OnCo
ideasIdea

A video-based surgical quality registry linking assessed skill to cancer outcomes

Surgeons' skill affects whether cancer comes back, but nobody measures it. Recording operations and rating them, increasingly with AI, then linking ratings to outcomes, would make surgical quality visible and improvable.

A registry in which cancer operations are routinely video-recorded, rated for technical skill by blinded peers and validated computer-vision tools, and linked to pathological (margins, lymph node yield) and oncological outcomes. Michigan's bariatric surgery collaborative showed that peer-rated skill predicts complications; oncology studies have linked skill ratings to margin status and survival. The registry supports credentialling for trials, targeted coaching, learning-curve monitoring for new techniques, and eventually AI feedback during surgery. Consent, data protection and non-punitive governance are the hard parts and must be designed with surgeons.

Hypothesis
Surgeons who receive video-based skill feedback improve rated skill and reduce positive margin rates measurably within two years, and registry skill scores predict recurrence independently of volume and stage.
Rationale
Skill-outcome associations have been shown in bariatric, colorectal and prostate surgery; video review with feedback improves technical scores in randomised studies of trainees. Making this systematic is an infrastructure and governance problem, not a scientific one.
What would test it
Enrol twenty centres, record and rate a defined operation for two years, and test skill-outcome associations and the effect of feedback in a stepped-wedge design.
Maturity
early clinical
Who has to act
data
Cost to try
Medium ($1M to $50M)
Years to first evidence
3
Bottlenecks it attacks

Connected

11top