Current smartphones incorporate multi-modal sensors that are able to collect meta-data that help infer when drinking occasions are either occurring or going to occur, researchers say.
Researchers at the University of Pittsburgh are finding ways by which digital interventions can help people make smarter drinking decisions, leading to reduced alcohol-related injuries and illness.
Six years ago, Brian P. Suffoletto, assistant professor of emergency medicine at the University of Pittsburgh, and his colleagues found that using text messaging to collect drinking data and to offer immediate feedback and support to young adults discharged from emergency rooms reduced the number of drinks they consumed and the number of binge-drinking episodes.
Now, the team has expanded on that research to better understand how communication technology can help people reduce their drinking.
"We wanted to interact with individuals when drinking decisions were actually being made. We could either frequently query individuals about their drinking-related activities, which would quickly become annoying, or sense when an individual is drinking, and interact with them only when pertinent," Suffoletto said.
He explained that current smartphones incorporate multi-modal sensors that are able to collect meta-data that help infer when drinking occasions are either occurring or going to occur. “For example, individuals may exhibit impaired psychomotor function due to alcohol, which results in more typing misspellings, which can be sensed by phones,” he said.
Then, machine learning models use time-based features (i.e. time of day, day of week), motion-based features (number of activities, accelerations, rotations), device-usage features (screen interactions, screen unlocks, typing deletions/insertions) and communication-based features (outgoing calls, missed calls, correspondents) to predict binge drinking with 94% accuracy. “To our knowledge, this is the first time that phone sensors have been used to predict drinking occasions,” he said.
“We found that continuous phone-sensor data can be reliably collected from individuals,” said Suffoletto. “This sensor data can be useful in inferring activities associated with drinking occasions. However, the ability to predict drinking occasions before they actually occur, and the effectiveness of individualised digital interventions that use real-time sensor data to trigger intervention delivery, have yet to be determined.”
Suffoletto is aware of ‘Big Brother’ concerns. “Although current technological innovations offer unprecedented opportunities to advance the science of alcohol treatment and prevention,” he admitted, “they also push the boundaries of data privacy. Our work should prompt scientists to discuss and debate this balance.”