AUTHORS
Ji Yeong An, MD1, Eui Jin Hwang, MD, PhD1&3, Gunhee Nam, BS2, Sang Hyup Lee, MD2, Chang Min Park, MD, PhD,1&3 Jin Mo Goo, MD, PhD1, and Ye Ra Choi, MD3&4
1 Department of Radiology, Seoul National University Hospital, Seoul, Republic of Korea
2Lunit, Seoul, Republic of Korea
3.Department of Radiology, Seoul National University College of Medicine, Seoul, Republic of Korea
4.Department of Radiology, Seoul Metropolitan Government Seoul National University Boramae Medical Center, Seoul, Republic of Korea
PUBLISHED
Abstract
Background
Timely and accurate interpretation of chest radiographs obtained to evaluate endotracheal tube (ETT) position is important for facilitating prompt adjustment if needed.
Objective
To evaluate the performance of a deep learning (DL)-based artificial intelligence (AI) system for detecting ETT presence and position on chest radiographs in three patient samples from two different institutions.
Methods
This retrospective study included 539 chest radiographs obtained immediately after ETT insertion from January 1, 2020 to March 31, 2020 in 505 patients (293 men, 212 women; mean age, 63 years) from institution A (sample A); 637 chest radiographs obtained from January 1, 2020 to January 3, 2020 in 304 patients (158 men, 147 women; mean age, 63 years) in the ICU (with or without an ETT) from institution A (sample B); and 546 chest radiographs obtained from January 1, 2020 to January 20, 2020 in 83 patients (54 men, 29 women; mean age, 70 years) in the ICU (with or without an ETT) from institution B (sample C). A commercial DL-based AI system was used to identify ETT presence and measure ETT tip-to-carina distance (TCD). Reference standard for proper ETT position was TCD between 3 cm and 7 cm, determined by human readers. Critical ETT position was separately defined as ETT tip below the carina or TCD ≤1 cm. ROC analysis was performed.
Results
AI had sensitivity and specificity for identification of ETT presence of 100.0% and 98.7% (sample B) and 99.2% and 94.5% (sample C). AI had sensitivity and specificity for identification of improper ETT position of 72.5% and 92.0% (sample A), 78.9% and 100.0% (sample B), and 83.7% and 99.1% (sample C). At threshold y-axis TCD ≤2 cm, AI had sensitivity and specificity for critical ETT position of 100.0% and 96.7% (sample A), 100.0% and 100.0% (sample B), and 100.0% and 99.2% (sample C).
Conclusion
AI identified improperly positioned ETTs on chest radiographs obtained after ETT insertion, as well as on chest radiographs obtained from patients in the ICU at two institutions.
Clinical Impact
Automated AI identification of improper ETT position on chest radiograph may allow earlier repositioning and thereby reduce complications.
