Chest Radiography AI Concordance and Lung Cancer Linkage in a Large Health Check-up Cohort
Discuss this preprint
Start a discussion What are Sciety discussions?Listed in
This article is not in any list yet, why not save it to one of your lists.Abstract
Purpose
To evaluate the implementation characteristics of a commercially available chest radiography artificial intelligence (AI) system in a large real-world health check-up cohort using workflow-level, lesion-specific, and exploratory retrospective lung cancer case analyses.
Methods
This retrospective single-centre study included 298,991 consecutive health check-up chest radiographs from 114,866 individuals obtained between 2019 and 2023 and interpreted under routine double reading by board-certified radiologists. A commercially available AI system was evaluated using two prespecified thresholds: positivity in any of ten findings for the all-score analysis and positivity for nodule or mass for the nodule-focused analysis, both at a manufacturer-recommended score threshold of 15. Because routine radiologist judgement rather than universal CT or pathologic verification served as the reference framework, the primary analyses were interpreted as radiologist-referenced operational concordance analyses.
Results
Radiologist-referenced sensitivity and specificity were 72.0% and 79.6%, respectively, in the all-score analysis and 87.1% and 91.8%, respectively, in the nodule-focused analysis. Negative predictive values were 99.0% and 100.0%, respectively. Among 48 histopathologically confirmed lung cancer cases, retrospective timeline analyses showed earlier AI positivity than routine radiologist positivity in a subset of cases. These findings should be interpreted as exploratory observations and do not establish prospective clinical benefit.
Conclusion
In a large health check-up cohort, chest radiography AI demonstrated stable concordance with routine radiologist judgement and high sensitivity for radiologist-reported pulmonary nodules and masses. Exploratory retrospective analyses showed earlier AI positivity in a subset of histopathologically confirmed lung cancer cases, supporting further prospective evaluation of AI-assisted health check-up workflows.
At a Glance Commentary
Scientific Knowledge on the Subject
Artificial intelligence has shown promise for supporting chest radiograph interpretation, including detection of pulmonary nodules and other thoracic abnormalities. However, most previous studies have used selected datasets, simulated reading environments, or enriched populations. Evidence remains limited regarding how chest radiography AI performs at programme scale in low-prevalence, real-world health check-up settings, particularly with respect to concordance with routine radiologist judgement, discordant review volume, and retrospective linkage to clinically confirmed lung cancer cases.
What This Study Adds to the Field
In 298,991 consecutive health check-up examinations, chest radiography AI demonstrated stable concordance with routine radiologist judgement. For radiologist-reported pulmonary nodules and masses, AI showed 87.1% sensitivity and 100.0% negative predictive value relative to the radiologist reference framework. Retrospective analysis of histopathologically confirmed lung cancer cases identified earlier AI positivity in a subset of patients, although prospective clinical benefit remains unproven. These findings provide large-scale, implementation-oriented evidence on the potential role and limitations of AI as a supplementary tool within radiologist-led chest radiography workflows.
