With smartphones, tablets and other connected devices becoming ubiquitous, the data they gather from a person’s day-to-day life can clue us in to not only patterns but changes as well—including the subtle signs of encroaching Alzheimer’s disease.
Initial results from a study by Eli Lilly & Co., Apple and Evidation Health showed that a combination of consumer devices and mobile apps could potentially help spot people with mild cognitive impairment or mild dementia related to Alzheimer’s.
Using iPhones, Apple Watches and iPads, as well as Apple’s Beddit sleep monitor, researchers were able to take the continuously varying signals and quantize them into the nearly imperceptible symptoms of cognitive and behavioral differences.
Like this story? Subscribe to FierceBiotech!
Biopharma is a fast-growing world where big ideas come along every day. Our subscribers rely on FierceBiotech as their must-read source for the latest news, analysis and data in the world of biotech and pharma R&D. Sign up today to get biotech news and updates delivered to your inbox and read on the go.
Those digital biomarkers, once validated, could also be used to monitor the progression of symptoms of people diagnosed with Alzheimer’s and test the efficacy of treatments. The exploratory results were presented at the Association for Computing Machinery's conference in Anchorage, Alaska.
Evidation, one of last year’s Fierce 15 winners, built a study platform to consent, collect and analyze at least 16 terabytes of data, gathered from 113 participants over 12 weeks in real-world settings.
RELATED: Evidation unveils first results from 10,000-strong virtual chronic pain study
That comprised passive sensor data, questionnaires about mood and energy, and measurements from simple assessment activities—such as motor skill tests, like rhythmically tapping the screen as fast as possible or dragging shapes onto each other, as well as reading and typing tasks.
"Over the past few years, we've seen how data and insights derived from wearables and mobile consumer devices have enabled people living with health conditions, along with their clinicians, to better monitor their health," first author Nikki Marinsek, a data scientist at Evidation, said in a statement.
RELATED: FierceMedTech's 2018 Fierce 15 | Evidation Health
"We know that insights from smart devices and digital applications can lead to improved health outcomes, but we don't yet know how those resources can be used to identify and accelerate diagnoses,” Marinsek said. “The results of the trial set the groundwork for future research that may be able to help identify people with neurodegenerative conditions earlier than ever before."
In the study, symptomatic participants tended to type more slowly and showed less routine behavior—namely, in the range of times associated with picking up and putting down their phones for the first and last times each day. They also sent fewer text messages throughout their day and spent more time in “helper apps,” such as the phone’s clock app and Siri’s suggestions.
Eli Lilly hopes this research will eventually lead to early screening and detection tools for chronic and neurodegenerative conditions, according to the Big Pharma’s chief digital officer, Divakar Ramakrishnan, Ph.D.
Last December, Lilly and Evidation expanded their digital biomarker collaboration into a multiyear project, with the goal of mining everyday data for applications across several disease areas. Currently, Evidation’s platform is being used to gather information from continuous glucose monitors and insulin pumps, to be put toward Lilly’s development of a connected diabetes product ecosystem.
Meanwhile, Evidation has been completing years of work in analyzing voice and speech patterns for signs of cognitive decline, under a DARPA grant with help from MIT, Boston University and the long-term Framingham study.
"With further study, we may be able to screen people at high risk or detect dementia and Alzheimer's earlier with the devices we use in our everyday lives," said Evidation co-founder and President Christine Lemke. "These early findings suggest the potential of novel digital measures that are based on data generated and controlled by individuals."