AI malignancy scores to end repeat scans and biopsies for benign lung nodules

Most lung nodules on CT are harmless but trigger years of follow-up scans, so this idea discharges AI-low-risk nodules at baseline instead of following them. Nodule AI improves discrimination over the Brock model, and follow-up imaging is a major cost and source of anxiety in screening and incidental nodule management. An RCT would compare immediate discharge of low-risk nodules with standard follow-up, using missed cancer at three years as the safety endpoint and scans and biopsies avoided as efficacy. The test is a multicentre RCT of 5,000 nodules. At early-clinical maturity it addresses the bottlenecks Overdiagnosis and false alarms and AI that is built but not validated or deployed.