We are all familiar with our smartphone tracking the distance we have walked or travelled with the help of several GPS applications but what if the gadget is also capable of tracking our erratic gait after a drinking episode? It most definitely can.
In 2012, 3.3 million deaths that are 5.9 per cent of all global deaths (7.6 per cent for men and 4.0 per cent for women), were attributable to alcohol consumption. In 2018, there were 10,511 people killed in these preventable drunk driving-related crashes. In fact, on average over the 10-year period from 2009-2018, more than 10,000 people died every year in drunk driving crashes. No matter how stable the drunk might feel they are, alcohol causes evident functional impairments in the body, especially the stereotypical characteristic of the drunk that's actually true: that soused walk. Scientists and researchers are ardently looking for a better and efficient way to determine the alcohol-related impairment to avoid high-risk events like drunk driving-related accidents, alcohol poisoning, physical assault and other trauma, by banking on this erratic gait impairments.
More than 96% of Americans own a smartphone, which is almost universally embedded with powerful sensors that allow for inertial measurements of gait. Researchers have begun to model the associations between gait abnormalities detected using smartphone sensors and either real or simulated alcohol consumption. Scientists from the University of Pittsburgh published new research that can prove a person's intoxication if they have a smartphone on them. The smartphone can tell you if you are drunk using software, measuring motion data to detect if a subject is intoxicated. The researchers are hoping that real-time data on the intoxication level of a participant could help people reduce their alcohol intake. This controlled lab study sought to explore the accuracy of gait related features measured by smartphone accelerometer sensors on detecting alcohol intoxication with an average accuracy of 93 per cent.
For the study, from August to December 2018, 22 adults were recruited via word of mouth and locally posted advertisements for a study to examine the effects of alcohol on psychomotor tasks. An initial screen test by telephone was conducted to ensure all participants were at least 21 years old and consumed alcohol at least once per week. Consented participants then made appointments to come to the laboratory for one session that would last for 7 hours. They were instructed to abstain from consuming any alcohol or using other drugs 24 hours prior to the session and also refraining from any sort of caffeine consumption for a minimum of 4 hours before the session. After providing informed consent, participants completed a questionnaire including the 10-question Alcohol Use Disorders Identification Test (AUDIT). Bodyweight and height were measured, and an intravenous line was placed to draw blood alcohol measurements and to administer nausea medicine.
They were instructed to walk 10 steps in a straight line on a flat, carpeted but specifically noncompliant surface, turn around and walk 10 steps back to the beginning spot. The researchers recorded the accelerometer data from the phyphox app and downloaded it onto a secure file.
Dr Suffoletto and his colleagues used personalised mathematical models that allowed them to compare each person against their own typical sober gait. "We found that, really, what was driving the model is the medial-lateral sway(staggering side to side), which kind of makes sense when you think about the caricature of the drunk cartoon, a figure who kind of is swaying back and forth," he explained. The data on each person's particular gait allowed the researchers to correctly identify over 90 per cent of the time when a subject's BrAC passed .08. Even though this research is in its early stages, it signifies a growing body of evidence that shows a device's motion data could be a viable measure of alcohol intoxication. The researchers are planning to do further experiments with subjects carrying the devices in their hands or pockets.
Police officers have long used a version of a gait test in the "walk and turn test," where the suspected drunk driver must be able to walk heel to toe in a straight line while maintaining their balance and counting their steps aloud. "Gait-sensed impairment is quite accurate, which is why the police have used the field sobriety test for decades," said Worcester Polytechnic Institute computer scientist, Emmanuel Agu. "One key difference with breathalyzers is that it's an assessment that can be done completely passively and avoids the stigma of having to carry breathalyzers to parties." he continues. Agu and his coworkers have also employed a smartphone to measure intoxication, and even built an app called AlcoGait that detects inebriation.
Thanks to people's differing metabolism, body weight, tolerance for alcohol, and other factors, blood alcohol concentration differs from person to person. One individuals .08 might be another's .20. Even though an average legal BrAC limit for driving is set in each country, the only sure shot method of measuring alcohol level is none other than a standard blood test. Dr Suffoletto's aim is to be able to provide more targeted support to the person during variable high-risk periods, helping them to set essential limits. "It made more sense to me than just trying to send people out to the world and expect them to act the way you told them to two months ago," he said. By monitoring their 'drunk walking', health experts might be able to better predict a person's problematic drinking that might often result in interpersonal violence or unpredictable fatal accidents.