• Seowoo Lee, Hyun Woo Lee, Hyung-Jun Kim, Deog Kyeom Kim, Jae-Joon Yim, Soon Ho Yoon, and Nakwon Kwak.
• Department of Radiology, Seoul National University College of Medicine, Seoul National University Hospital, Seoul, South Korea.
• Chest. 2022 Nov 1; 162 (5): 9951005995-1005.

BackgroundPrognostic prediction of nontuberculous mycobacteria pulmonary disease using a deep learning technique has not been attempted.Research QuestionCan a deep learning (DL) model using chest radiography predict the prognosis of nontuberculous mycobacteria pulmonary disease?Study Design And MethodsPatients who received a diagnosis of nontuberculous mycobacteria pulmonary disease at Seoul National University Hospital (training and validation dataset) between January 2000 and December 2015 and at Seoul Metropolitan Government-Boramae Medical Center (test dataset) between January 2006 and December 2015 were included. We trained DL models to predict the 3-, 5-, and 10-year overall mortality using baseline chest radiographs at diagnosis. We tested the predictability for the corresponding mortality using only DL-driven radiographic scores and using both radiographic scores and clinical information (age, sex, BMI, and mycobacterial species).ResultsThe datasets comprised 1,638 (training and validation set) and 566 (test set) chest radiographs from 1,034 and 200 patients, respectively. The Dl-driven radiographic score provided areas under the receiver operating characteristic curve (AUC) of 0.844, 0.781, and 0.792 for 10-, 5-, and 3-year mortality, respectively. The logistic regression model using both the radiographic score and clinical information provided AUCs of 0.922, 0.942, and 0.865 for the 10-, 5, and 3-year mortality, respectively.InterpretationThe DL model we developed could predict the mid-term to-long-term mortality of patients with nontuberculous mycobacteria pulmonary disease using a baseline radiograph at diagnosis, and the predictability increased with clinical information.Copyright © 2022 American College of Chest Physicians. Published by Elsevier Inc. All rights reserved.

16 keywords...

hide…