Detection of Major Depressive Disorder Using Vocal Acoustic Analysis and Machine Learning

Abstract

Purpose Diagnosis and treatment in psychiatry are still highly dependent on reports from patients and on clinician judgement. This fact makes them prone to memory and subjectivity biases. As for other medical fields, where objective biomarkers are available, there has been an increasing interest in the development of such tools in psychiatry. To this end, vocal acoustic parameters have been recently studied as possible objective biomarkers, instead of otherwise invasive and costly methods. Patients suffering from different mental disorders, such as major depressive disorder (MDD), may present with alterations of speech. These can be described as uninteresting, monotonous and spiritless speech, low voice. Methods Thirty-three individuals (11 males) over 18 years old were selected, 22 of which being previously diagnosed with MDD, and 11 healthy controls. Their speech was recorded in naturalistic settings, during a routine medical evaluation for psychiatric patients, and in different environments for healthy controls. Voices from third parties were removed. The recordings were submitted to to a vocal feature extraction algorithm, and to different machine learning classification techniques. Results The results showed that support vector machines (SVM) models provided the greatest classification performances for different kernels, with PUK kernel providing accuracy of 89.14% for the detection of MDD. Conclusion The use of machine learning classifiers with vocal acoustics features has shown to be very promising for the detection of major depressive disorder, but further tests with a larger sample will be necessary to validate our findings.

Evaluating the Feasibility and Acceptability of an Artificial-Intelligence-Enabled and Speech-Based Distress Screening Mobile App for Adolescents and Young Adults Diagnosed with Cancer: A Study Protocol

“…Despite these advancements, several gaps remain in the speech-based distress assessment literature. First, most existing tools only use one type of speech data, either acoustic (the sound of the voice) or semantic (the words used) data, but not both [ 36 , 37 ]. This has limited the use of different types of speech data to improve assessment precision.…”