Breaking News
January 22, 2019 - New machine learning algorithms identify early symptoms of urinary tract infections
January 22, 2019 - A global influenza pandemic high on the WHO’s agenda
January 22, 2019 - Amgen Makes All Repatha (evolocumab) Device Options Available In The US At A 60 Percent Reduced List Price
January 22, 2019 - Elastronics—hydrogel-based microelectronics for localized low-voltage neuromodulation
January 22, 2019 - Branched-chain amino acids in tumors can be targeted to prevent and treat cancer
January 22, 2019 - Fueling macrophages with energy to attack and eat cancer cells
January 22, 2019 - Amgen And UCB Receive Positive Vote From FDA Advisory Committee In Favor Of Approval For Evenity (romosozumab)
January 22, 2019 - Does being bilingual make children more focused? Study says no
January 22, 2019 - Study reveals new genes and biological pathways linked to osteoarthritis
January 22, 2019 - FSU study provides better understanding of spinal cord injuries
January 22, 2019 - Delaying bath for newborn babies increases breastfeeding rates, finds study
January 21, 2019 - WHO identifies non-communicable diseases as major threat to human health
January 21, 2019 - Many parents still try non-evidence-based cold prevention methods for children
January 21, 2019 - High Levels of Activity, Motor Ability Linked to Better Cognition
January 21, 2019 - Killer blows? Knockout study of pair of mouse MicroRNA provides cancer insight
January 21, 2019 - Buffalo researchers receive grant to quicken development of generic equivalents of contraceptives
January 21, 2019 - One-third of pregnant women do not believe cannabis is harmful to their fetus
January 21, 2019 - Fiderstat could be used as chemopreventative drug for intestinal cancers caused by APC gene mutations
January 21, 2019 - Modifying healthcare delivery practices may improve discussions between youth and healthcare providers
January 21, 2019 - UNIST researcher named as recipient of Merck’s 2018 Life Science Awards
January 21, 2019 - How Getting a Flu Shot Could Save Your Life
January 21, 2019 - Surgical adhesions can be treated, prevented in mice
January 21, 2019 - Increased physician-targeted marketing associated with higher opioid overdose deaths
January 21, 2019 - Researchers uncover specific microbial signatures of intestinal disease
January 21, 2019 - Researchers discover new blood vessel system in bones
January 21, 2019 - Simple blood test reliably detects signs of Alzheimer’s damage before symptoms
January 21, 2019 - Study to investigate new targeted oral treatments for severe asthma
January 21, 2019 - Plan Your Plate | NIH News in Health
January 21, 2019 - Fecal occult blood test may improve CRC outcomes in some
January 21, 2019 - Blood test detects Alzheimer’s disease years before symptoms develop
January 21, 2019 - Mount Sinai joins with Paradigm and ReqMed to repurpose drug for treatment of MPS
January 21, 2019 - FDA Advisory Committee Votes on Zynquista (sotagliflozin) as Treatment for Adults with Type 1 Diabetes
January 21, 2019 - The causes and complications of snoring
January 21, 2019 - Placenta adapts and compensates when pregnant mothers have poor diets or low oxygen
January 21, 2019 - New implant could restore the transmission of electrical signals in injured central nervous system
January 21, 2019 - Rapid-acting fentanyl test strips found to be effective at reducing overdose risk
January 21, 2019 - Coronary Artery Calcium May Help Predict CVD in South Asians
January 21, 2019 - The mystery of the super-ager
January 21, 2019 - Scientists develop smart microrobots that can change shape depending on their surroundings
January 21, 2019 - Keep Moving to Keep Brain Sharp in Old Age
January 21, 2019 - Despite progress, gay fathers and their children still structurally stigmatized
January 21, 2019 - New drug for treating liver parasites in vivax malaria
January 21, 2019 - Merck recognized with 2018 Life Science Industry Award for best use of social media
January 21, 2019 - Coeur Wallis equips the canton of Valais with 260 SCHILLER defibrillators
January 21, 2019 - Scientists propose quick and pain-free method for diagnosing kidney cancer
January 21, 2019 - Signs of memory loss could point to hearing issues
January 21, 2019 - HeartFlow Analysis shows highest diagnostic performance for detecting coronary artery disease
January 21, 2019 - How Much Caffeine is Too Much?
January 21, 2019 - Take a timeout before you force your child to apologize
January 21, 2019 - Scientists design two AI algorithms to improve early detection of cognitive impairment
January 21, 2019 - Novel therapy for children with chronic hormone deficiency provides lifeline for parents
January 21, 2019 - Bioethicists call for oversight of poorly regulated, consumer-grade neurotechnology products
January 21, 2019 - Study shows hereditary hemochromatosis behind many cancers and joint diseases
January 21, 2019 - Short bouts of stairclimbing throughout the day can improve cardiovascular health
January 20, 2019 - Liver Transplant Survival May Improve With Race Matching
January 20, 2019 - Study implicates hyperactive immune system in aging brain disorders
January 20, 2019 - Cancer Diagnosis May Quadruple Suicide Risk
January 20, 2019 - Parkinson’s disease experts devise a roadmap
January 20, 2019 - Research brings new hope to treating degenerative brain diseases
January 20, 2019 - Scientists pinpoint a set of molecules that wire the body weight center of the brain
January 20, 2019 - Researchers get close to developing elusive blood test for Alzheimer’s disease
January 20, 2019 - UCLA researchers demonstrate new technique to develop cancer-fighting T cells
January 20, 2019 - Researchers discover how cancer cells avoid genetic meltdown
January 20, 2019 - Exercise makes even the ‘still overweight’ healthier: study
January 20, 2019 - University of Utah to establish first-of-its-kind dark sky studies minor in the US
January 20, 2019 - School-based nutritional programs reduce student obesity
January 20, 2019 - Improved maternity care practices in the southern U.S. reduce racial inequities in breastfeeding
January 20, 2019 - New enzyme biomarker test indicates diseases and bacterial contamination
January 20, 2019 - Republican and Democratic governors have different visions to transform health care, say researchers
January 20, 2019 - Researchers discover that spin flips happen in only half a picosecond in the course of a chemical reaction
January 20, 2019 - Suicide Risk Up More Than Fourfold for Cancer Patients
January 20, 2019 - Doctors find 122 nails in Ethiopian’s stomach
January 20, 2019 - UV disinfection technology eliminates up to 97.7% of pathogens in operating rooms
January 20, 2019 - Researchers discover mechanism which drives leukemia cell growth
January 20, 2019 - AHA: Infection as a Baby Led to Heart Valve Surgery for Teen
January 20, 2019 - Injection improves vision in a form of childhood blindness
January 20, 2019 - Multiple sclerosis therapies delay progression of disability
January 20, 2019 - New study finds infrequent helmet use among bike share riders
January 20, 2019 - Clearing up information about corneal dystrophies
January 20, 2019 - Researchers describe new behavior in energy metabolism that refutes existing evidence
AI tool promotes positive peer groups to tackle substance abuse

