2025 ASEE Annual Conference & Exposition

Mental health disparities between urban and rural areas are shaped by a complex interplay of social determinants, including socioeconomic status, access to healthcare, education, and community resources. Traditional approaches to understanding these disparities often rely on broad statistical models that overlook nuanced patterns in large datasets. To address this gap, we propose a deep learning-based framework to systematically analyze the impact of various social determinants on mental health outcomes in urban and rural communities. The proposed framework leverages deep learning techniques, such as Convolutional Neural Networks (CNNs) and Recurrent Neural Networks (RNNs), to capture complex relationships between multiple social factors and mental health indicators. Using publicly available datasets from sources like the U.S. Census Bureau, Centers for Disease Control and Prevention (CDC), and National Institute of Mental Health (NIMH), the model will integrate structured data (e.g., income, employment, and education levels) and unstructured data (e.g., social media posts and news articles) to generate a comprehensive understanding of how social determinants impact mental health in diverse environments. By analyzing data at the county and neighborhood levels, the model aims to identify specific factors that contribute to higher rates of depression, anxiety, and other mental health disorders in rural areas compared to urban settings. The deep learning framework will utilize feature extraction techniques to uncover hidden patterns in the data, revealing the relative importance of different social determinants in predicting mental health outcomes. For instance, factors like healthcare access may weigh more heavily in rural areas, while stress due to high population density could be a more significant determinant in urban communities. Additionally, this approach will enable the identification of vulnerable subgroups within these populations, such as minority communities or low-income families, that are disproportionately affected by mental health disparities. The findings from this research can inform targeted public health interventions and resource allocation strategies to reduce these disparities. Ultimately, this study highlights the potential of deep learning to provide a more granular understanding of mental health disparities and the role of social determinants. By uncovering hidden trends and complex interactions in large datasets, this research aims to guide policymakers and healthcare professionals in designing more effective, data-driven strategies for promoting mental health equity across both urban and rural settings.