AI wearables for remote patient monitoring
Real-time data delivery in remote patient monitoring
David Ebert, Chief AI and Data Science Officer University of ArizonaRPM also uses the term “big-picture view” to describe what AI and wearables can do. He says the real power comes from the processing capabilities built into today’s wearables and implantable devices.
Several years ago, a patient with a pacemaker needed a purpose-built home monitor. Now, pacemakers contain Bluetooth sensors that connect to smartphones, collect data and send notifications to the patient’s care team.
“We’re taking advantage of the capabilities that people are bringing to the chip,” Ebert says. “What can we do Machine Learning and Predictive Analytics On the device.”
There are two keys to implementing this. There is an increasing focus on the efficiency of AI models. Data compression will save bandwidth, and the ability to “take out signals” will make the device’s output more valuable to physicians who do not have time to look at the raw data.
“We don’t want the AI model to drain its battery or take too long processing time,” says Ebert. “We don’t want bandwidth challenges that increase the digital divide.”
The second important step is Integrating streams of data and insights from devices into electronic health records and clinical warning systems. Otherwise, he notes, clinics would need additional equipment and necessary resources to set it up.
discover: Here are the wearable technology trends that are shaping health care.
How to Implement and Scale RPM with AI and Wearables
Mahajan says ease of integration is important. “Solutions that are effective and are adopted as seamlessly as possible do not create unnecessary work for physicians.”
Getting this right may require advanced data ingestion pipelines that can accommodate high-frequency data streams, notes Mahajan, as well as tools that normalize data as it is collected. “Organizations have to shift from systems built for episodes to systems built for continuous data,” he says.
Ebert says another idea is to use tools that have been developed From application programming interfaces to agentic AI interfaces. This way, devices can be deployed, monitored, and updated using software rather than specialized hardware, which comes with upfront costs and the need for specialized skills that hinder adoption. “This is a game changer for rural hospitals,” he says.
Another common barrier is single-use predictive models or clinical decision support tools, Mahajan says: “Health systems are not ready to take on 100 different tools. They’re looking for platforms or systems.”
Of course, there is also The concern is that AI models will replace physicians. That’s not an issue for Dr. Sairam Parthasarathy, director of the Center for Sleep and Circadian Sciences at the University of Arizona.
He says licensed providers are too few and “there are too many people who need our help. People don’t have to be sick before we can give them health advice,” and insights from data and AI models from wearable devices can ensure that won’t happen.
