Related Experiment Video
Updated: Aug 9, 2025
Lung CT Segmentation to Identify Consolidations and Ground Glass Areas for Quantitative Assesment of SARS-CoV Pneumonia
Published on: December 19, 2020
Validation of a deep learning, value-based care model to predict mortality and comorbidities from chest radiographs
Ayis Pyrros1, Jorge Rodriguez Fernandez2, Stephen M Borstelmann3
1Department of Radiology, Duly Health and Care, Hinsdale, Illinois.
Insights
A deep learning model accurately predicts comorbidities and mortality in COVID-19 patients using chest X-rays. This tool aids clinical decisions by analyzing frontal chest radiographs (CXRs) for conditions like diabetes and heart failure.
Area of Science:
- Medical Imaging
- Artificial Intelligence in Medicine
- Radiology
Background:
- Predicting comorbidities and mortality in COVID-19 patients is crucial for clinical decision-making.
- Hierarchical Condition Category (HCC) models and Risk Adjustment Factor (RAF) scores are standard tools for patient risk stratification.
- Frontal chest radiographs (CXRs) offer a readily available imaging modality.
Purpose of the Study:
- To validate a deep learning model for predicting comorbidities from frontal CXRs in COVID-19 patients.
- To compare the model's performance against HCC data and its ability to predict mortality outcomes.
- To assess the model's utility in both ambulatory and hospitalized COVID-19 cohorts.
Main Methods:
- A deep learning model was trained on 14,121 ambulatory frontal CXRs (2010-2019) to predict select comorbidities using the Medicare Advantage HCC Risk Adjustment Model.
- The model was validated internally on 413 ambulatory COVID-19 patients and externally on 487 hospitalized COVID-19 patients.
- Performance was evaluated using receiver operating characteristic (ROC) curves for comorbidity prediction and logistic regression for mortality prediction.
Main Results:
- The model achieved an area under the ROC curve (AUC) of 0.85 for predicting comorbidities including diabetes, obesity, and heart failure.
- The model demonstrated strong discriminatory ability for mortality prediction with an AUC of 0.84 in combined cohorts.
- Predicted comorbidities and RAF scores were accurately assessed in both internal and external COVID-19 cohorts.
Conclusions:
- Deep learning models can effectively predict select comorbidities from frontal CXRs in COVID-19 patients.
- The model shows significant potential for predicting mortality risk in COVID-19, aiding clinical decision-making.
- Frontal CXRs, analyzed by AI, offer a valuable tool for risk stratification in COVID-19 management.
Abstract:
We validate a deep learning model predicting comorbidities from frontal chest radiographs (CXRs) in patients with coronavirus disease 2019 (COVID-19) and compare the model's performance with hierarchical condition category (HCC) and mortality outcomes in COVID-19. The model was trained and tested on 14,121 ambulatory frontal CXRs from 2010 to 2019 at a single institution, modeling select comorbidities using the value-based Medicare Advantage HCC Risk Adjustment Model. Sex, age, HCC codes, and risk adjustment factor (RAF) score were used. The model was validated on frontal CXRs from 413 ambulatory patients with COVID-19 (internal cohort) and on initial frontal CXRs from 487 COVID-19 hospitalized patients (external cohort). The discriminatory ability of the model was assessed using receiver operating characteristic (ROC) curves compared to the HCC data from electronic health records, and predicted age and RAF score were compared using correlation coefficient and absolute mean error. The model predictions were used as covariables in logistic regression models to evaluate the prediction of mortality in the external cohort. Predicted comorbidities from frontal CXRs, including diabetes with chronic complications, obesity, congestive heart failure, arrhythmias, vascular disease, and chronic obstructive pulmonary disease, had a total area under ROC curve (AUC) of 0.85 (95% CI: 0.85-0.86). The ROC AUC of predicted mortality for the model was 0.84 (95% CI,0.79-0.88) for the combined cohorts. This model using only frontal CXRs predicted select comorbidities and RAF score in both internal ambulatory and external hospitalized COVID-19 cohorts and was discriminatory of mortality, supporting its potential use in clinical decision making.
More Related Videos
Related Concept Videos
01:30Pneumonia III: Complications and Assessment
01:27Chronic Obstructive Pulmonary Disease-IV: Assessement and Diagnostic Studies
Medical History
01:29Pulmonary Embolism II: Diagnostic Studies and Interprofessional Care
01:29Assessment of Ventilation II: Respiratory Depth and Rhythm
Respiratory depth measures the volume of air inhaled or exhaled during a breath. It can vary from shallow to deep and typically remains consistent when a person is at rest or asleep. Occasionally, individuals will automatically inhale deeply, known as sighing, which inflates the lungs with more air than normal breathing.
To assess respiratory depth, observe the degree of chest excursion or movement:
01:20Imaging Studies for Cardiovascular System III: X-Ray
Definition and Purpose
An X-ray, or radiograph, is a non-invasive method that uses ionizing radiation to take images of internal structures. It is mainly used in cardiac imaging to examine the heart, lungs, and major blood vessels, aiming to identify abnormalities in the heart's size, shape, and position, such as heart failure, congenital defects, and vascular...
01:13Radiological Investigation III: Pulmonary Angiogram and PET Scan
Pulmonary Angiogram
A Pulmonary Angiogram is an invasive procedure involving injecting a contrast medium through a catheter threaded into the pulmonary artery or the right side of the heart to visualize the pulmonary vasculature. Computed Tomography (CT) scans have mainly replaced this...