image: Left: Chest radiograph shows area of consolidation involving right lower lung consistent with pneumonia, as well as right pleural effusion. DL model predicted risk of 30-day mortality of 9%. Right: Gradient- weighted class activation map shows that model prediction was influenced by separate area of image corresponding with heart and liver (yellow and light blue colors). Patient’s CURB-65 score was 4. Patient recovered from pneumonia and remained alive at time of present investigation (14 months after pneumonia diagnosis). view more
Credit: AJR
Leesburg, VA, June 30, 2023—According to an accepted manuscript published in ARRS’ own American Journal of Roentgenology (AJR), a deep learning-based model using initial chest radiographs predicted 30-day mortality in patients with community-acquired pneumonia (CAP), improving upon the performance of an established risk prediction tool (i.e., CURB-65 score).
“The deep learning (DL) model may guide clinical decision-making in the management of patients with CAP by identifying high-risk patients who warrant hospitalization and intensive treatment,” concluded first author Eui Jin Hwang, MD, PhD, from the department of radiology at Seoul National University College of Medicine in Korea.
In this AJR accepted manuscript, a DL model was developed in 7,105 patients via one institution from March 2013 to December 2019 (3:1:1 allocation to training, validation, and internal test sets) to predict risk of all-cause mortality within 30 days after CAP diagnosis using patients’ initial chest radiograph. Hwang et al. then evaluated their DL model in patients diagnosed with CAP during emergency department visits at the same institution as the development cohort from January 2020 to December 2020 [temporal test cohort (n = 947)], and from two additional different institutions [external test cohort A (n = 467), January 2020 to December 2020; external test cohort B (n = 381), March 2019 to October 2021]. AUCs were compared between the DL model and a risk score based on confusion, blood urea nitrogen level, respiratory rate, blood pressure, and age ≥ 65 years.
Ultimately, a DL model using initial chest radiographs predicted 30-day all-cause mortality in patients with CAP with AUC ranging from 0.77 to 0.80 in test cohorts from different institutions. Additionally, the model showed higher specificity (range, 61–69%) than the CURB-65 score (44–58%) at the same sensitivity (all p < .001).
An electronic supplement to this AJR accepted manuscript is available here.
North America’s first radiological society, the American Roentgen Ray Society (ARRS) remains dedicated to the advancement of medicine through the profession of medical imaging and its allied sciences. An international forum for progress in radiology since the discovery of the x-ray, ARRS maintains its mission of improving health through a community committed to advancing knowledge and skills with the world’s longest continuously published radiology journal—American Journal of Roentgenology—the ARRS Annual Meeting, InPractice magazine, topical symposia, myriad multimedia educational materials, as well as awarding scholarships via The Roentgen Fund®.
MEDIA CONTACT:
Logan K. Young, PIO
44211 Slatestone Court
Leesburg, VA 20176
Journal
American Journal of Roentgenology
Method of Research
Imaging analysis
Subject of Research
People
Article Title
A Deep-Learning Model Using Chest Radiographs for Prediction of 30-Day Mortality in Patients With Community-Acquired Pneumonia: Development and External Validation
Article Publication Date
23-Jun-2023
COI Statement
Eui Jin Hwang reports a research grant from Lunit Inc., outside the present study. Chang Min Park reports a research grant from Lunit Inc., outside the present study, and holds stock of Promedius and stock options of Lunit Inc. and Coreline Soft.