Diagnosis of Depression Using Artificial Intelligence Methods

Depression is a widespread psychiatric disorder, which can significantly deteriorate the quality of life. Automatic depression detection could be an accessible and reliable diagnostic tool, addressing the current issues in the mental disorders area, such as social stigma, human bias, and others. The purpose of this paper is to study how accurately depression can be predicted on our exclusive dataset and what the most sustainable models and data representations are. The study focuses on problem formulations such as binary classification and abnormality detection. The exploited models included convolutional neural networks and the transformer, and they were either trained only on our dataset or employed in the form of pre-trained for the image classification instances. Additionally, a benchmark of classical machine learning algorithms for the Geneva Minimalistic Acoustic Parameter Set features was computed. In total, we derived the best average ROC-AUC value of 0.72 on the test, compared to the acoustic features benchmark of 0.55. This best result was provided by fine-tuning Inception architecture under the one-plus-epsilon classification algorithm (a recent instance of one-class classification methods).