Designing and implementing SMILE: An AI-driven platform for enhancing clinical decision-making in mental health and neurodivergence management

Abstract

Rising levels of anxiety, depression, and burnout among healthcare professionals (HCPs) underscore the urgent need for technology-driven interventions that optimize both clinical decision-making and workforce well-being. This innovation report introduces the Support, Management, Individual, Learning Enablement (SMILE) platform, designed to integrate advanced AI-driven decision support, federated learning for data privacy, and cognitive behavioral therapy (CBT) modules into a single, adaptive solution. A mixed-methods pilot evaluation involved focus groups, structured surveys, and real-world usability tests to capture changes in stress levels, user satisfaction, and perceived value. Quantitative analyses revealed significant reductions in reported stress and support times, alongside notable gains in satisfaction and perceived resource value. Qualitatively, participants praised SMILE's accessible interface, enhanced peer support, and real-time therapeutic interventions. These findings confirm the feasibility and utility of a holistic, Artificial Intelligence (AI) supported framework for improving mental health outcomes in high-stress clinical environments. Theoretically, SMILE contributes to emerging evidence on integrated AI platforms, while it offers an ethically sound and user-friendly blueprint for improving patient care and staff well-being.

Ähnliche Arbeiten