Towards Automatic Depression Detection: A BiLSTM/1D CNN-Based Model

Lin Lin,Lin Zhang,Xuri Chen,Ying Shen

doi:10.3390/app10238701

Abstract

Depression is a global mental health problem, the worst cases of which can lead to self-injury or suicide. An automatic depression detection system is of great help in facilitating clinical diagnosis and early intervention of depression. In this work, we propose a new automatic depression detection method utilizing speech signals and linguistic content from patient interviews. Specifically, the proposed method consists of three components, which include a Bidirectional Long Short-Term Memory (BiLSTM) network with an attention layer to deal with linguistic content, a One-Dimensional Convolutional Neural Network (1D CNN) to deal with speech signals, and a fully connected network integrating the outputs of the previous two models to assess the depressive state. Evaluated on two publicly available datasets, our method achieves state-of-the-art performance compared with the existing methods. In addition, our method utilizes audio and text features simultaneously. Therefore, it can get rid of the misleading information provided by the patients. As a conclusion, our method can automatically evaluate the depression state and does not require an expert to conduct the psychological evaluation on site. Our method greatly improves the detection accuracy, as well as the efficiency.

Highlights

Depression is a global mental disease, whose key features include disruption in emotion experience, communication, and self regulation [1]
We investigate the problem of automatic depression detection and introduce an automatic depression detection method based on the Bidirectional Long Short-Term Memory (BiLSTM) and 1D CNN models to predict the presence of depression, as well as to assess the severity of depressive symptoms
Compared with the baseline performance on the test set, it can be seen that our method can effectively improve the assessment accuracy with MAE and Root Mean Squared Error (RMSE) values equal to 9.30 and 11.55, respectively

Summary

Introduction

Depression is a global mental disease, whose key features include disruption in emotion experience, communication, and self regulation [1]. More than 264 million people in the world are suffering from depression. Depression can lead to self-harm or even suicide activities. According to the World Health Organization (WHO) reports, about 800,000 people die from severe depression every year [2]. Traditional treatments for depression such as psychotherapy or pharmacological are timely, costly, and sometimes ineffective [4]. For individuals with financial difficulties, the cost of diagnosis and treatment is a heavy burden, which makes patients unwilling to consult a doctor. Physicians usually assess the severity of depression based on clinical interviews, rating scales, and self-assessments [5]. Fearing public stigma and other negative consequences brought by the diagnosis, patients sometimes hide their true conditions from

Methods

Results

Discussion

Conclusion