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

Source: https://onco.cc/ideas/idea-fund-surgical-video-registry/  
OnCo record `idea-fund-surgical-video-registry` (Idea). Data CC BY-NC 4.0, attribute "Data from OnCo (onco.cc)"; commercial use needs a licence.

## TL;DR

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.

## Summary

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.

## Fields

- Kind: Idea
- Last checked: 2026-09-08
- 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.
- Proposed test: 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
- Actor: data

## Sources

- Bottleneck evidence (Surgery and radiotherapy cure most, get least): Sullivan et al., Global cancer surgery (Lancet Oncology Commission 2015): https://doi.org/10.1016/S1470-2045(15)00223-5

## Connected records

- ideas: [A permanently funded international network for randomised cancer surgery trials](https://onco.cc/ideas/idea-fund-surgical-trials-network/), [An independent evaluation unit for surgical robots and AI, paid on evidence](https://onco.cc/ideas/idea-fund-surgical-ai-robotics-evaluation/), [Mandatory staged registries for new surgical techniques before wide adoption](https://onco.cc/ideas/idea-fund-device-technique-registry/), [Public risk-adjusted outcome reporting for cancer surgery to drive centralisation](https://onco.cc/ideas/idea-fund-surgical-outcomes-public-reporting/)
- cancers: [Colorectal cancer](https://onco.cc/cancers/colorectal/), [Gastric & gastro-oesophageal junction cancer](https://onco.cc/cancers/gastric/), [Prostate cancer](https://onco.cc/cancers/prostate/)
- technologies: [Digital pathology & AI](https://onco.cc/technologies/digital-pathology-ai/), [Robotic & minimally invasive surgery](https://onco.cc/technologies/robotic-surgery/)
- bottlenecks: [Surgery and radiotherapy cure most, get least](https://onco.cc/bottlenecks/b-surgery-radiation-innovation/), [Weak real-world evidence and registries](https://onco.cc/bottlenecks/b-real-world-evidence/)
- key papers: [Global cancer surgery: delivering safe, affordable, and timely cancer surgery](https://onco.cc/key-papers/paper-sullivan-lancet-oncol/)

---
JSON: https://onco.cc/api/v1/entities/idea-fund-surgical-video-registry.json