ANALYZING THE INFLUENCE OF AI IN PREDICTIVE ANALYTICS FOR MENTAL HEALTH AND ITS IMPACT ON EARLY INTERVENTION, ANXIETY LEVELS, AND TREATMENT ADHERENCE

Abstract

This study aimed to investigate the impact of AI-driven predictive analytics on mental health outcomes, particularly anxiety levels, treatment adherence, and early intervention efficacy among university students. Given the rising mental health challenges in academic settings, understanding the role of technology in enhancing interventions is increasingly relevant. Grounded in existing literature that supports the efficacy of technology in mental health care, particularly through the lens of the Technology Acceptance Model (TAM), the research utilized a quantitative design with a sample of 200 students from three universities in Pakistan. TAM posits that perceived ease of use and perceived usefulness significantly influence user acceptance of technology, providing a framework for understanding how students engage with AI tools. Data were collected using standardized self-report measures and analyzed with statistical techniques such as t-tests and ANOVA. Results indicated that the experimental group using AI tools experienced a significant reduction in anxiety levels, with scores decreasing from a mean of 15.1 to 7.5 (p < .001), alongside improved treatment adherence. These findings suggest that AI interventions can effectively enhance mental health support in university settings. However, limitations such as the restricted sample size and potential biases from self-reported measures should be acknowledged. Future research should focus on longitudinal studies to assess long-term effects and explore the integration of AI tools across diverse populations. In conclusion, this research contributes to understanding technology's role in mental health, highlighting its potential to improve outcomes and support systems for students.