Performance of a deep-learning algorithm for referable thoracic abnormalities on chest radiographs: A multicenter study of a health screening cohort

Abstract

Purpose: This study evaluated the performance of a commercially available deep-learning algorithm (DLA) (Insight CXR, Lunit, Seoul, South Korea) for referable thoracic abnormalities on chest X-ray (CXR) using a consecutively collected multicenter health screening cohort.

Methods and materials: A consecutive health screening cohort of participants who underwent both CXR and chest computed tomography (CT) within 1 month was retrospectively collected from three institutions' health care clinics (n = 5,887). Referable thoracic abnormalities were defined as any radiologic findings requiring further diagnostic evaluation or management, including DLA-target lesions of nodule/mass, consolidation, or pneumothorax. We evaluated the diagnostic performance of the DLA for referable thoracic abnormalities using the area under the receiver operating characteristic (ROC) curve (AUC), sensitivity, and specificity using ground truth based on chest CT (CT-GT). In addition, for CT-GT-positive cases, three independent radiologist readings were performed on CXR and clear visible (when more than two radiologists called) and visible (at least one radiologist called) abnormalities were defined as CXR-GTs (clear visible CXR-GT and visible CXR-GT, respectively) to evaluate the performance of the DLA.

Results: Among 5,887 subjects (4,329 males; mean age 54±11 years), referable thoracic abnormalities were found in 618 (10.5%) based on CT-GT. DLA-target lesions were observed in 223 (4.0%), nodule/mass in 202 (3.4%), consolidation in 31 (0.5%), pneumothorax in one 1 (<0.1%), and DLA-non-target lesions in 409 (6.9%). For referable thoracic abnormalities based on CT-GT, the DLA showed an AUC of 0.771 (95% confidence interval [CI], 0.751-0.791), a sensitivity of 69.6%, and a specificity of 74.0%. Based on CXR-GT, the prevalence of referable thoracic abnormalities decreased, with visible and clear visible abnormalities found in 405 (6.9%) and 227 (3.9%) cases, respectively. The performance of the DLA increased significantly when using CXR-GTs, with an AUC of 0.839 (95% CI, 0.829-0.848), a sensitivity of 82.7%, and s specificity of 73.2% based on visible CXR-GT and an AUC of 0.872 (95% CI, 0.863-0.880, P <0.001 for the AUC comparison of GT-CT vs. clear visible CXR-GT), a sensitivity of 83.3%, and a specificity of 78.8% based on clear visible CXR-GT.

Conclusion: The DLA provided fair-to-good stand-alone performance for the detection of referable thoracic abnormalities in a multicenter consecutive health screening cohort. The DLA showed varied performance according to the different methods of ground truth.

Conflict of interest statement

The authors have declared that no competing interests exist.

Figures

Fig 1. Flow chart of the study population.

Fig 2. The prevalence of normal cases, and target and non-target lesions of a deep-learning algorithm (DLA) showing significant differences between the three institutions.

Institution G has fewer normal cases and more DLA-non-target lesions compared to those of the other two institutions.

Fig 3. Receiver operating characteristic curve (ROC) curve of a deep-learning algorithm (DLA) for referable thoracic abnormalities on chest radiography based on different standard reference methods.

The area under the ROC curve (AUC) shows better performance when using visible and clear visible CXR compared to using CT as ground truth methods, except for institution G (C).