Interpretation of Depression Detection Models via Feature Selection Methods

Given the prevalence of depression worldwide and its major impact on society, several studies employed artificial intelligence modelling to automatically detect and assess depression. However, interpretation of these models and cues are rarely discussed in detail in the AI community, but have received increased attention lately. In this article, we aim to analyse the commonly selected features using a proposed framework of several feature selection methods and their effect on the classification results, which will provide an interpretation of the depression detection model. The developed framework aggregates and selects the most promising features for modelling depression detection from 38 feature selection algorithms of different categories. Using three real-world depression datasets, 902 behavioural cues were extracted from speech behaviour, speech prosody, eye movement and head pose. To verify the generalisability of the proposed framework, we applied the entire process to depression datasets individually and when combined. The results from the proposed framework showed that speech behaviour features (e.g. pauses) are the most distinctive features of the depression detection model. From the speech prosody modality, the strongest feature groups were F0, HNR, formants, and MFCC, while for the eye activity modality they were left-right eye movement and gaze direction, and for the head modality it was yaw head movement. Modelling depression detection using the selected features (even though there are only 9 features) outperformed using all features in all the individual and combined datasets. Our feature selection framework did not only provide an interpretation of the model, but was also able to produce a higher accuracy of depression detection with a small number of features in varied datasets. This could help to reduce the processing time needed to extract features and creating the model.

1 Introduction

According to the World Health Organisation (WHO), major depressive disorders are an increasing global issue that leads to devastating consequences [1]. A person living with depression suffers enormously and functions poorly in everyday life tasks. Depression is a major contributor to the overall global burden of disease and is the leading cause of disability worldwide. Depression is strongly linked with non-communicable disorders, such as diabetes and heart disease, increased risk of substance use disorders, and at its worst, it can lead to suicide. Even though treatments for depression are effective, only 10 percent of depressed patients receive such treatments, where one of the barriers to effective care is inaccurate diagnoses. Misdiagnosed and untreated depression does not only affect the sufferer at a personal level, but also affects the employer and the government at an economic level.