此页面是自动翻译的，不保证翻译的准确性。请参阅 英文版 对于源文本。

AI for Gastric POCUS ( Point-of-care Ultrasound) (POCUS)

2026年7月29日 更新者：University Health Network, Toronto

Development of an Artificial Intelligence Algorithm to Enhance the Gastric Point-of-care Ultrasound. A Proof-of-concept Study.

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)

研究概览

地位

招聘中

条件

详细说明

Gastric (stomach) Point-of-care ultrasound (POCUS) is an ultrasound examination done at bedside to assess the stomach. It is a validated non-invasive way to find out what is the content in the stomach and its volume. Gastric POCUS is increasingly used before surgery to determine the risk of gastric contents going into the lungs (possibly causing a lung infection and breathing problems) and guide anesthetic management whenever the doctors are not certain about the stomach content based on clinical information.

Gastric POCUS is a relatively new skill for anesthesiologists. While, obtaining the required images is relatively straightforward, the interpretation of such images, however, requires advanced training. Preliminary data have suggested that Artificial Intelligence (AI)-based programs and devices can help in image capturing and its interpretation for other ultrasound applications. This study will be the first to the researcher's knowledge to develop an AI algorithm to enhance anesthesiologists' ability to recognize a full stomach using gastric POCUS. 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.

This is an observational prospective cohort study that follows the CONSORT (Consolidated Standards of Reporting Trials)-AI extension reporting guidelines.

The researchers expect to enroll 30 healthy volunteers for the study.

Following a period of fasting for solids for at least 8 hours and clear fluids for at least 2 hours from the time of study visit. An anesthesiologist or sonographer with a minimum previous experience of 50 gastric ultrasound examinations will perform a standardized gastric ultrasound exam.

A baseline ultrasound examination will be conducted first with the participant lying on their back with the head elevated at 30 degrees (supine position) and then again with the participant lying on their right side (right lateral decubitus position(RLD)).

The same procedure will be repeated twice after ingestion of

  1. various volumes of water (100-500) determined at random
  2. 1 of 5 different solid or thick fluid foods also determined at random (a banana, an apple, a cup of yogurt, a croissant or a muffin).

Each one of the 30 participants will be randomized to 1 of 5 different volumes of water (100ml, 200ml, 300ml, 400ml, 500ml). Then ultrasound images will be obtained. Subsequently, each participant will also be randomized to 1 of 5 solids (a banana, an apple, a cup of yogurt, a croissant or a muffin) in a 1:1:1:1:1 ratio. A computer-generated list of random numbers for each participant will be created.

The investigators plan to collect 90 10-second clips in total, and each clip can be deconstructed into 10 frozen frames per second, for a total of 100 frozen frames per clip. The investigators expect to generate 9,000 individual images, 80% of which will be used to train the model, 10% to fine-tune and 10% to test the model accuracy. The three de-identified clips from each participant will be normalized and annotated by consultant anesthesiologists to indicate orientation (medial or lateral, cephalad or caudad) and identify relevant structures, as well as the type of content and antral CSA in the right lateral decubitus in case of fluid.

All the collected images will then be fed to an AI to generate computational data.

研究类型

观察性的

注册 (估计的)

30

联系人和位置

本节提供了进行研究的人员的详细联系信息，以及有关进行该研究的地点的信息。

学习联系方式

学习地点

  • 加拿大
    • Ontario
      • Toronto、Ontario、加拿大、M5T 2S8
        • 招聘中
        • Toronto Western Hospital, University Health Network
        • 接触：
        • 首席研究员：
          • Anahi Perlas, MD, FRCPC

参与标准

研究人员寻找符合特定描述的人，称为资格标准。这些标准的一些例子是一个人的一般健康状况或先前的治疗。

资格标准

适合学习的年龄

  • 成人
  • 年长者

接受健康志愿者

是的

取样方法

非概率样本

研究人群

Adult healthy volunteer aged ≥18 years

描述

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.

学习计划

本节提供研究计划的详细信息，包括研究的设计方式和研究的衡量标准。

研究是如何设计的？

设计细节

研究衡量的是什么？

主要结果指标

结果测量
措施说明
大体时间
To see the overall accuracy of the AI model
大体时间：Through study completion, an average of 2 years
To see the overall accuracy of the AI-enhanced ultrasound model to differentiate no content and clear fluid from solid.
Through study completion, an average of 2 years

次要结果测量

结果测量
措施说明
大体时间
To measure the accuracy of the AI model in differentiating a empty from a full stomach
大体时间：Through study completion, an average of 2 years
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).
Through study completion, an average of 2 years
To measure the balanced accuracy of the AI model
大体时间：Through study completion, an average of 2 years
Balanced accuracy accounts for uneven distributions of detected objects (e.g., small vs. large anatomical structures)
Through study completion, an average of 2 years
To measure the precision of the AI model
大体时间：Through study completion, an average of 2 years
Precision evaluates the proportion of true positives among detected objects, addressing false positives that can lead to unnecessary interventions in clinical settings.
Through study completion, an average of 2 years
To measure the recall of the AI model
大体时间：Through study completion, an average of 2 years
(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.
Through study completion, an average of 2 years
To evaluate the model's classification performance across different confidence thresholds.
大体时间：Through study completion, an average of 2 years
Receiver Operating Characteristic (ROC) curves and Area Under Curve (AUC) will be computed to evaluate the model's classification performance across different confidence thresholds.
Through study completion, an average of 2 years
To evaluate the model's performance in detecting different anatomical structures (e.g., organs, vessels).
大体时间：Through study completion, an average of 2 years
Class-specific mean Average Precision (mAP) will be calculated to evaluate the model's performance in detecting different anatomical structures (e.g., organs, vessels). mAP is the standard metric for object detection tasks, summarizing precision and recall across multiple confidence thresholds.
Through study completion, an average of 2 years
To measure the latency and average inference time per image
大体时间：Through study completion, an average of 2 years
Given the clinical need for real-time feedback during ultrasound procedures, the average inference time per image and latency will be measured for each model.
Through study completion, an average of 2 years

合作者和调查者

在这里您可以找到参与这项研究的人员和组织。

赞助

University Health Network, Toronto

调查人员

  • 首席研究员：Anahi Perlas、University Health Network, Toronto

研究记录日期

这些日期跟踪向 ClinicalTrials.gov 提交研究记录和摘要结果的进度。研究记录和报告的结果由国家医学图书馆 (NLM) 审查，以确保它们在发布到公共网站之前符合特定的质量控制标准。

研究主要日期

学习开始 (实际的)

2026年5月5日

初级完成 (估计的)

2027年12月31日

研究完成 (估计的)

2027年12月31日

研究注册日期

首次提交

2026年4月27日

首先提交符合 QC 标准的

2026年5月6日

首次发布 (实际的)

2026年5月12日

研究记录更新

最后更新发布 (实际的)

2026年7月31日

上次提交的符合 QC 标准的更新

2026年7月29日

最后验证

2026年4月1日

更多信息

与本研究相关的术语

关键字

其他研究编号

  • 25-6148

药物和器械信息、研究文件

研究美国 FDA 监管的药品

不

研究美国 FDA 监管的设备产品

不

此信息直接从 clinicaltrials.gov 网站检索，没有任何更改。如果您有任何更改、删除或更新研究详细信息的请求，请联系 register@clinicaltrials.gov. clinicaltrials.gov 上实施更改，我们的网站上也会自动更新.

订阅