AI for Gastric POCUS ( Point-of-care Ultrasound)
ConditionPoint-of-care Ultrasound
Trial statusRecruiting
Trial phaseNot listed
Trial typeObservational
Biological sexAll
Age18+
SponsorUniversity Health Network, Toronto
About this trial
The goal of this observational study is to train and test an AI (Artificial Intelligence)-based program to assist anesthesiologists in the interpretation of stomach ultrasound images and differentiate a "full" from an "empty" stomach.
It is a healthy-volunteer study, where the participants will undergo ultrasound examination of their stomach at three different time points to visualize the stomach contents. These are at fasting state, after taking some solid food and after taking some water. Here, the participants will be randomized to receive one of five different types solid foods and one of five different volumes of water. The stomach ultrasound images will then be used to train and test the accuracy of the model to diagnose the type of stomach content (nothing vs. clear fluid vs. solid food)
Eligibility criteria
This trial accepts healthy volunteersQualifiers
Aged ≥18 years
Any sex
Be healthy
The edge of the left lobe of the liver
Disqualifiers
Previous gastro-esophageal surgery (e.g., gastric by-pass, sleeve gastrectomy, fundoplication, partial gastrectomy)
Allergy to any of the food that will be provided.
Trial population
Adult healthy volunteer aged ≥18 years
Trial design
Design model
Cohort
Time perspective
Prospective
Treatments tested in this trial
Not listed
Trial groups
No trial groups listed
Trial outcomes
Primary outcomes
1
To see the overall accuracy of the AI model
To see the overall accuracy of the AI-enhanced ultrasound model to differentiate no content and clear fluid from solid.
Time frame
Through study completion, an average of 2 yearsSecondary outcomes
1
To measure the accuracy of the AI model in differentiating a empty from a full stomach
To see the accuracy of the AI-enhanced ultrasound model to differentiate an "empty" (no content or clear fluid with an antral CSA (Cross-sectional Area)\< 10 cm2 in the RLD) from a "full" stomach (solid content or clear fluid with an antral CSA \> 10cm2 in the RLD).
Time frame
Through study completion, an average of 2 years2
To measure the balanced accuracy of the AI model
Balanced accuracy accounts for uneven distributions of detected objects (e.g., small vs. large anatomical structures)
Time frame
Through study completion, an average of 2 years3
To measure the precision of the AI model
Precision evaluates the proportion of true positives among detected objects, addressing false positives that can lead to unnecessary interventions in clinical settings.
Time frame
Through study completion, an average of 2 years4
To measure the recall of the AI model
(b) Recall (sensitivity) quantifies the model's ability to detect all relevant objects (true positives), critical for avoiding missed detections (false negatives) in important medical diagnoses.
Time frame
Through study completion, an average of 2 yearsSponsors and contacts
Click on the lead sponsor to view all of their trials.
Source ClinicalTrials.gov