Consumer devices differentiate users with mild Alzheimer’s, cognitive impairment
Researchers from Apple, Eli Lilly and Evidation Health have shown in a feasibility study that wearable devices could help to identify those people beginning to experience cognitive decline.
Researchers from Apple, Eli Lilly and Evidation Health have shown in a feasibility study that wearable devices could help to identify those people beginning to experience cognitive decline.
A paper presented on Thursday at the Association for Computing Machinery’s KDD Conference in Anchorage, Alaska, offers evidence that consumer-grade smart devices can provide remote monitoring of symptoms related to cognitive impairment.
The 12-week exploratory study, conducted by Evidation Health on behalf of Eli Lilly and Apple, monitored 31 people with cognitive impairment and 82 without cognitive impairment. Researchers collected a total of 16 terabytes of data, including passively derived sensor data from the smart devices, questionnaires about mood and energy, as well as simple assessment activities on a digital app.
“We describe how careful data unification, time-alignment and imputation techniques can handle missing data rates inherent in real-world settings and ultimately show utility of these disparate data in differentiating symptomatics from healthy controls based on features computed purely from device data,” state the authors of the Lilly Exploratory Digital Assessment Study.
Also See: Machine learning helps to identify early signs of Alzheimer’s
All study participants were provided with an iPhone 7 plus, an Apple Watch Series 2, a 10.5-inch iPad Pro with a smart keyboard and a Beddit sleep-monitoring device, along with apps to collect all sensor and app-usage events.
“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,” said first author Nikki Marinsek, a data scientist at Evidation Health, which created a secure platform to obtain study participants’ consent to collect and analyze the data.
“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,” added Marinsek. “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.”
What the study found was that symptomatic participants tended to have slower typing than healthy controls, exhibited less routine behavior compared with healthy controls, and received fewer text messages in total (and per day) and had a lower interquartile range of daily outgoing messages.
In addition, symptomatic individuals spent more total time in the Clock app than healthy controls, were more likely to view or access Siri’s app suggestions, and answered the daily one-question surveys less often than healthy controls and—when they did respond—tended to respond later in the day.
“While further research is needed, the study findings provide important insight into the potential benefits of wearable devices in identifying chronic health conditions such as MCI, Alzheimer's disease and dementia,” commented Divakar Ramakrishnan, Lilly’s chief digital officer. “These findings could inform subsequent research that may eventually lead to early screening or detection tools for neurodegenerative conditions.
A paper presented on Thursday at the Association for Computing Machinery’s KDD Conference in Anchorage, Alaska, offers evidence that consumer-grade smart devices can provide remote monitoring of symptoms related to cognitive impairment.
The 12-week exploratory study, conducted by Evidation Health on behalf of Eli Lilly and Apple, monitored 31 people with cognitive impairment and 82 without cognitive impairment. Researchers collected a total of 16 terabytes of data, including passively derived sensor data from the smart devices, questionnaires about mood and energy, as well as simple assessment activities on a digital app.
“We describe how careful data unification, time-alignment and imputation techniques can handle missing data rates inherent in real-world settings and ultimately show utility of these disparate data in differentiating symptomatics from healthy controls based on features computed purely from device data,” state the authors of the Lilly Exploratory Digital Assessment Study.
Also See: Machine learning helps to identify early signs of Alzheimer’s
All study participants were provided with an iPhone 7 plus, an Apple Watch Series 2, a 10.5-inch iPad Pro with a smart keyboard and a Beddit sleep-monitoring device, along with apps to collect all sensor and app-usage events.
“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,” said first author Nikki Marinsek, a data scientist at Evidation Health, which created a secure platform to obtain study participants’ consent to collect and analyze the data.
“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,” added Marinsek. “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.”
What the study found was that symptomatic participants tended to have slower typing than healthy controls, exhibited less routine behavior compared with healthy controls, and received fewer text messages in total (and per day) and had a lower interquartile range of daily outgoing messages.
In addition, symptomatic individuals spent more total time in the Clock app than healthy controls, were more likely to view or access Siri’s app suggestions, and answered the daily one-question surveys less often than healthy controls and—when they did respond—tended to respond later in the day.
“While further research is needed, the study findings provide important insight into the potential benefits of wearable devices in identifying chronic health conditions such as MCI, Alzheimer's disease and dementia,” commented Divakar Ramakrishnan, Lilly’s chief digital officer. “These findings could inform subsequent research that may eventually lead to early screening or detection tools for neurodegenerative conditions.
More for you
Loading data for hdm_tax_topic #better-outcomes...