Researchers think they’ve come up with a cutting-edge way to predict the likelihood of a given homeless youth running into trouble with substance abuse – and to devise individualized rehab strategies for those who nevertheless develop a disorder.
Scientists interviewed hundreds of homeless youth in various geographical and social settings to tease out the many environmental and psychological factors that led them to develop an unhealthy relationship with drugs and alcohol. With that data in hand, they developed an artificial intelligence-driven algorithm that, with the ongoing use of machine learning, may be used to help young people heading off a potentially devastating problem with lifelong implications.
Penn State University‘s College of Information Sciences and Technology developed the tool in hopes of getting ahead of drug problems for young people who are already in an unstable situation.
“Proactive prevention of substance use disorder among homeless youth is much more desirable than reactive mitigation strategies such as medical treatments for the disorder and other related interventions,” said Amulya Yadav, assistant professor of information sciences and technology and principal investigator on the project. “Unfortunately, most previous attempts at proactive prevention have been ad-hoc in their implementation.”
The paper will be presented at the Knowledge Discovery in Databases conference later this month. Maryam Tabar, a doctoral student in informatics and lead author, said she hopes policymakers will use the study’s insights to devise data-driven programs and policies.
The researchers interviewed 1,200 young homeless people in six U.S. states. Factors associated with substance use include criminal history, victimization experiences and mental health characteristics, according to the study. Adverse childhood experiences and physical street victimization were more likely to lead to substance use disorder than other types of victimization, such as sexual victimization, among homeless youth.
Post-traumatic stress disorder and depression were found to be more problematic than other mental health disorders among these youth, according to the researchers.
Yadav and colleague Anamika Barman-Adhikari, assistant professor of social work at the University of Denver and co-author of the paper, are working together on a separate project to build software that designs personalized rehabilitation programs for homeless youth suffering from opioid addiction. Their simulation was more than twice as good as baselines in minimizing opioid addiction among homeless youth. Now, they’re hoping the model can be applied effectively to the real world.
“We wanted to understand what the causative issues are behind people developing opiate addiction,” Yadav said. “And then we wanted to assign these homeless youth to the appropriate rehabilitation program.”
“For example, if a person developed an opioid addiction because they were isolated or didn’t have a social circle, then perhaps as part of their rehabilitation program they should talk to a counselor,” explained Yadav. “On the other hand, if someone developed an addiction because they were depressed because they couldn’t find a job or pay their bills, then a career counselor should be a part of the rehabilitation plan.”
Yadav added, “If you just treat the condition medically, once they go back into the real world, since the causative issue still remains, they’re likely to relapse.”