Mental health is a crucial aspect of overall well-being, with depression being the most prevalent mental health disorder. This study focuses on analyzing mental health data to address the Sustainable Development Goal of ‘Good Health and Well-being’. It leverages the NHANES dataset, spanning 20 years, to identify patterns in mental health, particularly depression. Big data frameworks like Spark, Hadoop, and TensorFlow are utilized for data analysis, considering factors such as biological causes, demographics, and lifestyle. The study employs statistical analyses, including correlation, mediation, and prediction, to understand and forecast depression, highlighting the role of various factors in mental health. The Mean Squared Error (MSE) is calculated from the predicted values, indicating that a significant portion of the dataset was successfully predicted. Although our analysis has produced encouraging results in terms of predictive accuracy and feature selection, it also reveals certain limitations that require our attention.