Establishment and Application of an Artificial Intelligence Algorithm for Automatic Identification of Intraoperative Bleeding During Laparoscopic Pancreaticoduodenectomy

Xinrui Zhu，MD

Status: Enrolling

Conditions: Laparoscopic Pancreaticoduodenectomy

Treatments: Other: laparoscopic pancreaticoduodenectomy

Study type: Observational

Funder types: Other

Identifiers

NCT06172062

2023-1663-2

Details and patient eligibility

About

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.

Enrollment: 400 estimated patients

Sex: All

Volunteers: No Healthy Volunteers

Inclusion criteria

1. 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.

Trial design

400 participants in 1 patient group

LPD cohort

Description:

surgical videos of laparoscopic pancreaticoduodenectomy with label to build and test the algorithms.

Treatment:

Other: laparoscopic pancreaticoduodenectomy