FDA clears edible medical sensor for human consumption

System in a pill communicates via skin patch


The US Food and Drug Administration (FDA) has officially cleared edible computers to be used in medical applications for monitoring patient health.

After four years of discussions, Proteus Digital has received approval for its Ingestion Event Marker, a silicon sensor about 1mm square that is encased in a pill and is meant to be swallowed. Once stomach acid reaches the sensor it acts as an electrolyte, generating 1-2 volts of power between the copper salt cathode and a magnesium anode.

While it carries no aerial itself, the chip emits a tone that can be picked up on a patch worn on the outside of the body. The patch then relays the sensor's data (along with heart rate and body movement of the patent) to a mobile phone with the right software application installed.

The sensor doesn't last long for sustained operation and is passed through the gut "like high-fiber food," according to the manufacturer. "We are very much looking forward to bringing the benefits of our ingestible sensor to the American public in the form of innovative product offerings," said Dr. George M. Savage, co-founder and chief medical officer at Proteus Digital in a statement.

Before you start getting images of a Fantastic Voyage scenario, the current technology that has been approved is very basic. The sensor is designed to ensure that medication is taken correctly and on time by providing a log of ingestion, and we're still years away from the medical robots that can maneuver through the body and perform repairs, as envisioned by some so-called technology gurus.

Nevertheless, the FDA approval is an important step in allowing the use of wetware, or implantable computers, to improve human health. The EU has already approved the Proteus Digital designs and certified them as safe for human use. With the FDA decision, the company now has access to the most expensive healthcare market in the world.

"The FDA validation represents a major milestone in digital medicine. Directly digitizing pills, for the first time, in conjunction with our wireless infrastructure, may prove to be the new standard for influencing medication adherence and significantly aid chronic disease management," said Dr. Eric Topol, professor of genomics at The Scripps Research Institute. ®

Similar topics

Narrower topics


Other stories you might like

  • Nuance helps launch healthcare AI industry group
    Microsoft embraces Nuance to deepen its healthcare connections

    Microsoft's purchase of AI company Nuance got Redmond's foot in the door of the healthcare industry, and it's widening the opening as Nuance helps form an industry group to explore applications of AI in hospitals and clinics.

    Nuance and The Health Management Academy – a peer group made up of healthcare executives from the top 150 US hospital systems, announced on Wednesday the formation of The AI Collaborative. The Collaborative will specifically consist of Academy members from hospital groups that have already deployed or are deploying AI and ML systems in healthcare settings. 

    AI has a wide range of applications in the healthcare industry, for many of which Nuance already has a product. One of its most well known is speech recognition and conversational AI platform Dragon Naturally Speaking, which is used by clinicians for speech recognition tasks like note taking and session transcripts. 

    Continue reading
  • Can AI transformer models help design drugs and treat incurable diseases?
    From protein prediction to drug generation, neural networks are revolutionizing medication

    Special report AI can study chemical molecules in ways scientists can't comprehend, automatically predicting complex protein structures and designing new drugs, despite having no real understanding of science.

    The power to design new drugs at scale is no longer limited to Big Pharma. Startups armed with the right algorithms, data, and compute can invent tens of thousands of molecules in just a few hours. New machine learning architectures, including transformers, are automating parts of the design process, helping scientists develop new drugs for difficult diseases like Alzheimer's, cancer, or rare genetic conditions.

    In 2017, researchers at Google came up with a method to build increasingly bigger and more powerful neural networks. Today, transformer-based models are behind some of the largest AI systems and typically learn patterns from vast amounts of text. They're versatile and can process different forms of language from code to ancient scripts scribbled thousands of years ago.

    Continue reading
  • Watchdog rubber-stamps cavity-detecting neural network for dentists
    Ain't that the tooth?

    VideaHealth, a dental AI startup spun out of MIT and Harvard, has received FDA approval in the US to commercialize its cavity-detection algorithm for clinical use. 

    The software is designed to help dentists look for signs of tooth decay in X-ray scans. Officials granted Videa 510(k) clearance, meaning it has successfully demonstrated its product can be marketed as safe and effective for human use and functions similarly to an approved device. 

    The algorithm demonstrated it could reduce the number of caries missed by dentists by up to 43 percent, and slash dental lesion detection errors by 15 percent on average in the FDA trial, the biz said.

    Continue reading

Biting the hand that feeds IT © 1998–2022