From that group, the authors selected a study sample of 765 young men and women ages 18 to 25 who had screened positive for past hazardous alcohol use and divided them into three groups.
Members of one group received text messages and were asked to respond to drinking-related queries. They received real-time feedback through text messages each Thursday and Sunday for 12 weeks.
The Thursday text asked about their drinking plans for the coming weekend.
If they reported anticipating a heavy drinking day, “they were then asked whether they were willing to set a low-risk drinking goal” of less than five drinks per occasion for men or less than four drinks per occasion for women, the article authors said.
“Depending on the response to each query, participants were provided with real-time text feedback to either strengthen their low-risk drinking plan or goal, or to promote reflection on their drinking plan or decision not to set a low-risk goal,” the report said. “Then, on Sunday, participants were sent a text asking them to report the most drinks they had during a single occasion during the weekend.” Based on their response, “they were provided with text feedback to either support their low-risk drinking behavior or promote reflection on their binge-drinking behavior,” according to the report.
Members of a second group were asked to respond to alcohol consumption queries each Sunday, but did not receive any feedback. Members of a third control group did not receive or send text messages throughout the study period.
The researchers then analyzed the three groups for their self-reported number of binge drinking days, the number of drinks per drinking day in the prior 30 days, the proportion of participants with weekend binge episodes and most drinks consumed per drinking episode during the 12 weekends of the study period.
Patients using the complete system experienced a 14% drop in the number of binge drinking days per month and an 8% reduction in the number of drinks when they did go out, according to the research data. Meanwhile, high risk behavior increased in the other two groups.
Researchers found for the group receiving both text messages and feedback, there was a reduction in the number of binge drinking days per month, from 3.7 days at baseline to 3.1 days during the study period. In contrast, the number of binge drinking days per month rose for the group receiving messages alone, from 3.3 days to 4.2 days, and for the control group, from 3.2 days to 3.6.
The researchers also found for the group receiving both text messages and feedback there were decreases in the number of drinks per binge drinking day, from a baseline of 3.8 drinks to 3.5. In contrast, there was an increase for groups receiving messages alone from four drinks per drinking day to 4.2, and for the control group, from 3.6 drinks to four.
Armed with these results, the next stage is to try to implement the program at UPMC and possibly attract a business or organization to commercialize it, said study lead author Dr. Brian Suffoletto, an assistant professor at the University of Pittsburgh Medical School and an emergency room physician at UPMC's Mercy Hospital
“We can scale this nationally at very little cost,” he said.
He conceived of the project six years ago after reading an article in the Archives of Dermatology about a text-based messaging project encouraging people to use sun block.
Suffoletto wondered whether a similar program might address the problem of binge drinking among young adults. Working with Jack Dorman, director of academic computing at UPMC-affiliated Western Psychiatric Institute and Clinic, he created a software package that includes using natural language processing in the interactive response portion of the program.
Follow Joseph Conn on Twitter: @MHJConn