Electrical Fingerprint: Comparison of Characteristic Patterns of Different Surgical Interventions Based on Electrosurgical Unit Data
Trial Snapshot
- Phase
- Not Applicable
- Status
- Recruiting
- Enrollment
- 160
- Locations
- 1
- Primary Endpoint
- Identification of Unique Electrosurgical Data Patterns ("Digital Fingerprints") for Surgical Procedures
Study Overview
Brief Summary
The purpose of this prospective, single center study is to verify the hypothesis that each type of intervention creates a specific data pattern like a digital "fingerprint". This fingerprint offers the possibility to identify specific workflows of surgical procedures but also to differentiate between them, what can be used for training purposes. The following clinical study is not covered by the MDR regulation since we do not investigate performance or safety of a device but collect and assign electrical data only.
Detailed Description
The Erbe ESU VIO 3 provides electrical measurement data with high accuracy and time resolution. With the availability of the Erbe ECB Data Transmitter it is possible to record electrical data from the VIO 3 during clinical procedures, which open up a variety of possibilities for enhancing clinical workflows.
For this purpose, the VIO 3 will be connected via ECB (Erbe communication bus) interface with the "Data Transmitter". Using the software implemented by Erbe on the "Data transmitter", electrical data - generated during electrosurgical interventions - are recorded, forwarded via LAN, WLAN or LTE and stored in the Azure Cloud. These data do not contain any patient information and will be only used for the stated study objective.
In future, based on the analyses of electrosurgical device data users could benefit from e.g. continuous training as well as self enhancement/reflection by electrosurgical information offered during or after a surgical procedure. A first step to reach this goal is to build up a database containing electrosurgical data of different surgical interventions, to identify the electrosurgical "fingerprint" of each intervention and to detect different patterns between them. Therefore, the purpose of this study is to record electrosurgical data and to verify the hypothesis that each type of intervention creates a specific data pattern like a digital "fingerprint".
Study Design
- Study Type
- Observational
- Observational Model
- Case Only
- Time Perspective
- Prospective
Eligibility Criteria
- Ages
- 18 Years to — (Adult, Older Adult)
- Sex
- Female
- Accepts Healthy Volunteers
- No
Inclusion Criteria
- •Age ≥ 18 years
- •Written informed consent
- •Patients undergoing one of the following surgeries:
- •Supra cervical hysterectomy
- •Total hysterectomy
- •Breast conserving surgeries: B-plastic + periareolar mastopexy
- •Breast conserving surgeries: segmental resection
Exclusion Criteria
- •Expected lack of patient compliance or inability of the patient to understand the purpose of the clinical trial
- •Lack of patient consent
- •Surgery under local anaesthesia
- •Robot-Assisted Surgery
Arms & Interventions
Unknown
Procedure type
Procedures:
- Supra cervical hysterectomy (+/- salpingectomy)
- Total hysterectomy
- Breast conserving surgeries: b-plastic + periareolar mastopexy (+/- Sentinel lymphonodectomy, SLNE)
- Breast conserving surgeries: segmental resection (+/- SLNE)
Data will be collected among patients who undergo surgery at the Department of Women's Health independently of this study.
Intervention: Procedure type (Device)
Outcomes
Primary Outcomes
Identification of Unique Electrosurgical Data Patterns ("Digital Fingerprints") for Surgical Procedures
Time Frame: During surgery and post-procedure analysis (data collection over 12 months)
The study aims to determine whether different types of surgical interventions generate distinct electrosurgical data patterns. The accuracy of assigning recorded electrosurgical data to the correct surgical procedure type will be evaluated. Data Source: Electrosurgical signals recorded by the Erbe ECB Data Transmitter and VIO 3 system, stored in the Erbe Cloud for analysis. Measurement Method: * Each dataset will be classified into one of the predefined procedure types or as "unknown." * The classification algorithm must achieve at least 80% accuracy in correctly identifying procedure types. * The classification algorithm must achieve at least 80% accuracy in assigning procedures outside the predefined types to the "unknown" category.
Secondary Outcomes
No secondary outcomes reported