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

Source: https://onco.cc/ideas/idea-prev-lung-nodule-ai-discharge/  
OnCo record `idea-prev-lung-nodule-ai-discharge` (Idea). Data CC BY-NC 4.0, attribute "Data from OnCo (onco.cc)"; commercial use needs a licence.

## TL;DR

Most lung nodules on CT are harmless but trigger years of follow-up scans. A validated AI score could discharge low-risk nodules immediately.

## Summary

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.

## Fields

- Kind: Idea
- Last checked: 2026-09-08
- Hypothesis: AI-based discharge removes at least 40% of follow-up CTs and 25% of benign biopsies with missed cancers under 0.5%.
- Rationale: Follow-up imaging burden is a major cost and anxiety source in screening and incidental nodule management.
- Proposed test: Run a multicentre RCT of 5,000 nodules.
- Maturity: early-clinical
- Actor: clinic

## Sources

- Bottleneck evidence (Overdiagnosis and false alarms): Welch & Black, Overdiagnosis in cancer (JNCI 2010): https://doi.org/10.1093/jnci/djq099

## Connected records

- cancers: [Non-small-cell lung cancer](https://onco.cc/cancers/nsclc/)
- fronts: [Early Detection & Screening](https://onco.cc/fronts/early-detection/), [Imaging](https://onco.cc/fronts/imaging/)
- technologies: [AI in radiology](https://onco.cc/technologies/radiology-ai-screening/), [CT (computed tomography)](https://onco.cc/technologies/ct/)
- bottlenecks: [AI that is built but not validated or deployed](https://onco.cc/bottlenecks/b-ai-validation/), [Overdiagnosis and false alarms](https://onco.cc/bottlenecks/b-overdiagnosis/)
- key papers: [Overdiagnosis in cancer](https://onco.cc/key-papers/paper-welch-j-natl-cancer-inst/)

---
JSON: https://onco.cc/api/v1/entities/idea-prev-lung-nodule-ai-discharge.json