# MONDEP: A unified SpatioTemporal MONitoring Framework for National DEPression Forecasting

## TL;DR

MONDEP is a new framework that uses machine learning to predict depression rates at different administrative levels in Thailand, helping policymakers manage mental health services more effectively.

## Contribution

The paper introduces MONDEP, a unified spatiotemporal framework for forecasting depression using machine learning and deep learning at district and national levels.

## Key findings

- MONDEP uses machine learning and deep learning to forecast depression at district and national levels in Thailand.
- Using deep learning models with multivariate time series improved MAE by 13% compared to SARIMAX baseline.
- The framework demonstrates how lower administrative-level data can estimate national mental health profiles.

## Abstract

Depression has become a prevalent mental disorder that significantly affects a person's emotions, behaviors, physical health, ability to perform daily tasks, and ability to maintain healthy relationships. Untreated depression can escalate the risk of suicide, making the situation even worse. Despite an abundance of models previously proposed for forecasting depression, the issue of foretelling the overall number of patients at each administrative level remains under-investigated. Therefore, in this paper, we propose a simple but effective SpatioTemporal Monitoring Framework for National Depression Forecasting (MONDEP). In particular, we analyze national depression statistics data in Thailand as a case study and create prediction models for a real-time depression forecasting system using machine learning and deep learning approaches. In order to forecast the prevalence of depression at various administrative levels, we use the hierarchical structure of depression aggregation. The proposed framework consists of three modules: Data Pre-processing to extract and pre-process the raw data, Exploratory Data Analysis (EDA) to visualize and analyze the data to get insight, and Model Training and Testing to predict future depression cases. The objective of our research is to construct a comprehensive MONDEP framework that utilizes machine learning and deep learning to predict depression profiles at the district and national levels using multivariate time series across various administrative levels. Our study illustrates the considerable association between a spatial-temporal component and demonstrates how depression profiles may be represented by employing lower administrative-level data to estimate the general level of mental health across the nation. Additionally, the best performance across all criteria is obtained when a deep learning model is used to exploit multivariate time series, showing a 13% improvement in MAE measure compared to the SARIMAX baseline. We believe the proposed framework could be used as a point of reference for decision-making regarding the management of depression and has the potential to be incredibly helpful for policymakers in successfully managing mental health services on time.