# AI clears the normal lung screening scans so radiologists read only the suspicious ones

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

## TL;DR

Most screening CT scans are normal. Letting a validated AI clear them, and sending only flagged scans to a radiologist, would let screening scale without more radiologists.

## Summary

Autonomous AI triage for chest X-ray is already CE-marked; for low-dose CT, tools reach high sensitivity for nodules of 6 mm and above. Propose a prospective non-inferiority trial where AI-negative scans are not read by radiologists (safety net: random 10% audit), with missed-cancer rate at two years as the primary endpoint.

## Fields

- Kind: Idea
- Last checked: 2026-09-08
- Hypothesis: AI negative-triage removes at least half of reads from radiologists with a missed-cancer rate non-inferior (margin 0.5 per 1,000) to double reading.
- Rationale: Radiologist capacity is the binding constraint on lung screening rollout in most countries; workload reduction, not detection, is the value.
- Proposed test: Two-arm prospective trial across three to five screening centres, about 50,000 scans, with registry-linked interval cancers.
- Maturity: early-clinical
- Actor: clinic

## Sources

- Bottleneck evidence (The hardest cancers are found late): Crosby et al., Early detection of cancer (Science 2022): https://doi.org/10.1126/science.aay9040

## 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/)
- companies: [Aidoc](https://onco.cc/companies/aidoc/), [Lunit](https://onco.cc/companies/lunit/)
- bottlenecks: [AI that is built but not validated or deployed](https://onco.cc/bottlenecks/b-ai-validation/), [Not enough oncologists, nurses, pathologists, physicists](https://onco.cc/bottlenecks/b-workforce/), [The hardest cancers are found late](https://onco.cc/bottlenecks/b-early-detection/)
- key papers: [Early detection of cancer](https://onco.cc/key-papers/paper-crosby-science/)

---
JSON: https://onco.cc/api/v1/entities/idea-prev-ldct-ai-negative-triage.json