AI Assistance on Chest Radiographs: No Accuracy Gain, But Faster Reads and Higher Confidence

Commercial AI for chest X-ray did not improve diagnostic accuracy in a prospective 5-reader crossover study; for some findings, false positives increased. However, reading time dropped by 6–17 sec (p≤0.031) and most readers reported higher confidence.

• Accuracy for pleural effusions and pulmonary nodules decreased in several reader-tool pairings due to increased false positives.
• AI support reduced senior consultations in selected pairings and, in one case, lowered CT escalation.
• Findings suggest need for careful local adaptation to avoid automation bias and maintain accuracy.

Automated summary

RadPigeon summaries are original and for information only. They are not clinical advice.