Lee Taehee, Ahn Su Yeon, Kim Jihang, Park Jong Sun, Kwon Byoung Soo, Choi Sun Mi, Goo Jin Mo, Park Chang Min, Nam Ju Gang
Department of Radiology and Institute of Radiation Medicine, Seoul National University Hospital and College of Medicine, 101, Daehak-Ro, Jongno-Gu, Seoul, 03080, Republic of Korea.
Department of Radiology, Konkuk University Medical Center, Konkuk University School of Medicine, Seoul, 05030, Republic of Korea.
Eur Radiol. 2024 Jul;34(7):4206-4217. doi: 10.1007/s00330-023-10501-w. Epub 2023 Dec 19.
To develop and validate a deep learning-based prognostic model in patients with idiopathic pulmonary fibrosis (IPF) using chest radiographs.
To develop a deep learning-based prognostic model using chest radiographs (DLPM), the patients diagnosed with IPF during 2011-2021 were retrospectively collected and were divided into training (n = 1007), validation (n = 117), and internal test (n = 187) datasets. Up to 10 consecutive radiographs were included for each patient. For external testing, three cohorts from independent institutions were collected (n = 152, 141, and 207). The discrimination performance of DLPM was evaluated using areas under the time-dependent receiver operating characteristic curves (TD-AUCs) for 3-year survival and compared with that of forced vital capacity (FVC). Multivariable Cox regression was performed to investigate whether the DLPM was an independent prognostic factor from FVC. We devised a modified gender-age-physiology (GAP) index (GAP-CR), by replacing D with DLPM.
DLPM showed similar-to-higher performance at predicting 3-year survival than FVC in three external test cohorts (TD-AUC: 0.83 [95% CI: 0.76-0.90] vs. 0.68 [0.59-0.77], p < 0.001; 0.76 [0.68-0.85] vs. 0.70 [0.60-0.80], p = 0.21; 0.79 [0.72-0.86] vs. 0.76 [0.69-0.83], p = 0.41). DLPM worked as an independent prognostic factor from FVC in all three cohorts (ps < 0.001). The GAP-CR index showed a higher 3-year TD-AUC than the original GAP index in two of the three external test cohorts (TD-AUC: 0.85 [0.80-0.91] vs. 0.79 [0.72-0.86], p = 0.02; 0.72 [0.64-0.80] vs. 0.69 [0.61-0.78], p = 0.56; 0.76 [0.69-0.83] vs. 0.68 [0.60-0.76], p = 0.01).
A deep learning model successfully predicted survival in patients with IPF from chest radiographs, comparable to and independent of FVC.
Deep learning-based prognostication from chest radiographs offers comparable-to-higher prognostic performance than forced vital capacity.
• A deep learning-based prognostic model for idiopathic pulmonary fibrosis was developed using 6063 radiographs. • The prognostic performance of the model was comparable-to-higher than forced vital capacity, and was independent from FVC in all three external test cohorts. • A modified gender-age-physiology index replacing diffusing capacity for carbon monoxide with the deep learning model showed higher performance than the original index in two external test cohorts.
利用胸部X光片开发并验证一种基于深度学习的特发性肺纤维化（IPF）患者预后模型。
为了开发一种基于胸部X光片的深度学习预后模型（DLPM），我们回顾性收集了2011年至2021年期间诊断为IPF的患者，并将其分为训练集（n = 1007）、验证集（n = 117）和内部测试集（n = 187）。每位患者最多纳入10张连续的X光片。为了进行外部测试，我们收集了来自独立机构的三个队列（n = 152、141和207）。使用3年生存时间依赖性受试者工作特征曲线下面积（TD-AUC）评估DLPM的辨别性能，并与用力肺活量（FVC）进行比较。进行多变量Cox回归以研究DLPM是否是独立于FVC的预后因素。我们通过用DLPM替代D设计了一种改良的性别-年龄-生理学（GAP）指数（GAP-CR）。
在三个外部测试队列中，DLPM在预测3年生存率方面表现出与FVC相似或更高的性能（TD-AUC：0.83 [95% CI：0.76 - 0.90] 对 0.68 [0.59 - 0.77]，p < 0.001；0.76 [0.68 - 0.85] 对 0.70 [0.60 - 0.80]，p = 0.21；0.79 [0.72 - 0.86] 对 0.76 [0.69 - 0.83]，p = 0.41）。在所有三个队列中，DLPM都是独立于FVC的预后因素（p值均 < 0.001）。在三个外部测试队列中的两个队列中，GAP-CR指数的3年TD-AUC高于原始GAP指数（TD-AUC：0.85 [0.80 - 0.91] 对 0.79 [0.72 - 0.86]，p = 0.02；0.72 [0.64 - 0.80] 对 0.69 [0.61 - 0.78]，p = 0.56；0.76 [0.69 - 0.83] 对 0.68 [0.60 - 0.76]，p = 0.01）。
一种深度学习模型成功地从胸部X光片中预测了IPF患者的生存率，与FVC相当且独立于FVC。
基于胸部X光片的深度学习预后评估提供了比用力肺活量更高的预后性能。
• 使用6063张X光片开发了一种基于深度学习的特发性肺纤维化预后模型。• 该模型的预后性能与用力肺活量相当或更高，并且在所有三个外部测试队列中独立于FVC。• 一种用深度学习模型替代一氧化碳弥散量的改良性别-年龄-生理学指数在两个外部测试队列中表现出比原始指数更高的性能。
