MIT Developing Ingestible Sensor Capable of Targeting Drug Administration

By DocWire News Editors - Last Updated: April 11, 2023

Researchers at MIT have been working on developing a new ingestible implant that may help drugs target specific parts of the body. The device, ReMix, utilizes an “in-body GPS” that aims to help make diagnoses and guide the administration of drugs. The researchers state that their goal is to provide affordable patient care that less invasive and time consuming than previous methods.

Advertisement

With much of their recent research being focused on AI and deep learning, ReMix adds to the growing body of innovative medical technology research. The device, being developed with help from clinicians at Massachusetts General Hospital, uses complex algorithms to spot the location of ingestible implants via wireless signals.

Dina Katabi, MIT professor, has used these signals to detect subtle movements and vital signs from afar. MIT Computer Science & Artificial Intelligence Laboratory (CSAIL) researchers have found the device to be effective in animal studies, with the device being tracked within a few centimeters. The goal is for the device to be used similarly in humans, revolutionizing drug therapy.

In testing the device, researchers implanted a small sensor in the animals and tracked it with a wireless device. Using an algorithm, the researchers then tracked the device, which does not itself release a signal. The sensor simply reflects the signal sent at it by the wireless device.

The researchers claim that the challenge lies within the signal bouncing off many different body parts, more so off the skin than the sensor itself. To combat this issue, the researchers have developed a semiconductor that is capable of combining the signals and filtering out the unwanted frequencies.

Going forward, the researchers hope to combine these wireless data with other data, such as MRI radiographs, to enhance the systems accuracy. They also plan to do further research to determine how the algorithm can account for discrepancies in patient physiologies.

“We want a model that’s technically feasible, while still complex enough to accurately represent the human body,” said Deepak Vasisht, lead author of the paper on MIT’s ReMix research. “If we want to use this technology on actual cancer patients one day, it will have to come from better modeling a person’s physical structure.”

Source: Healthcare IT News

Advertisement