Recent advancements in artificial intelligence have the potential to significantly enhance the diagnosis of substance use disorders. University of Cincinnati researchers have developed an innovative AI system that may transform how clinicians assess and treat patients struggling with addiction.
MSN, Bioengineer.org, and various national news outlets have spotlighted this breakthrough technology.
Developed by Professor Hans Breiter and Senior Research Associate Sumra Bari from the UC College of Engineering and Applied Science, this AI system can accurately predict behaviors associated with substance use disorders with up to 83% accuracy. Furthermore, it has an 84% accuracy rate for predicting the severity of addiction, facilitating quicker treatment for those in need.
This study represents a pioneering effort to utilize a computational cognition framework alongside artificial intelligence. The researchers aimed to explore how human judgment can aid in forecasting behaviors indicative of substance use disorders, identifying the substances involved, and evaluating the severity of the addiction.
Professor Breiter emphasized, “This is a new type of AI that can predict mental illness and commonly co-occurring conditions like addiction. It’s a low-cost first step for triage and assessment.”
The findings were published in the prestigious Nature journal Mental Health Research.
According to Bioengineer.org, the UC system is both groundbreaking and revolutionary for diagnosing and treating substance use disorders. They also noted that the lower costs associated with this technology could significantly alleviate barriers to care, ultimately promoting health equity.
Featured image at top: UC Professor Hans Breiter created a novel AI system that helps predict substance use disorder. Photo/Andrew Higley/UC
Conclusion: The innovative AI system developed at the University of Cincinnati represents a substantial leap forward in the early diagnosis and treatment of substance use disorders, promising improved outcomes and greater accessibility for patients in need.
