Examining Factors for Anxiety and Depression Prediction

Abstract

Mental health conditions, such as anxiety and depression, are a significant public health concern that can have significant impacts on an individual's quality of life, relationships, and overall well-being. In recent years, data science and machine learning techniques have emerged as important tools for early detection for mental health issues. This research aims at understanding the factors leading to anxiety and depression and implement predictive modelling for improving the accuracy and efficiency of early mental health diagnoses. Tabular DNN outperformed ANN and other machine learning classifiers by approximately 30%. Overall, our findings suggest that deep learning tabular models have the potential to improve the accuracy and efficiency. Thereby helping in early mental health diagnoses so that accessible and convenient support to individuals in need in context of this work