Key result
AI chest radiograph border analysis shows modest discrimination for pulmonary thromboembolism with AUC ~0.66.
Why the study?
To evaluate the utility of an AI-based cardiovascular border analysis of chest radiographs in patients with pulmonary thromboembolism.
Does AI-based cardiovascular border analysis of chest radiographs provide diagnostic utility in patients with pulmonary thromboembolism?
Case-Control (n=390)
No
Does AI-based cardiovascular border analysis of chest radiographs provide diagnostic utility in patients with pulmonary thromboembolism?
Effect estimate: AUC 0.658
AI-based cardiovascular-border analysis of chest radiographs offers modest diagnostic performance for detecting pulmonary thromboembolism, particularly using the pulmonary trunk measurement.
No abstract yet. The journal hasn't published one we can show.
No takes yet. Share an insight, caveat, or question.
Ok et al. (2026) conducted a case-control in Pulmonary thromboembolism (PTE) (n=390). AI-based cardiovascular border analysis of chest radiographs vs. Age- and sex-matched controls was evaluated on Diagnostic performance assessed using receiver operating characteristic (ROC) analysis (AUC 0.658). AI-based cardiovascular-border analysis of chest radiographs showed modest discriminative performance for pulmonary thromboembolism, with the pulmonary trunk Z-score yielding an AUC of 0.658.
Synapse has enriched 5 closely related papers on similar clinical questions. Consider them for comparative context: