Re-examining the robustness of voice features in predicting depression: Compared with baseline of confounders | |
Pan, Wei1,2; Flint, Jonathan3; Shenhav, Liat4; Liu, Tianli5; Liu, Mingming1,2; Hu, Bin6; Zhu, Tingshao1![]() | |
First Author | Pan, Wei |
Correspondent Email | tszhu@psych.ac.cn |
Contribution Rank | 1 |
Abstract | A large proportion of Depression Disorder patients do not receive an effective diagnosis, which makes it necessary to find a more objective assessment to facilitate a more rapid and accurate diagnosis of depression. Speech data is easy to acquire clinically, its association with depression has been studied, although the actual predictive effect of voice features has not been examined. Thus, we do not have a general understanding of the extent to which voice features contribute to the identification of depression. In this study, we investigated the significance of the association between voice features and depression using binary logistic regression, and the actual classification effect of voice features on depression was re-examined through classification modeling. Nearly 1000 Chinese females participated in this study. Several different datasets was included as test set. We found that 4 voice features (PC1, PC6, PC17, PC24, P<0.05, corrected) made significant contribution to depression, and that the contribution effect of the voice features alone reached 35.65% (Nagelkerke's R-2). In classification modeling, voice data based model has consistently higher predicting accuracy(F-measure) than the baseline model of demographic data when tested on different datasets, even across different emotion context. F-measure of voice features alone reached 81%, consistent with existing data. These results demonstrate that voice features are effective in predicting depression and indicate that more sophisticated models based on voice features can be built to help in clinical diagnosis. |
2019-06-20 | |
Language | 英语 |
DOI | 10.1371/journal.pone.0218172 |
Source Publication | PLOS ONE
![]() |
ISSN | 1932-6203 |
Volume | 14Issue:6Pages:14 |
Subtype | article |
Indexed By | SCI |
Funding Project | National Basic Research Program of China[2014CB744600] |
Publisher | PUBLIC LIBRARY SCIENCE |
WOS Keyword | HAN CHINESE WOMEN ; CLINICAL DEPRESSION ; MENTAL-DISORDERS ; FIELD TRIALS ; SPEECH ; EMOTION ; BURDEN ; CLASSIFICATION ; EPIDEMIOLOGY ; DISABILITY |
WOS Research Area | Science & Technology - Other Topics |
WOS Subject | Multidisciplinary Sciences |
WOS ID | WOS:000484893500028 |
Citation statistics | |
Document Type | 期刊论文 |
Identifier | http://ir.psych.ac.cn/handle/311026/29828 |
Collection | 社会与工程心理学研究室 |
Corresponding Author | Zhu, Tingshao |
Affiliation | 1.Chinese Acad Sci, Inst Psychol, Beijing, Peoples R China 2.Univ Chinese Acad Sci, Beijing, Peoples R China 3.Univ Calif Los Angeles, Semel Inst Neurosci & Human Behav, Ctr Neurobehav Genet, Los Angeles, CA 90024 USA 4.Univ Calif Los Angeles, Dept Comp Sci, Los Angeles, CA 90024 USA 5.Peking Univ, Inst Populat Res, Beijing, Peoples R China 6.Lanzhou Univ, Sch Informat Sci & Engn, Lanzhou, Gansu, Peoples R China |
First Author Affilication | Institute of Psychology, Chinese Academy of Sciences |
Corresponding Author Affilication | Institute of Psychology, Chinese Academy of Sciences |
Recommended Citation GB/T 7714 | Pan, Wei,Flint, Jonathan,Shenhav, Liat,et al. Re-examining the robustness of voice features in predicting depression: Compared with baseline of confounders[J]. PLOS ONE,2019,14(6):14. |
APA | Pan, Wei.,Flint, Jonathan.,Shenhav, Liat.,Liu, Tianli.,Liu, Mingming.,...&Zhu, Tingshao.(2019).Re-examining the robustness of voice features in predicting depression: Compared with baseline of confounders.PLOS ONE,14(6),14. |
MLA | Pan, Wei,et al."Re-examining the robustness of voice features in predicting depression: Compared with baseline of confounders".PLOS ONE 14.6(2019):14. |
Files in This Item: | ||||||
File Name/Size | DocType | Version | Access | License | ||
Re-examining the rob(557KB) | 期刊论文 | 出版稿 | 限制开放 | CC BY-NC-SA | Application Full Text |
Items in the repository are protected by copyright, with all rights reserved, unless otherwise indicated.
Edit Comment