Smartphone App Detects Opioid Overdose

Researchers at the University of Washington have developed a smartphone app that can detect if someone is experiencing an opioid overdose. The app uses sonar to monitor the breathing rate of a user, which it can do from up to three feet away, to assess if someone is experiencing an overdose. So far, the technology has accurately predicted overdoses 90% of the time, and if it detects an overdose it can automatically connect the user to emergency services.

It has been estimated that 115 opioid users die daily from opioid overdose in the U.S., which starkly illustrates the current opioid crisis. A drug user experiencing an overdose will breathe slowly, or stop breathing altogether. Emergency services can administer a drug called naloxone  (Narcan), which can stop the symptoms of overdose and save someone’s life if administered in time.

However, a drug user experiencing an overdose may not be capable of calling someone and getting help. In an effort to reduce the death toll associated with opioid overdose, researchers have developed a smartphone app called Second Chance.



“The idea is that people can use the app during opioid use so that if they overdose, the phone can potentially connect them to a friend or emergency services to provide naloxone,” said Shyam Gollakota, a researcher involved in the study. “Here we show that we have created an algorithm for a smartphone that is capable of detecting overdoses by monitoring how someone’s breathing changes before and after opioid use.”

The app imperceptibly bounces sound waves off a drug user’s chest and then analyzes them when they return, to assess the breathing rate. “We’re looking for two main precursors to opioid overdose: when a person stops breathing, or when a person’s breathing rate is seven breaths per minute or lower,” said Dr. Jacob Sunshine, another researcher involved in the study. “Less than eight breaths per minute is a common cutoff point in a hospital that would trigger people to go to the bedside and make sure a patient is OK.” The app also assesses how users are moving, so if they are slumping or have nodded off this could also trigger an alarm.

So far, the researchers have tested the app at an injection site and in volunteers (who were already undergoing an elective surgery) who underwent anesthesia to create a simulated overdose. The app correctly predicted the “overdose” in 19 out of 20 volunteers. “When the app detects decreased or absent breathing, we’d like it to send an alarm asking the person to interact with it,” said Gollakota said. “Then if the person fails to interact with it, that’s when we say: ‘OK this is a stage where we need to alert someone,’ and the phone can contact someone with naloxone.”