OnCo
ideasIdea

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

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.

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.

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.
What would test it
Two-arm prospective trial across three to five screening centres, about 50,000 scans, with registry-linked interval cancers.
Maturity
early clinical
Who has to act
clinic
Cost to try
Medium ($1M to $50M)
Years to first evidence
4
Bottlenecks it attacks

Connected

10top

Pages like this

not linked directly; found by shared links