On January 9th, a team led by assistant Professor Jacob Sunshine of the University of Washington published results surrounding a new smartphone application developed to detect opioid overdoses and facilitate timely medical intervention.
The current opioid crisis in the United States has resulted in a record two-thirds of 72,000 drug overdose deaths in 2017 being associated with substances such as fentanyl, a widely used pain medication and synthetic opioid. Therefore, research into modern technology that could mitigate the consequences of overdoses is more significant than ever.
When administered in excess, opioids can cause a rapid cessation of breathing and respiratory failure. The application takes advantage of such physiological effects, using sonar to detect changes in breathing that are indicative of a drug overdose, even when the individual is up to 3 feet away from their device.
Professor Sunshine explained that “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 therefore uses two precursors to assess opioid overdose: a drop in breathing rate to 7 breaths per minute or less, as well as interrupted breathing.
Specifically, the researchers wanted to address the issue of overdoses occurring in at-risk individuals in unmonitored places.
“The big challenge with the opioid epidemic is people experiencing overdoses in unwitnessed environments, leading them to die,” Sunshine said. “We know how to identify the problem and how to treat it, but the problem has been connecting those two in a timely fashion.”
Once an overdose is detected, the patient’s phone can create a connection to a friend or emergency services so that naloxone, a drug commonly used to reverse the effects of an opioid overdose, can be provided.
The researchers explained that patients struggling with addiction through recreational use of opioids and individuals experiencing effects following prescribed therapy for chronic pain would be treated slightly differently by the application.
“For the former group, we want to add functionality that connects patients with medication-assisted therapy, naloxone, counselling, additional help,” Sunshine said. “For those who may not have a primary care physician, we want to have a way that connects them to health services. This could be something of interest for extremely at-risk populations, including pregnant women with opioid use disorder (OUD).”
Lead author Rajalakshmi Nandakumar additionally noted that “People aren’t always perfectly still while they’re injecting drugs, so we want to still be able to track their breathing as they’re moving around. We can also look for characteristic motions during opioid overdose, like if someone’s head slumps or nods off.”
The algorithm that is the basis of the application was tested at the Insite supervised injection facility in Vancouver, Canada.
Participants were required to prepare their drugs as normal, whilst monitors placed on their chests tracked their breathing rates prior to and following injection.
Of the 94 individuals who took part in the procedure, 47 were found to have a breathing rate of seven breaths per minute or less, 49 stopped breathing for a notable period of time, and 2 experienced an overdose that required medical intervention.
On average, the algorithm correctly identified symptoms of an overdose in 90% of cases.
Further testing was performed in conjunction with the anaesthesiology team at the University of Washington medical centre.
“When patients undergo anaesthesia, they experience much of the same physiology that people experience when they’re having an overdose,” Sunshine said. “Nothing happens when people experience this event in the operating room because they’re receiving oxygen and they are under the care of an anaesthesiology team. But this is a unique environment to capture difficult-to-reproduce data to help further refine the algorithms for what it looks like when someone has an acute overdose.”
In order to ‘simulate’ the event of an overdose, healthy participants that were previously scheduled for surgeries received anaesthesia and were simultaneously monitored by the application.
In this case, the algorithm correctly identified 19 out of 20 simulated overdoses.
The app is estimated to be released in around eight months, once it has received approval from the US Food and Drug Administration (FDA).
In the current climate of unprecedented deaths occurring through opioid use in the United States, the potential of this application for increasing the likelihood of overdoses being identified and treated as efficiently as possible is of great value.
Professor Sunshine is optimistic about the benefit that the app will have in wider society.
“There’s two known things: What overdose looks like — the respiratory physiology of it — it’s all known. The treatment for it; it’s all known. It’s just connecting those two in a timely fashion that is needed, and that’s the missing link that this tech is trying to solve.”
Image credit: Nathan Forget via Flickr