Skip to content

SleeveData: Development of a Standard Dataset for Postoperative Outcomes Following Laparoscopic Sleeve Gastrectomy

SleeveData: Development of a Standard Dataset for Postoperative Outcomes Following Laparoscopic Sleeve Gastrectomy - SleeveAI

Status
Active, not recruiting
Phases
Unknown
Study type
Observational
Source
DRKS
Registry ID
DRKS00033088
Enrollment
300
Registered
2024-01-10
Start date
2024-03-01
Completion date
Unknown
Last updated
2025-04-07

For informational purposes only — not medical advice. Sourced from public registries and may not reflect the latest updates. Terms

Conditions

Obesity with an body mass index over 40

Interventions

Group 1: Patients undergoing laparoscopic sleeve gastrectomy for obesity

Sponsors

Universitätsmedizin Mannheim
Lead Sponsor

Eligibility

Sex/Gender
All
Age
18 Years to No maximum

Inclusion criteria

Inclusion criteria: - Scheduled for LSG - Written informed consent

Exclusion criteria

Exclusion criteria: - Previous bariatric or major upper gastrointestinal surgery - Language barriers or impaired mental state - Unable to attend follow-up examinations

Design outcomes

Primary

MeasureTime frame
To develop and validate a predictive algorithm using machine learning techniques that analyzes annotated surgical videos of laparoscopic sleeve gastrectomy to determine the likelihood of patients developing postoperative dysphagia, reflux symptoms, and to evaluate the degree of weight loss 12 months after LSG.

Secondary

MeasureTime frame
• To identify and analyze the correlation between specific intraoperative events or techniques (as captured in surgical videos) and the development of postoperative symptoms, including dysphagia and reflux, as well as the extent of weight loss. • To create and utilize a comprehensive dataset that combines surgical video annotations with clinical parameters (including postoperative symptomatology and weight loss metrics) for advanced research in bariatric surgery outcomes. • To assess the feasibility and effectiveness of machine learning algorithms in predicting surgical outcomes, focusing on both immediate postoperative complications (like dysphagia and reflux) and long-term outcomes (such as weight loss), based on intraoperative video data.

Countries

Germany

Contacts

Public ContactCui Yang

Universitätsmedizin Mannheim

cui.yang@umm.de+496213835152

Outcome results

None listed

Source: DRKS (via WHO ICTRP) · Data processed: Feb 4, 2026