Skip to Content

The Networked Pill

A new information system records what pills do to the body.

A system that monitors pill taking and its effects is being engineered by a Silicon Valley startup. The technology consists of pills that report when they’ve been taken, and sensors that monitor the body’s responses.

Smart pill: Proteus’s system consists of a pill that contains an “ingestible event marker” powered by a thin-film battery. Its electrical signal is picked up by sensors on a patch worn either on or just under the skin. The data are sent to a caregiver who looks for correlations between use of the medication and the patient’s condition.

The company behind the technology, Proteus Biomedical, of Redwood City, CA, calls its technology the Raisin system. George Savage, Proteus’s cofounder and a former ER physician, says that the company was motivated by the fact that so many medical problems stem from drug compliance problems. According to Savage, 40 percent of hospital readmissions for heart failure happen because patients fail to take their medications properly.

Even when a regimen is followed, it may not be the best regimen. According to Leslie Saxon, a cardiologist at the University of Southern California, who works as a consultant for Proteus, the dosages of drugs used for heart failure are derived from large clinical trials and may not meet a particular patient’s needs. “Imagine a situation where drug ingestion is tracked, and heart pressure before, immediately after, and later are known,” says Saxon. “That represents real, individualized, tailored drug therapy.”

In the Raisin system, each pill contains an “ingestible event marker” (IEM). The IEM consists of a sand-grain-size microchip with a thin-film battery that is activated on ingestion, as it is exposed to water. The battery, Proteus says, is nontoxic because it is made from materials similar to those in a vitamin pill. Once swallowed, the IEM sends through the body’s tissues a high-frequency electrical current that’s modulated in such a way that it provides a unique marker of the pill. It’s not an RFID technology: it uses the conductive tissues of the body to conduct the signal, rather than a radio, and the signal is confined within the body. Mark Zdeblick, the company’s CTO, says that the IEMs could cost less than a penny each when manufactured in volume.

The electrical current is picked up and logged by a receiver on a patch placed on the patient’s chest or abdomen, or placed underneath the skin as a subcutaneous insert. The receiver also contains sensors that monitor physiological parameters such as heart rate, respiration, and bodily movement. Heart rate is monitored by detecting the electrical activity of the heart; respiration is monitored by detecting changes in the impedance of the electrodes as the chest expands and contracts; activity is monitored with a miniature accelerometer, similar to the ones in iPhones. Combining the parameters can reveal behavioral measures such as sleep patterns.

Monitoring chemistry-based parameters such as blood glucose with subcutaneously implanted chips is possible in principle, says Ben Costello, Proteus’s vice president of sensor development, although it’s more challenging to do technologically. For the present, the company is focusing on biophysical parameters that can be measured on top of the skin.

Once collected, the data are uploaded to a server via a cell phone or a PC for a caregiver’s scrutiny. The patient can then be advised to adjust dosages or change medications.

Similar technologies are being developed elsewhere. For example, the MagneTrace system, designed by engineers at the Georgia Institute of Technology, records when magnetized pills pass through a patient’s esophagus and sends the information to a computer. The Raisin system takes the additional step of incorporating on- and in-body sensors that correlate pill taking with the body’s physiological responses.

Privacy issues are an obvious concern with a technology such as Raisin. Savage says that because the pill’s signal is transmitted electrically through skin tissues rather than by radio, it couldn’t be picked up remotely by, say, a company wanting to know what medications its prospective employees are taking. Proteus adds that security safeguards would be used to protect transmitted data.

And because the signal doesn’t go beyond the skin, the pills in one person’s stomach wouldn’t trigger the receiver in another person’s body. Proteus says that even if two users came into physical contact, the conduction of electricity from one person’s skin to the other’s would be too weak for inadvertent data exchange to happen.

While acknowledging that privacy concerns need to be addressed, Savage offers an optimistic vision in which the technology enhances community support by enabling the sharing of information. As an example, he points out that people managing mental illness usually want to stick to their regimens, but the nature of the problem makes it difficult for them to do so. The Raisin system would alert relatives if the patient misses a dose.

The system would also eliminate the need for direct observed therapy, he suggests, in which patients with contagious illnesses such as tuberculosis are required to be observed by a health-care provider as they take each dose of their medication. The Raisin system would achieve the same goal with less intrusion.

“If clinical trials show that this complicated technology is safe and effective, it has the potential to be very useful in monitoring patients’ adherence,” says Olga Klibanov, an assistant professor at the Temple University School of Pharmacy, who works with inner-city HIV patients and was not involved in research on the Raisin. “Data that can be collected with this tool would likely be useful–not only in a trial setting, but also to clinicians in taking care of patients.”

So far, Proteus has raised $60 million from investors including the Carlyle Group and Kaiser Permanente Ventures, and it has filed more than 250 patents. Clinical trials with human users began earlier this year, to test the functionality of the IEM and sensors. The company hopes to have the system on the market in 2011.

Keep Reading

Most Popular

Large language models can do jaw-dropping things. But nobody knows exactly why.

And that's a problem. Figuring it out is one of the biggest scientific puzzles of our time and a crucial step towards controlling more powerful future models.

OpenAI teases an amazing new generative video model called Sora

The firm is sharing Sora with a small group of safety testers but the rest of us will have to wait to learn more.

Google’s Gemini is now in everything. Here’s how you can try it out.

Gmail, Docs, and more will now come with Gemini baked in. But Europeans will have to wait before they can download the app.

This baby with a head camera helped teach an AI how kids learn language

A neural network trained on the experiences of a single young child managed to learn one of the core components of language: how to match words to the objects they represent.

Stay connected

Illustration by Rose Wong

Get the latest updates from
MIT Technology Review

Discover special offers, top stories, upcoming events, and more.

Thank you for submitting your email!

Explore more newsletters

It looks like something went wrong.

We’re having trouble saving your preferences. Try refreshing this page and updating them one more time. If you continue to get this message, reach out to us at customer-service@technologyreview.com with a list of newsletters you’d like to receive.