Dr. Honggang Wang, chair of the Computer Science and Engineering Department at the Katz School, presented his latest research in June at an IEEE conference on Connected Health: Applications, Systems and Engineering Technologies.

By Dave DeFusco

A Katz School researcher and several colleagues are developing an AI-powered wearable device that can monitor illicit drug use in individuals with substance use disorder.

In a research paper, “Precision Polysubstance Use Episode Detection in Wearable Biosensor Data Streams,” Dr. Honggang Wang, chair of the Katz School’s Computer Science and Engineering Department, describes a method called RP-STREAM, which is an algorithm that can identify when an individual is using drugs by analyzing data collected from a wearable device. 

To develop the model, the researchers collected data from 15 people who had used cocaine and were fitted with a wearable biosensor called Affectiva Q, which can measure various physiological changes such as electrodermal activity, physical activity and body temperature. To figure out when these people used cocaine, the researchers evaluated patient notes, urine tests and data from the device. 

“When it comes to detecting drug use, some studies have been successful in finding out when people use drugs, but they usually look at big chunks of time,” said Dr. Wang. “This new method is different because it can figure out when someone uses drugs in smaller timeframes. It’s like looking at a movie frame by frame instead of the whole movie at once.” 

Dr. Wang presented the team’s findings at the Institute of Electrical and Electronics Engineers (IEEE) International Conference on Connected Health: Applications, Systems and Engineering Technologies, with colleagues Joshua Rumbut and Hua Fang of the University of Massachusetts Dartmouth and University of Massachusetts Chan Medical School, and Edward Boyer of Ohio State University and Harvard Medical School.

RP-STREAM, or Real-time Precision Pattern Recognition for Polysubstance Use Episode Detection in Wearable Biosensor Data Streams, uses a set of rules derived from previous studies to differentiate between substances and identify substance-use episodes accurately. The algorithm includes an intelligent mechanism for setting the threshold at which an observation is considered abnormal, which helps in distinguishing substance use episodes from other anomalies in the biosensor data. It can also recognize substance use occurrences that vary in length and over many days, making it suitable for real-world scenarios where substance-use patterns aren’t fixed. 

“Presently, the usual ways to check if someone relapsed aren’t very good,” said Dr. Wang. “They test things like urine or blood, which can’t tell us much about when it happened. People can also lie or forget about it.”

During the experiments, RP-STREAM was able to find and identify when people used cocaine and cannabis, and the episodes were usually about 53 minutes in duration on average. They also compared RP-STREAM to another method and found that RP-STREAM was better at not giving false alarms, meaning it didn’t mistakenly detect substance abuse.

“We want to keep working on this method to make it better at recognizing substance use for new participants,” said Dr. Wang. “This is important because it can help us understand what leads to substance use and maybe even predict when someone might relapse. We can also study how people’s tolerance to drugs changes over time in real-life situations, which will help us understand why people use drugs again and how to help them stop.”