AI-assisted gastric POCUS: distinguishing full vs empty stomach

Is this trial a fit for you?

A plain-English reading of the study's rules. Only the study team can confirm whether you qualify.

What this trial studies

This observational cohort study aims to train and test an AI program that interprets gastric POCUS images to classify stomach contents as full or empty. Healthy volunteers will undergo stomach ultrasound at fasting, after solid food, and after water intake, with randomized solid foods and water volumes. The study follows CONSORT-AI guidelines and seeks to improve interpretation of gastric ultrasound by clinicians who perform the exam at the bedside. Enrollment is planned for 30 participants, with imaging data used to train and validate the AI model. Interventions are not testing treatments, but rather generating and analyzing imaging data to develop the AI tool.

Why it matters

Who can join: the full rules

Inclusion Criteria:

A. Inclusion Criteria at the level of the participants

* Participants must meet all the following inclusion criteria to be eligible for the study:

  * Aged ≥18 years
  * Any sex
  * Be healthy

B. Inclusion Criteria at the level of the input data • Transverse ultrasound images (10 sec clips) of the gastric antrum in the epigastric area that contain all these structures:

* The edge of the left lobe of the liver
* The gastric antrum
* The pancreas
* The aorta

Exclusion Criteria:

A. Exclusion Criteria at the level of the participants

* Participants meeting any of the following exclusion criteria are ineligible for the study:

  * Previous gastro-esophageal surgery (e.g., gastric by-pass, sleeve gastrectomy, fundoplication, partial gastrectomy)
  * Allergy to any of the food that will be provided.

B. Exclusion Criteria at the level of the input data

• Ultrasound images (10 sec clips) where the gastric antrum cannot be positively identified.

Where it's running

• Toronto Western Hospital, University Health Network
  Toronto, Ontario, Canada Recruiting

Study contacts

• Principal investigator: Anahi Perlas — University Health Network, Toronto
• Study coordinator: Jayanta Chowdhury, MBBS,MD
• Email: jayanta.chowdhury@uhn.ca
• Phone: 416-603-5800

Similar studies

Other studies for the same condition or treatment. Recruiting studies are listed first.

• Workshop for training emergency physicians in point-of-care ultrasound using simulation

  This study is testing a hands-on workshop to help emergency doctors improve their ultrasound skills and see how well they learn before and after the training.

  Recruiting Duke University · Durham, North Carolina · NCT06960837

• Using ultrasound in emergency medical services in Switzerland

  This study is testing whether using ultrasound by helicopter emergency medical teams in Switzerland can help improve patient care and decision-making before they reach the hospital.

  Recruiting Insel Gruppe AG, University Hospital Bern · Zurich, Canton of Zurich · NCT06602856

• Improving Sleep for Older Adults in the Emergency Department

  This project tests whether wearing a Fitbit overnight can help understand and improve sleep for adults 70 and older in the emergency department who are likely to be admitted.

  Recruiting at 2 sites University Health Network, Toronto · Toronto, Ontario and 1 other locations · NCT07928141

• Can miRNA-371a-3p tell us which small testicular masses need surgery or can be watched?

  This study tests whether the miRNA-371a-3p biomarker can help decide if small testicular masses (≤2 cm) are cancer and should be treated with surgery or followed with surveillance.

  Recruiting University Health Network, Toronto · Toronto, Ontario · NCT07852871

• Effects of excitatory and inhibitory LIFUS of GPi in Parkinson’s patients without DBS

  This study tests two deep-brain focused ultrasound patterns on people with Parkinson’s to see if they change task performance and tremor, compared with a sham stimulation.

  Recruiting University Health Network, Toronto · Toronto, Ontario · NCT07846007

• Co-Adaptation of a Digital Pain Program for Canadian Veterans

  We’re testing whether a self-guided digital pain management program, delivered through the Manage My Pain app, is acceptable and useful for Canadian Veterans with chronic pain.

  Recruiting University Health Network, Toronto · Toronto, Ontario · NCT07818980

How to take part

1. Review the eligibility criteria above with your treating physician.
2. Check the official listing on ClinicalTrials.gov for the latest contact details and recruitment status.
3. Contact the study coordinator or principal investigator to ask for pre-screening. Pre-screening is free and never obligates you to enroll.