2 companies apply Google's new standalone AI chips to patient monitoring, colonoscopy

Google Coral
Google's Coral line of chips and boards are designed to run AI and machine learning models locally, after they've been trained, in a wide range of connected devices. (Image: Google)

Google has been no stranger to the industry’s rush to bring artificial intelligence software to healthcare—with programs in diabetic retinopathy, electronic patient records and cancer-seeking CT scans—but now they’re looking to supply the hardware, too. 

Earlier this year, the tech giant unveiled plans for a specialized line of small-scale computer chips, circuit boards and cameras tailored for developers—designed specifically to run AI programs locally and within a mass-produced product. Now, Google’s Coral venture is out of beta, and two companies are looking to bring the devices into the hospital and home-care settings.   

The Orlando, Florida-based care.ai is using Google’s hardware to develop an autonomous monitoring platform that helps detect patient falls and other dangers. 

Webinar

How ICON, Lotus, and Bioforum are Improving Study Efficiency with a Modern EDC

CROs are often at the forefront of adopting new technologies to make clinical trials more efficient. Hear how ICON, Lotus Clinical Research, and Bioforum are speeding database builds and automating reporting tasks for data management.

By employing cameras and computer vision analysis, the onboard AI is designed to interpret the data on its own and notify caregivers of any potential situations. It does not transmit any video, maintaining both the person’s privacy and compliance with HIPAA regulations.

This can include whether someone is at risk for developing pressure ulcers in a hospital bed, or if a person with dementia leaves their room or another area. The wall-mounted system is designed to have no burden on patients with no wearable devices, while lessening the workload and attention required by staff or caregivers in both home and hospital settings. 

RELATED: Google, Mayo Clinic team up on patient data and AI healthcare research

Care.ai's automated camera. (Image: care.ai)

“We believe we are on the cusp of an amazing revolution for AI in healthcare and are proud to partner with care.ai to witness it becoming a reality,” said Billy Rutledge, director of Coral. “By combining care.ai’s AI-powered autonomous monitoring platform with our edge computing framework, we can address some of the most demanding challenges in healthcare in a way that’s never been accomplished before this collaboration.”

The devices are currently being piloted with Consulate Health Care, a provider of rehabilitation and long-term care for the elderly, with about 140 centers in the U.S.

“What the team at care.ai has put together is truly ground-breaking,” said Consulate CIO Mark Crandall. "This is the first and only autonomous monitoring solution in healthcare that can truly transform an ordinary room into a self-aware room."

RELATED: Special Report—The top AI lighthouse projects to watch in biopharma 

Meanwhile in San Francisco, Virgo Surgical Video Solutions aims to enlist Coral’s AI chips to quickly spot polyps and potential cases of colon cancer.

With gastroenterologists performing about 15 million colonoscopies annually in the U.S., some precancerous polyps go undetected. Virgo is developing a small, portable video-capture device that plugs into a standard endoscopy system to provide a second set of eyes. 

While the company does not yet have a timeline for clinical trials of the device, a demo in a simulated colon showed how the system outlines and highlights polyps whenever they’re in view of the endoscope in real time.

“We're also developing detection and classification models beyond just polyp detection, for things like Barrett's esophagus, instrument detection and technique analysis,” said Virgo CEO and co-founder Matt Schwartz.

Suggested Articles

AstraZeneca is linking up with DeepMatter, a big data firm focused on achieving reproducibility in chemistry, to help improve its compound synthesis.

The $210 million fund began life by leading a $17 million series A round in Quellis Biosciences.

The nine-story building will house Amgen’s Bay Area employees when it opens early in 2022.