Smartphone Sensors Can Detect Cannabis Intoxication, Study Says
Want to listen to this article for FREE?
Complete the form below to unlock access to ALL audio articles.
The sensors in an ordinary smartphone can help identify a cannabis high, according to preliminary research.
Published in Drug and Alcohol Dependence, the study found that data obtained via a phone’s GPS and accelerometer could help determine whether the phone’s owner was high or not with 90 percent accuracy.
Phone me when you’re high
To make their findings, the researchers from the Rutgers Institute for Health recruited 57 young cannabis consumers aged between 18 and 25 from Pittsburgh, Pennsylvania.
All participants had an app installed on their smartphones that recorded their number of outgoing calls, distance travelled, and data from the phones’ GPSs and accelerometers. Phone surveys were also carried out three times a day, so the researchers could know when the recruits were actually intoxicated.
After analyzing the data, the research group found that a phone’s sensors could identify when a participant was high with 67 percent accuracy. But when these data were combined with time data (day of the week, time of day), the accuracy of identifying a high went up to 90 percent.
Indeed, writing in their paper, the researchers considered time data to be the most important type of data needed to identify a cannabis high via a smartphone; travel data (from a phone’s GPS) and motion data (from a phone’s accelerometer) were considered second and third most important, respectively.
“Knowing at what time of day, and on what days of the week a young adult tends to use cannabis would likely have an important impact on being able to detect cannabis use,” the researchers wrote in their paper.
As for the travel and motion data, the study’s authors noted that “the micro- and macro-movements captured by accelerometer and GPS, respectively, appear to be promising digital markers for detection of addictive behaviors and related states (e.g., craving).”
The authors also noted that their study has its limitations, including the fact that there “were relatively few data points for which participants reported not being under the influence of cannabis.” Further studies, therefore, may be needed to properly assess the method’s robustness.
In many areas with legal access to recreational cannabis, the standard way for checking whether a person is intoxicated with cannabis or not is to test for THC in their blood. But these tests are often invasive and time-consuming.
As such, several research efforts have been launched in recent years to create a less intrusive, more portable technique. One breathalyzer prototype, developed at the University of Pittsburgh in 2019, uses carbon nanotubes, 100,000 times smaller than a human hair, to “detect THC at levels comparable to or better than mass spectrometry.”
But other scientists aren’t as convinced that human breath is the best sample to take for THC identification.
According to Shalini Prasad, a professor of bioengineering at the University of Texas at Dallas, the actual THC levels present in breath are so low that such tests risk producing error-prone data, which require extensive processing to filter out other compounds. Saliva, according to Prasad, is a medium far better suited to studying THC intoxication levels, which is why her research team chose to develop their own saliva-based THC detection kit in 2020.