Subjects
Male ,Tenth Revision, MTL =, multi-task learning ,BMI =, body mass index ,030218 nuclear medicine & medical imaging ,0302 clinical medicine ,ROC =, receiver operating characteristic ,Interquartile range ,convolutional neural networks ,COVID-19 =, coronavirus disease 2019 ,EHR =, electronic health record ,Univariate analysis ,medicine.diagnostic_test ,HCC =, hierarchical condition category ,Middle Aged ,chest radiography ,Hospitalization ,030220 oncology & carcinogenesis ,Ambulatory ,Female ,Radiography, Thoracic ,medicine.symptom ,Adult ,medicine.medical_specialty ,AUC =, area under curve ,CNN =, convolutional neural network ,multi-task learning ,ICD10 =, International Classification of Diseases ,Asymptomatic ,Article ,03 medical and health sciences ,Internal medicine ,medicine ,RT-PCR =, reverse transcription-polymerase chain reaction ,Humans ,Radiology, Nuclear Medicine and imaging ,Retrospective Studies ,business.industry ,CHF =, congestive heart failure ,COVID-19 ,deep learning ,Retrospective cohort study ,CXR =, chest radiograph ,medicine.disease ,Comorbidity ,Confidence interval ,Oxygen ,CI =, confidence interval ,Chest radiograph ,business ,COPD =, chronic obstructive pulmonary disease - Abstract
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.
- Published
- 2021