The Model to Predict Depression Risk using Deep Learning Techniques from Basic Satisfaction in Subsistence A Case Study of Peoples in Bangkok

Abstract

This research aims to predict the risk of depression based on external factors using deep learning models. It has three objectives: (1) to study, develop, and create a model to predict the risk of depression, focusing on a case study of individuals in Bangkok using deep learning techniques; (2) to test the effectiveness of the predictive model for depression risk in the case of people in Bangkok using deep learning techniques; and (3) to compare and evaluate the prediction model's results against a questionnaire designed by the researcher, which focuses on external factors that contribute to depression risk, and compare it with the depression assessment questionnaire provided by the Department of Mental Health, Ministry of Public Health. The case study involved 400 online survey samples from Bangkok residents. Both internal and external factor models were created, with score criteria adjusted according to international standards, and the results were compared. It was found that the model based on external factors achieved 99.92% accuracy, while the model based on internal factors achieved 99.93% accuracy, with only a 0.01% difference between the two. Both models had a mean squared error (MSE) of less than 0.0295 and a mean absolute error (MAE) of less than 0.1279. In conclusion, both models are consistent, and the research can be further developed to improve the accuracy of depression risk prediction