Unveiling mental health with machine learning and deep learning: Exploring applications and navigating challenges

In today fast-paced society, psychological health issues such as anxiety, depression, and stress have become increasingly prevalent across diverse populations.This paper explores the prediction of anxiety, depression, and stress levels via machine learning algorithms. Five different machine learning algorithms were employed to predict the severity of anxiety, depression, and stress across the sampled population. These algorithms were chosen for their high accuracy, making them particularly well-suited for predicting psychological problems. However, applying these algorithms made it apparent that class imbalances existed in the confusion matrix, necessitating incorporating the F1 score measure. The F1 score proved crucial in identifying the most accurate model among the five applied algorithms, ultimately revealing that the random forest classifier was the most effective in predicting anxiety, depression, and stress levels. Moreover, the specificity parameter was examined, showing that the algorithms exhibited notable sensitivity to negative results. The authors emphasized the trade-off between accuracy and execution time, particularly in the hybrid approach. While the hybrid model combined the strengths of multiple algorithms to achieve higher prediction accuracy for anxiety, depression, and stress levels, it also resulted in longer execution times. This trade-off is a common challenge in machine learning, where increasing model complexity can lead to improved accuracy but at the cost of slower processing speeds. This study contributes to the growing body of research on machine learning in mental health prediction, offering valuable insights into the intricacies of class imbalances and the importance of performance metrics such as the f1 score and specificity. The findings underscore the potential of machine learning algorithms, particularly the random forest classifier, in enhancing our understanding and prediction of psychological health issues in diverse and dynamic populations.