AI tool promotes positive peer groups to tackle substance abuse

image_pdfDownload PDFimage_print

When it comes to fighting substance abuse, research suggests the company you keep can make the difference between recovery and relapse. So, while group intervention programs can play an important role in preventing substance abuse, especially in at-risk populations such as homeless youth, they can also inadvertently expose participants to negative behaviors.

Now, researchers from the USC Center for Artificial Intelligence in Society have created an algorithm that sorts intervention program participants—who are voluntarily working on recovery—into smaller groups, or subgroups, in a way that maintains helpful social connections and breaks social connections that could be detrimental to recovery.

“We know that substance abuse is highly affected by social influence; in other words, who you are friends with,” says Aida Rahmattalabi, a USC computer science graduate student and lead author of the study.

“In order to improve effectiveness of interventions, you need to know how people will influence each other in a group.”

Rahmattalabi and colleagues from USC Viterbi School of Engineering, USC Suzanne Dworak-Peck School of Social Work and the University of Denver worked in collaboration with Urban Peak, a Denver-based non-profit serving homeless youth, to develop the decision aid, which they hope will assist interventionists in substance abuse prevention.

Results showed the algorithm performed significantly better than control strategies for forming groups. The study, called Influence Maximization for Social Network Based Substance Abuse Prevention, was published in the AAAI conference on Artificial Intelligence student abstract section.

Co-authors of the study were USC’s Phebe Vayanos, assistant professor of industrial and systems engineering and computer science, Milind Tambe, the Helen N. and Emmett H. Jones Professor in Engineering and professor of computer science and industrial and systems engineering, and Eric Rice, associate professor in social work; Anamika Barman Adhikari from the University of Denver; and Robin Baker from Urban Peak.

Power of peer influence

Every year, up to two million youth in the U.S. will experience homelessness, and estimates suggest between 39 and 70 percent of homeless youth abuse drugs or alcohol.

Substance abuse initiatives such as group therapy can offer support by encouraging homeless youth to share their experiences, learn positive coping strategies, and build healthy social networks.

But if these groups are not properly structured, they can exacerbate the problems they intend to treat by encouraging the formation of friendships based on antisocial behavior. This is a process known in social work as “deviancy training,” when peers reinforce each other for deviant behavior.

The team tackled this problem from an artificial intelligence perspective, creating an algorithm that takes into account both how the individuals in a subgroup are connected—their social ties—and their prior history of substance abuse.

Survey data gathered voluntarily from homeless youth in Los Angeles, as well as behavioral theories and observations of previous interventions, were used to build a computational model of the interventions.

“Based on this we have an influence model that explains how likely it is for an individual to adopt negative behaviors or change negative behaviors based on their participation in the group,” says Rahmattalabi.

“This helps us predict what happens when we group people into smaller groups.”

Perhaps the most surprising finding was that, contrary to common intuition, evenly distributing regular substance users across the subgroups is not the optimal way to design a successful intervention.

“Uniform distribution of users while ignoring their existing relationships can greatly decrease the success rate of these interventions,” says Rahmattalabi.

In addition, the analysis suggests that sometimes conducting the intervention could actually have a detrimental on the group.

“In some cases, we found it’s actually a bad idea to conduct the intervention: for example, if you have many high-risk people in a group, it is better to not connect them with low-risk individuals,” says Rahmattalabi.

As new data is added to the algorithm, the researchers hope it will adapt to changing conditions, revealing how social networks evolve during the course of the intervention program. This could allow interventionists to determine how an intervention will shape participant outcomes. The researchers are continuing to work with Urban Peak, and plan to deploy the tool to optimize intervention group strategies for homeless youth in Denver in fall 2018.


Explore further:
Marijuana use amongst youth stable, but substance abuse admissions up

Provided by:
University of Southern California

Tagged with:

About author

Related Articles