이현우 (서울대학교 보라매병원) | 한빛사논문 > 한빛사

한빛사논문

조회323

서울대학교 보라매병원

CV File 122 kb

Chest, 2022 Jun 28;S0012-3692(22)01188-6. | https://doi.org/10.1016/j.chest.2022.06.018 Deep Learning-Based Prediction Model Using Radiography in Nontuberculous Mycobacterial Pulmonary Disease

Seowoo Lee MD^a, Hyun Woo Lee MD^b, Hyung-Jun Kim MD^c, Deog Kyeom Kim PhD^b, Jae-Joon Yim MD^d, Soon Ho Yoon PhD^a,e, Nakwon Kwak MD^d

^aDepartment of Radiology, Seoul National University College of Medicine, Seoul National University Hospital, Seoul, South Korea
^bDivision of Respiratory and Critical Care, Department of Internal Medicine, Seoul Metropolitan Government-Seoul National University Boramae Medical Center, Seoul, South Korea
^cDivision of Pulmonary and Critical Care Medicine, Department of Internal Medicine, Armed Forces Capital Hospital, Seongnam, South Korea
^dDivision of Pulmonary and Critical Care Medicine, Department of Internal Medicine, Seoul National University College of Medicine, Seoul National University Hospital, Seoul, South Korea
^eDepartment of Radiology, UMass Memorial Medical Center, Worcester, MA

Drs S. Lee and H. W. Lee contributed equally to this manuscript as first authors.
Drs S. H. Yoon and N. Kwak contributed equally to this manuscript as senior authors.
Correspondence to: Soon Ho Yoon PhD; Nakwon Kwak MD

Abstract

Background: Prognostic prediction of nontuberculous mycobacteria pulmonary disease using a deep learning technique has not been attempted.

Research question: Can a deep learning (DL) model using chest radiography predict the prognosis of nontuberculous mycobacteria pulmonary disease?

Study design and methods: Patients 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).

Results: The 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.

Interpretation: The 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.

논문정보

형식Research article
게재일2022년 06월 (BRIC 등록일 2022-10-11)
연구진국내(교신)+국외 연구진
분야 의약학 > 응용의학

댓글 작성 로그인

CV 열람하기

연락처 보기