Skip to main page content
U.S. flag

An official website of the United States government

Dot gov

The .gov means it’s official.
Federal government websites often end in .gov or .mil. Before sharing sensitive information, make sure you’re on a federal government site.

Https

The site is secure.
The https:// ensures that you are connecting to the official website and that any information you provide is encrypted and transmitted securely.

Access keys NCBI Homepage MyNCBI Homepage Main Content Main Navigation
. 2024 Jul 20;24(14):4721.
doi: 10.3390/s24144721.

The Role of Selected Speech Signal Characteristics in Discriminating Unipolar and Bipolar Disorders

Dorota Kamińska  1 , Olga Kamińska  2 , Małgorzata Sochacka  3 , Marlena Sokół-Szawłowska  4
Affiliations

The Role of Selected Speech Signal Characteristics in Discriminating Unipolar and Bipolar Disorders

Dorota Kamińska et al. Sensors (Basel). .

Abstract

Objective: The objective of this study is to explore and enhance the diagnostic process of unipolar and bipolar disorders. The primary focus is on leveraging automated processes to improve the accuracy and accessibility of diagnosis. The study aims to introduce an audio corpus collected from patients diagnosed with these disorders, annotated using the Clinical Global Impressions Scale (CGI) by psychiatrists.

Methods and procedures: Traditional diagnostic methods rely on the clinician's expertise and consideration of co-existing mental disorders. However, this study proposes the implementation of automated processes in the diagnosis, providing quantitative measures and enabling prolonged observation of patients. The paper introduces a speech signal pipeline for CGI state classification, with a specific focus on selecting the most discriminative features. Acoustic features such as prosodies, MFCC, and LPC coefficients are examined in the study. The classification process utilizes common machine learning methods.

Results: The results of the study indicate promising outcomes for the automated diagnosis of bipolar and unipolar disorders using the proposed speech signal pipeline. The audio corpus annotated with CGI by psychiatrists achieved a classification accuracy of 95% for the two-class classification. For the four- and seven-class classifications, the results were 77.3% and 73%, respectively, demonstrating the potential of the developed method in distinguishing different states of the disorders.

Keywords: bipolar disorder; classification; depression; healthcare application; machine learning; mania; speech signal.

PubMed Disclaimer

Conflict of interest statement

Author Małgorzata Sochacka was employed by the company Britenet MED Sp. z o. o. The remaining authors declare that the research was conducted in the absence of any commercial or financial relationships that could be construed as a potential conflict of interest.

Figures

Figure 1
Figure 1
Typical speech recognition pipeline, the two-track approach. (A) Machine learning, (B) deep learning.
Figure 2
Figure 2
Distribution of the number of patients by gender and disease entity.
Figure 3
Figure 3
Distribution of the patients’ population by age.
Figure 4
Figure 4
Histogram of the number of patient voice recordings.
Figure 5
Figure 5
Similarity of features subsets selected using different techniques—example analysis for 100-feature set.
Figure 6
Figure 6
Type of speech signal features most frequently selected by different techniques—example analysis for 100-feature set.
Figure 7
Figure 7
Number of examples in a given CGI category for three analyzed cases.
Figure 8
Figure 8
The relationship between the number of features and the classification results. IGR selection for (from left) 2, 4, and 7 classes.
Figure 9
Figure 9
Confusion matrix for ML and IGR selection for two classes. In gray are highlighted correctly classified instances.
Figure 10
Figure 10
Confusion matrix for RF and MI selection for four classes. In gray are highlighted correctly classified instances.
Figure 11
Figure 11
Confusion matrix for RF and LASSO selection for seven classes. In gray are highlighted correctly classified instances.
See this image and copyright information in PMC

References

    1. Kessler R.C., Chiu W.T., Demler O., Walters E.E. Prevalence, severity, and comorbidity of 12-month DSM-IV disorders in the National Comorbidity Survey Replication. Arch. Gen. Psychiatry. 2005;62:617–627. doi: 10.1001/archpsyc.62.6.617. - DOI - PMC - PubMed
    1. Anker S.D., Morley J.E., von Haehling S. Welcome to the ICD-10 code for sarcopenia. J. Cachexia Sarcopenia Muscle. 2016;7:512–514. - PMC - PubMed
    1. OECD. European Union . Health at a Glance: Europe 2018: State of Health in the EU Cycle. OECD; Paris, France: 2018.
    1. OECD. European Union . Health at a Glance: Europe 2020. OECD; Paris, France: 2020. p. 237. - DOI
    1. Kessing L.V., Andersen P.K. Predictive effects of previous episodes on the risk of recurrence in depressive and bipolar disorders. Curr. Psychos. Ther. Rep. 2005;3:123–130. - PubMed