Exploring the ability of vocal biomarkers in distinguishing depression from bipolar disorder, schizophrenia, and healthy controls
BackgroundVocal features have been exploited to distinguish depression from healthy controls. While there have been some claims for success, the degree to which changes in vocal features are specific to depression has not been systematically studied. Hence, we examined the performances of vocal feat...
| Main Authors: | , , , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
Frontiers Media S.A.
2023-07-01
|
| Series: | Frontiers in Psychiatry |
| Subjects: | |
| Online Access: | https://www.frontiersin.org/articles/10.3389/fpsyt.2023.1079448/full |
| _version_ | 1797770851541581824 |
|---|---|
| author | Wei Pan Wei Pan Wei Pan Fusong Deng Xianbin Wang Xianbin Wang Xianbin Wang Bowen Hang Bowen Hang Bowen Hang Wenwei Zhou Wenwei Zhou Wenwei Zhou Tingshao Zhu Tingshao Zhu |
| author_facet | Wei Pan Wei Pan Wei Pan Fusong Deng Xianbin Wang Xianbin Wang Xianbin Wang Bowen Hang Bowen Hang Bowen Hang Wenwei Zhou Wenwei Zhou Wenwei Zhou Tingshao Zhu Tingshao Zhu |
| author_sort | Wei Pan |
| collection | DOAJ |
| description | BackgroundVocal features have been exploited to distinguish depression from healthy controls. While there have been some claims for success, the degree to which changes in vocal features are specific to depression has not been systematically studied. Hence, we examined the performances of vocal features in differentiating depression from bipolar disorder (BD), schizophrenia and healthy controls, as well as pairwise classifications for the three disorders.MethodsWe sampled 32 bipolar disorder patients, 106 depression patients, 114 healthy controls, and 20 schizophrenia patients. We extracted i-vectors from Mel-frequency cepstrum coefficients (MFCCs), and built logistic regression models with ridge regularization and 5-fold cross-validation on the training set, then applied models to the test set. There were seven classification tasks: any disorder versus healthy controls; depression versus healthy controls; BD versus healthy controls; schizophrenia versus healthy controls; depression versus BD; depression versus schizophrenia; BD versus schizophrenia.ResultsThe area under curve (AUC) score for classifying depression and bipolar disorder was 0.5 (F-score = 0.44). For other comparisons, the AUC scores ranged from 0.75 to 0.92, and the F-scores ranged from 0.73 to 0.91. The model performance (AUC) of classifying depression and bipolar disorder was significantly worse than that of classifying bipolar disorder and schizophrenia (corrected p < 0.05). While there were no significant differences in the remaining pairwise comparisons of the 7 classification tasks.ConclusionVocal features showed discriminatory potential in classifying depression and the healthy controls, as well as between depression and other mental disorders. Future research should systematically examine the mechanisms of voice features in distinguishing depression with other mental disorders and develop more sophisticated machine learning models so that voice can assist clinical diagnosis better. |
| first_indexed | 2024-03-12T21:28:03Z |
| format | Article |
| id | doaj.art-d141de8bb0a54426b9904f5e0539b95f |
| institution | Directory Open Access Journal |
| issn | 1664-0640 |
| language | English |
| last_indexed | 2024-03-12T21:28:03Z |
| publishDate | 2023-07-01 |
| publisher | Frontiers Media S.A. |
| record_format | Article |
| series | Frontiers in Psychiatry |
| spelling | doaj.art-d141de8bb0a54426b9904f5e0539b95f2023-07-28T03:14:50ZengFrontiers Media S.A.Frontiers in Psychiatry1664-06402023-07-011410.3389/fpsyt.2023.10794481079448Exploring the ability of vocal biomarkers in distinguishing depression from bipolar disorder, schizophrenia, and healthy controlsWei Pan0Wei Pan1Wei Pan2Fusong Deng3Xianbin Wang4Xianbin Wang5Xianbin Wang6Bowen Hang7Bowen Hang8Bowen Hang9Wenwei Zhou10Wenwei Zhou11Wenwei Zhou12Tingshao Zhu13Tingshao Zhu14Key Laboratory of Adolescent Cyberpsychology and Behavior (CCNU), Ministry of Education, Wuhan, ChinaSchool of Psychology, Central China Normal University, Wuhan, ChinaKey Laboratory of Human Development and Mental Health of Hubei Province, Wuhan, ChinaWuhan Wuchang Hospital, Wuchang Hospital Affiliated to Wuhan University of Science and Technology, Wuhan, ChinaKey Laboratory of Adolescent Cyberpsychology and Behavior (CCNU), Ministry of Education, Wuhan, ChinaSchool of Psychology, Central China Normal University, Wuhan, ChinaKey Laboratory of Human Development and Mental Health of Hubei Province, Wuhan, ChinaKey Laboratory of Adolescent Cyberpsychology and Behavior (CCNU), Ministry of Education, Wuhan, ChinaSchool of Psychology, Central China Normal University, Wuhan, ChinaKey Laboratory of Human Development and Mental Health of Hubei Province, Wuhan, ChinaKey Laboratory of Adolescent Cyberpsychology and Behavior (CCNU), Ministry of Education, Wuhan, ChinaSchool of Psychology, Central China Normal University, Wuhan, ChinaKey Laboratory of Human Development and Mental Health of Hubei Province, Wuhan, ChinaInstitute of Psychology, Chinese Academy of Sciences, Beijing, ChinaCAS Key Laboratory of Behavioral Science, Institute of Psychology, Chinese Academy of Sciences, Beijing, ChinaBackgroundVocal features have been exploited to distinguish depression from healthy controls. While there have been some claims for