ORIGINAL ARTICLE Detection of major depressive disorder using vocal acoustic analysis and machine learning—an exploratory study Caroline Wanderley Espinola 1,2 & Juliana Carneiro Gomes 3 & Jessiane Mônica Silva Pereira 3 & Wellington Pinheiro dos Santos 1 Received: 15 April 2020 /Accepted: 28 September 2020 # Sociedade Brasileira de Engenharia Biomedica 2020 Abstract Purpose Diagnosis and treatment in psychiatry are still highly dependent on reports from patients and on clinician judgment. 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 and 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 a vocal feature extraction algorithm, and to different machine learning classification techniques. Results The results showed that random tree models with 100 trees provided the greatest classification performances. It achieved mean accuracy of 87.5575% ± 1.9490, mean kappa index, sensitivity, and specificity of 0.7508 ± 0.0319, 0.9149 ± 0.0204, and 0.8354 ± 0.0254, respectively, for the detection of MDD. Conclusion The use of machine learning classifiers with vocal acoustic features appears to be very promising for the detection of major depressive disorder in this exploratory study, but further experiments with a larger sample will be necessary to validate our findings. Keywords Major depressive disorder . Diagnosis . Voice . Acoustic parameters . Machine learning . Support vector machines Introduction Clinical assessment and treatment in psychiatry currently de- pend on diagnostic criteria built entirely on expert consensus, instead of relying on objective biomarkers (Bzdok and Meyer- lindenberg 2018). Such criteria, described in the Diagnostic and Statistical Manual, 5th Edition (DSM-5), and in the International Classification of Diseases (ICD-10), are still con- sidered the gold standard for diagnosis in psychiatry (American Psychiatric Association 2013). Nevertheless, those * Wellington Pinheiro dos Santos wellington.santos@ufpe.br Caroline Wanderley Espinola caroline.espinola@ufpe.br Juliana Carneiro Gomes jcg@ecomp.poli.br Jessiane Mônica Silva Pereira jmsp@ecomp.poli.br 1 Departamento de Engenharia Biomédica, Universidade Federal de Pernambuco, Recife, Brazil 2 Serviço de Emergência Psiquiátrica, Hospital Ulysses Pernambucano, Recife, PE, Brazil 3 Núcleo de Engenharia da Computação, Escola Politécnica de Pernambuco, Universidade de Pernambuco, Recife, Brazil Research on Biomedical Engineering https://doi.org/10.1007/s42600-020-00100-9