Posted in | News | Medical Robotics

Wearable AI System Tracks Tiny Sensors for Precise Diagnosis

In a recently published study in the journal Cell Reports Physical Science, researchers from the University of Southern California have created a system that uses AI to track tiny devices that monitor disease markers in the gut. Devices utilizing this novel system may enable at-risk individuals to monitor their gastrointestinal (GI) tract health at home, eliminating the need for invasive tests in hospital settings.

Wearable AI System Tracks Tiny Sensors for Precise Diagnosis
A wearable system that can locate ingestibles in the gut with millimeter resolution. Image Credit: Khan Lab at University of Southern California

Ingestibles are like Fitbits for the gut, but tracking them once swallowed has been a significant challenge.

Yasser Khan, Assistant Professor, Department of Electrical and Computer Engineering, University of Southern California

When bacteria in the intestines break down food, gas is produced that can provide information about an individual's health. To evaluate GI tract gases, physicians utilize indirect procedures, like breath testing and stool analysis, or direct ones, such as intestinal tube collection and flatus collection.

Ingestible capsules—devices that a user swallows—offer a promising alternative, but no such technologies have been developed yet for precise gas sensing.

To address this issue, Khan and associates created a wearable coil system that may be worn beneath a t-shirt or other piece of clothing. Once an ingestible pill has been taken, the coil's magnetic field interacts with sensors within it.

AI examines the signals the tablet receives and, in less than a few mm, determines the device's location in the stomach. Using the device's optical gas-sensing membranes, the system tracks 3D real-time amounts of ammonia, a proxy for a bacteria linked with ulcers and gastric cancer.

The wearable coil can be used anywhere, unlike earlier attempts that relied on large desktop coils to follow edibles as they pass through the digestive system. Beyond monitoring GI tract gasses, the technique may also be utilized to diagnose Crohn's disease-related intestinal inflammation and target specific areas of the gut with medication.

The researchers evaluated the device's effectiveness using a range of GI tract-mimicking media, such as liquids that mimic the fluids found in the stomach and intestines and a synthetic bovine intestine.

During these tests, the device demonstrated its ability to pinpoint its location and measure levels of oxygen and ammonia gases. Any ingestible device can utilize the technology we have developed.

Yasser Khan, Assistant Professor, Department of Electrical and Computer Engineering, University of Southern California

Khan says that the device needs further improvement, such as making it smaller and with reduced power consumption. After further refinement, Khan and associates intend to test the gadget on pigs to examine its efficacy and safety in a creature whose biology is similar to that of humans.

Successful outcomes from these trials will bring the device nearer to readiness for human clinical trials. We are optimistic about the practicality of the system and believe it will soon be applicable for use in humans.

Yasser Khan, Assistant Professor, Department of Electrical and Computer Engineering, University of Southern California

Journal Reference:

Abdigazy, A., et al. (2024) 3D gas mapping in the gut with AI-enabled ingestible and wearable electronics. Cell Reports Physical Science. doi.org/10.1016/j.xcrp.2024.101990

Tell Us What You Think

Do you have a review, update or anything you would like to add to this news story?

Leave your feedback
Your comment type
Submit

While we only use edited and approved content for Azthena answers, it may on occasions provide incorrect responses. Please confirm any data provided with the related suppliers or authors. We do not provide medical advice, if you search for medical information you must always consult a medical professional before acting on any information provided.

Your questions, but not your email details will be shared with OpenAI and retained for 30 days in accordance with their privacy principles.

Please do not ask questions that use sensitive or confidential information.

Read the full Terms & Conditions.