success, the degree to which changes in vocal features are specific to depression has not been systematically studied. Hence, we examined the performances of vocal features in differentiating depression from bipolar disorder (BD), schizophrenia and healthy controls, as well as pairwise classifications for the three disorders.MethodsWe sampled 32 bipolar disorder patients, 106 depression patients, 114 healthy controls, and 20 schizophrenia patients. We extracted i-vectors from Mel-frequency cepstrum coefficients (MFCCs), and built logistic regression models with ridge regularization and 5-fold cross-validation on the training set, then applied models to the test set. There were seven classification tasks: any disorder versus healthy controls; depression versus healthy controls; BD versus healthy controls; schizophrenia versus healthy controls; depression versus BD; depression versus schizophrenia; BD versus schizophrenia.ResultsThe area under curve (AUC) score for classifying depression and bipolar disorder was 0.5 (F-score = 0.44). For other comparisons, the AUC scores ranged from 0.75 to 0.92, and the F-scores ranged from 0.73 to 0.91. The model performance (AUC) of classifying depression and bipolar disorder was significantly worse than that of classifying bipolar disorder and schizophrenia (corrected p < 0.05). While there were no significant differences in the remaining pairwise comparisons of the 7 classification tasks.ConclusionVocal features showed discriminatory potential in classifying depression and the healthy controls, as well as between depression and other mental disorders. Future research should systematically examine the mechanisms of voice features in distinguishing depression with other mental disorders and develop more sophisticated machine learning models so that voice can assist clinical diagnosis better.https://www.frontiersin.org/articles/10.3389/fpsyt.2023.1079448/fulldepressionhealthy controlsschizophreniabipolar disorderi-vectorslogistic regression MFCCs |
| spellingShingle | Wei Pan Wei Pan Wei Pan Fusong Deng Xianbin Wang Xianbin Wang Xianbin Wang Bowen Hang Bowen Hang Bowen Hang Wenwei Zhou Wenwei Zhou Wenwei Zhou Tingshao Zhu Tingshao Zhu Exploring the ability of vocal biomarkers in distinguishing depression from bipolar disorder, schizophrenia, and healthy controls Frontiers in Psychiatry depression healthy controls schizophrenia bipolar disorder i-vectors logistic regression MFCCs |
| title | Exploring the ability of vocal biomarkers in distinguishing depression from bipolar disorder, schizophrenia, and healthy controls |
| title_full | Exploring the ability of vocal biomarkers in distinguishing depression from bipolar disorder, schizophrenia, and healthy controls |
| title_fullStr | Exploring the ability of vocal biomarkers in distinguishing depression from bipolar disorder, schizophrenia, and healthy controls |
| title_full_unstemmed | Exploring the ability of vocal biomarkers in distinguishing depression from bipolar disorder, schizophrenia, and healthy controls |
| title_short | Exploring the ability of vocal biomarkers in distinguishing depression from bipolar disorder, schizophrenia, and healthy controls |
| title_sort | exploring the ability of vocal biomarkers in distinguishing depression from bipolar disorder schizophrenia and healthy controls |
| topic | depression healthy controls schizophrenia bipolar disorder i-vectors logistic regression MFCCs |
| url | https://www.frontiersin.org/articles/10.3389/fpsyt.2023.1079448/full |
| work_keys_str_mv | AT weipan exploringtheabilityofvocalbiomarkersindistinguishingdepressionfrombipolardisorderschizophreniaandhealthycontrols AT weipan exploringtheabilityofvocalbiomarkersindistinguishingdepressionfrombipolardisorderschizophreniaandhealthycontrols AT weipan exploringtheabilityofvocalbiomarkersindistinguishingdepressionfrombipolardisorderschizophreniaandhealthycontrols AT fusongdeng exploringtheabilityofvocalbiomarkersindistinguishingdepressionfrombipolardisorderschizophreniaandhealthycontrols AT xianbinwang exploringtheabilityofvocalbiomarkersindistinguishingdepressionfrombipolardisorderschizophreniaandhealthycontrols AT xianbinwang exploringtheabilityofvocalbiomarkersindistinguishingdepressionfrombipolardisorderschizophreniaandhealthycontrols AT xianbinwang exploringtheabilityofvocalbiomarkersindistinguishingdepressionfrombipolardisorderschizophreniaandhealthycontrols AT bowenhang exploringtheabilityofvocalbiomarkersindistinguishingdepressionfrombipolardisorderschizophreniaandhealthycontrols AT bowenhang exploringtheabilityofvocalbiomarkersindistinguishingdepressionfrombipolardisorderschizophreniaandhealthycontrols AT bowenhang exploringtheabilityofvocalbiomarkersindistinguishingdepressionfrombipolardisorderschizophreniaandhealthycontrols AT wenweizhou exploringtheabilityofvocalbiomarkersindistinguishingdepressionfrombipolardisorderschizophreniaandhealthycontrols AT wenweizhou exploringtheabilityofvocalbiomarkersindistinguishingdepressionfrombipolardisorderschizophreniaandhealthycontrols AT wenweizhou exploringtheabilityofvocalbiomarkersindistinguishingdepressionfrombipolardisorderschizophreniaandhealthycontrols AT tingshaozhu exploringtheabilityofvocalbiomarkersindistinguishingdepressionfrombipolardisorderschizophreniaandhealthycontrols AT tingshaozhu exploringtheabilityofvocalbiomarkersindistinguishingdepressionfrombipolardisorderschizophreniaandhealthycontrols |