Real-time AI detection of surgical smoke during endoscopic laparoscopic procedures
Official title: Development of AI-Based Approaches for Automated Real-Time Detection of Surgical Smoke Using Endoscopic Image and Video Data
Run by University Hospital Tuebingen · NCT07397000 · Data updated 2026-11-12
This pilot will test whether an AI system can detect surgical smoke in real time from endoscopic video during laparoscopic procedures that use high-frequency surgical devices.
Quick facts
| Study type | Observational |
|---|---|
| Ages | 18 Years and up |
| Sex | Women only |
| Enrollment | 30 (estimated) |
| Sponsor | University Hospital Tuebingen Academic / other |
| Locations | 1 site (Tübingen) |
| Status | Recruiting |
| Started | February 21, 2024 |
| Main results expected | May 26, 2025 |
| Study ends | August 2026 |
| Registry record updated | February 9, 2026 |
| Trial ID | NCT07397000 on ClinicalTrials.gov |
Is this trial a fit for you?
✓Likely a good fit
Adult women (≥18) scheduled for laparoscopic surgery using HF devices and a Karl Storz S‑Pilot system who can give informed consent are ideal candidates.
✕Probably not a fit
Patients who do not undergo HF electrosurgery, cannot have the S‑Pilot device used, or cannot provide informed consent are unlikely to benefit.
A plain-English reading of the study's rules. Only the study team can confirm whether you qualify.
What this trial studies
This is a prospective, monocentric observational pilot that will collect endoscopic video and device activation logs to build a training dataset for an AI model. Women undergoing laparoscopic procedures with anticipated smoke generation from high-frequency (HF) surgical devices and use of a Karl Storz S‑Pilot smoke evacuation system will be enrolled. The S‑Pilot activation by clinical staff will serve as the reference standard, and model performance will be measured on held-out test data with a target F1 score ≥ 0.8. No experimental interventions will be applied; the study records intraoperative data to train and validate the computer-assisted detection algorithm.
Why it matters
Potential benefit: If successful, the AI could give immediate alerts when smoke appears, helping staff reduce exposure and improve visualization during laparoscopic surgery.
How similar studies have gone: Related AI work in endoscopic image analysis and surgical workflow recognition has shown promise, but real-time automated detection of surgical smoke is novel and only sparsely reported.
Who can join: the full rules
Show full inclusion / exclusion criteria
Inclusion Criteria: * \- Age ≥ 18 years * Written consent after receiving information * Indication for surgical treatment using HF surgery Exclusion Criteria: * \- Expected lack of compliance by the patient or inability of the patient to understand the meaning and purpose of the clinical trial * Lack of patient consent * S-Pilot cannot be used
Where it's running
-
Department of Women's Health, University Hospital
Tübingen, Germany Recruiting
Study contacts
- Principal investigator: Prof. Dr. Bernhard Krämer — Deparment of Women's Health, University Hospital Tübingen
- Study coordinator: Prof. Dr. Bernhard Krämer
- Email: bernhard.kraemer@med.uni-tuebingen.de
- Phone: +497071 2982211
How to take part
- Review the eligibility criteria above with your treating physician.
- Check the official listing on ClinicalTrials.gov for the latest contact details and recruitment status.
- Contact the study coordinator or principal investigator to ask for pre-screening. Pre-screening is free and never obligates you to enroll.