A Study to Assess the Accuracy of Artificial Intelligence for Ultrasound-guided Regional Anesthesia
Study Details
Study Description
Brief Summary
The goal of this observational study is to assess the accuracy of Artificial Intelligence (AI) software to assist ultrasound scanning prior to peripheral nerve blocks. 40 healthy volunteers are going to be accepted to this study in which ultrasound scanning will be performed for four different block types.
The main questions it aims to answer are:
-
Can Nerveblox, the artificial intelligence software highlight and find the key anatomical landmarks on the provided nerve or plane block correctly?
-
Can the user obtain a correct view of provided nerve or plane block, when the AI software scan success reaches 100%?
Participants will be evaluated under four nerve block regions to identify their key anatomical landmarks using ultrasound-guided artificial intelligence software.
Three residents with different levels of Ultrasound-guided Regional Anesthesia(UGRA) experience but eligible to perform UGRA techniques will collect the ultrasound images when the artificial intelligence software scan success fed by ultrasound reached 100%. After collecting US images, each pair of US images(highlighted and raw ) will be evaluated by 2 experts for the accuracy of AI assistance, independently and blindly.
| Condition or Disease | Intervention/Treatment | Phase |
|---|---|---|
|
Detailed Description
Ultrasound-guided Regional Anesthesia (UGRA) is currently an effective method for the anesthesiologist. In this single-centered study, we aim to assess the accuracy of artificial intelligence effectiveness. All scans will be performed on an FDA-cleared general-purpose ultrasound device (GE Logiq, Wisconsin, USA) and software setup will be provided by the sponsor also having the software (Nerveblox, Smart Alfa Teknoloji San. Ve Tic. A.S., Ankara, Turkey).
The methodology of the study is that:
-
Three independent residents, in the 2nd, 3rd, and 4th years of education in the field of anesthesiology and also eligible to perform UGRA, will be recruited for using the artificial intelligence software (Nerveblox v1.0).
-
40 (20 male and 20 female) volunteers will be recruited for the study and the volunteer's demographic information (body mass index, gender, age) will be considered and recorded.
-
The order of volunteers will be randomized between participants.
-
Considered peripheral nerve and plane blocks are:
-
Interscalene brachial plexus
-
Supraclavicular brachial plexus
-
Infraclavicular brachial plexus
-
Transversus abdominis plane
-
Each trainee will reach 100% "scan success" on the Nerveblox to record the raw and highlighted images.
-
Each trainee will scan only 1 time.
On the data analysis:
-
Evaluation of the accuracy of artificial intelligence software will be completed independently by 2 experts in the field of regional anesthesia using the grading scale (0: mislocated, 1: very poor, 2: poor, 3: good, 4: very good, 5: excellent).
-
Experts will be asked the evaluate the accuracy of Nerveblox highlighting performance when it reached 100%.
-
Demographic data averages will be presented on the result of the study.
-
Data will be analyzed by using SPSS 25.0 software at a 95% confidence level. For the measurements, the mean, standard deviation (SD), minimum, maximum, and median statistics will be provided.
Study Design
Outcome Measures
Primary Outcome Measures
- Accuracy of AI to identify key anatomical landmarks on real-time ultrasound image prior to ultrasound-guided peripheral nerve and plane blocks [1 month]
Residents will scan the 40 volunteers (20 male and 20 female) using the artificial intelligence software until obtaining 100% scan success which means all region-related key anatomical landmarks are identified and color-overlayed correctly. The accuracy of key anatomical landmarks will be evaluated by 2 independent experts in the field of regional anesthesia.
Secondary Outcome Measures
- Evaluation of rating results completed by experts according to demographic information [1 day, after scanning and rating the all volunteers]
During the scanning, the volunteer's body mass index, gender, and age information will be collected. The accuracy of artificial intelligence software will be evaluated with the collected demographic information in order to learn the difference in accuracy.
Eligibility Criteria
Criteria
Inclusion Criteria:
-
Volunteers over the age of 18
-
Able to accept and sign the Informed Consent Form before participating in the study
Exclusion Criteria:
-
Volunteers below the age of 18
-
Unwilling to accept or having psychiatric/neurological diseases to sign an Informed Consent Form before participating in the study
-
Inability to lie flat
-
Anatomical deformity in the selected regions
Contacts and Locations
Locations
| Site | City | State | Country | Postal Code | |
|---|---|---|---|---|---|
| 1 | Gazi University School of Medicine | Çankaya | Ankara | Turkey | 06500 |
Sponsors and Collaborators
- Smart Alfa Teknoloji San. ve Tic. A.S.
- Gazi University
Investigators
- Study Director: Dudu Berrin Günaydın, Proffessor, Gazi University
Study Documents (Full-Text)
None provided.More Information
Publications
None provided.- SMARTALPHA-NERVEBLOX-1021