Establishment and Application of an Artificial Intelligence Algorithm for Automatic Identification of Intraoperative Bleeding During Laparoscopic Pancreaticoduodenectomy
Trial Snapshot
- Phase
- Not Applicable
- Status
- Recruiting
- Sponsor
- Enrollment
- 400
- Locations
- 1
- Primary Endpoint
- performance of artifical intelligence algorithm
Study Overview
Brief Summary
Surgeons will label surgical videos of laparoscopic pancreaticoduodenectomy with bleeding information from multicenter. The labeled surgical video will be used as training material to train the algorithmic model so as to build an artificial intelligence algorithm that can automatically identify intraoperative bleeding in this surgery. Then, we will test the performance capability of the algorithm.
Study Design
- Study Type
- Observational
- Observational Model
- Cohort
- Time Perspective
- Retrospective
Eligibility Criteria
- Sex
- All
- Accepts Healthy Volunteers
- No
Inclusion Criteria
- •surgical videos that recorded complete laparoscopic pancreaticoduodenectomy including resection and reconstruction phases.
Exclusion Criteria
- •1.surgical videos that recorded laparoscopic pancreaticoduodenectomy combined with resection and reconstruction of mesentericoportal vein.
Outcomes
Primary Outcomes
performance of artifical intelligence algorithm
Time Frame: through study completion, an average of 1 month
test the performance of the algorithm , including accuracy
Secondary Outcomes
No secondary outcomes reported
Investigators
Xinrui Zhu,MD
attending doctor
West China Hospital
