AI Identifies Key Factors Predicting Anxiety Recovery

Researchers at Penn State have discovered that machine learning can predict recovery from generalized anxiety disorder (GAD) with up to 72% accuracy, SciTech Daily reported. Analyzing over 80 psychological, sociodemographic, and health-related factors from 126 individuals, the study identified 11 key variables influencing long-term recovery.

Key factors promoting recovery included higher education levels, older age, strong social support, and positive emotional states. Conversely, predictors of nonrecovery encompassed depressed affect, daily discrimination, and increased visits to mental health professionals.

Lead author Candice Basterfield emphasized the potential of AI to enhance personalized treatment strategies, particularly for patients with comorbid conditions like depression. The research lays the groundwork for tailored therapies, allowing clinicians to effectively address individual needs.

Published in the Journal of Anxiety Disorders, this study highlights a significant advancement in using AI to improve mental health outcomes, offering hope for those struggling with GAD. The research was supported by the U.S. National Institutes of Health.