Identifying Psychological Symptoms Based on Facial Movements
Background: Many methods have been proposed to automatically identify the presence of mental illness, but these have mostly focused on one specific mental illness. In some non-professional scenarios, it would be more helpful to understand an individual's mental health status from all perspectiv...
| Main Authors: | , , , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
Frontiers Media S.A.
2020-12-01
|
| Series: | Frontiers in Psychiatry |
| Subjects: | |
| Online Access: | https://www.frontiersin.org/articles/10.3389/fpsyt.2020.607890/full |
| _version_ | 1818394029286490112 |
|---|---|
| author | Xiaoyang Wang Xiaoyang Wang Yilin Wang Yilin Wang Mingjie Zhou Mingjie Zhou Baobin Li Baobin Li Xiaoqian Liu Xiaoqian Liu Tingshao Zhu Tingshao Zhu |
| author_facet | Xiaoyang Wang Xiaoyang Wang Yilin Wang Yilin Wang Mingjie Zhou Mingjie Zhou Baobin Li Baobin Li Xiaoqian Liu Xiaoqian Liu Tingshao Zhu Tingshao Zhu |
| author_sort | Xiaoyang Wang |
| collection | DOAJ |
| description | Background: Many methods have been proposed to automatically identify the presence of mental illness, but these have mostly focused on one specific mental illness. In some non-professional scenarios, it would be more helpful to understand an individual's mental health status from all perspectives.Methods: We recruited 100 participants. Their multi-dimensional psychological symptoms of mental health were evaluated using the Symptom Checklist 90 (SCL-90) and their facial movements under neutral stimulation were recorded using Microsoft Kinect. We extracted the time-series characteristics of the key points as the input, and the subscale scores of the SCL-90 as the output to build facial prediction models. Finally, the convergent validity, discriminant validity, criterion validity, and the split-half reliability were respectively assessed using a multitrait-multimethod matrix and correlation coefficients.Results: The correlation coefficients between the predicted values and actual scores were 0.26 and 0.42 (P < 0.01), which indicated good criterion validity. All models except depression had high convergent validity but low discriminant validity. Results also indicated good levels of split-half reliability for each model [from 0.516 (hostility) to 0.817 (interpersonal sensitivity)] (P < 0.001).Conclusion: The validity and reliability of facial prediction models were confirmed for the measurement of mental health based on the SCL-90. Our research demonstrated that fine-grained aspects of mental health can be identified from the face, and provided a feasible evaluation method for multi-dimensional prediction models. |
| first_indexed | 2024-12-14T05:54:42Z |
| format | Article |
| id | doaj.art-d1e39e2624db4bca8be1e73f51f0fdba |
| institution | Directory Open Access Journal |
| issn | 1664-0640 |
| language | English |
| last_indexed | 2024-12-14T05:54:42Z |
| publishDate | 2020-12-01 |
| publisher | Frontiers Media S.A. |
| record_format | Article |
| series | Frontiers in Psychiatry |
| spelling | doaj.art-d1e39e2624db4bca8be1e73f51f0fdba2022-12-21T23:14:37ZengFrontiers Media S.A.Frontiers in Psychiatry1664-06402020-12-011110.3389/fpsyt.2020.607890607890Identifying Psychological Symptoms Based on Facial MovementsXiaoyang Wang0Xiaoyang Wang1Yilin Wang2Yilin Wang3Mingjie Zhou4Mingjie Zhou5Baobin Li6Baobin Li7Xiaoqian Liu8Xiaoqian Liu9Tingshao Zhu10Tingshao Zhu11Institute of Psychology, Chinese Academy of Sciences, Beijing, ChinaDepartment of Psychology, University of Chinese Academy of Sciences, Beijing, ChinaInstitute of Psychology, Chinese Academy of Sciences, Beijing, ChinaDepartment of Psychology, University of Chinese Academy of Sciences, Beijing, ChinaInstitute of Psychology, Chinese Academy of Sciences, Beijing, ChinaDepartment of Psychology, University of Chinese Academy of Sciences, Beijing, ChinaDepartment of Psychology, University of Chinese Academy of Sciences, Beijing, ChinaSchool of Computer Science and Technology, University of Chinese Academy of Sciences, Beijing, ChinaInstitute of Psychology, Chinese Academy of Sciences, Beijing, ChinaDepartment of Psychology, University of Chinese Academy of Sciences, Beijing, ChinaInstitute of Psychology, Chinese Academy of Sciences, Beijing, ChinaDepartment of Psychology, University of Chinese Academy of Sciences, Beijing, ChinaBackground: Many methods have been proposed to automatically identify the presence of mental illness, but these have mostly focused on one specific mental illness. In some non-professional scenarios, it would be more helpful to understand an individual's mental health status from all perspectives.Methods: We recruited 100 participants. Their multi-dimensional psychological symptoms of mental health were evaluated using the Symptom Checklist 90 (SCL-90) and their facial movements under neutral stimulation were recorded using Microsoft Kinect. We extracted the time-series characteristics of the key points as the input, and the subscale scores of the SCL-90 as the output to build facial prediction models. Finally, the convergent validity, discriminant validity, criterion validity, and the split-half reliability were respectively assessed using a multitrait-multimethod matrix and correlation coefficients.Results: The correlation coefficients between the predicted values and actual scores were 0.26 and 0.42 (P < 0.01), which indicated good criterion validity. All models except depression had high convergent validity but low discriminant validity. Results also indicated good levels of split-half reliability for each model [from 0.516 (hostility) to 0.817 (interpersonal sensitivity)] (P < 0.001).Conclusion: The validity and reliability of facial prediction models were confirmed for the measurement of mental health based on the SCL-90. Our research demonstrated that fine-grained aspects of mental health can be identified from the face, and provided a feasible evaluation method for multi-dimensional prediction models.https://www.frontiersin.org/articles/10.3389/fpsyt.2020.607890/fullmental healthpsychological symptomsSCL-90facial movementsmachine learningmultitrait-multimethod matrix |
| spellingShingle | Xiaoyang Wang Xiaoyang Wang Yilin Wang Yilin Wang Mingjie Zhou Mingjie Zhou Baobin Li Baobin Li Xiaoqian Liu Xiaoqian Liu Tingshao Zhu Tingshao Zhu Identifying Psychological Symptoms Based on Facial Movements Frontiers in Psychiatry mental health psychological symptoms SCL-90 facial movements machine learning multitrait-multimethod matrix |
| title | Identifying Psychological Symptoms Based on Facial Movements |
| title_full | Identifying Psychological Symptoms Based on Facial Movements |
| title_fullStr | Identifying Psychological Symptoms Based on Facial Movements |
| title_full_unstemmed | Identifying Psychological Symptoms Based on Facial Movements |
| title_short | Identifying Psychological Symptoms Based on Facial Movements |
| title_sort | identifying psychological symptoms based on facial movements |
| topic | mental health psychological symptoms SCL-90 facial movements machine learning multitrait-multimethod matrix |
| url | https://www.frontiersin.org/articles/10.3389/fpsyt.2020.607890/full |
| work_keys_str_mv | AT xiaoyangwang identifyingpsychologicalsymptomsbasedonfacialmovements AT xiaoyangwang identifyingpsychologicalsymptomsbasedonfacialmovements AT yilinwang identifyingpsychologicalsymptomsbasedonfacialmovements AT yilinwang identifyingpsychologicalsymptomsbasedonfacialmovements AT mingjiezhou identifyingpsychologicalsymptomsbasedonfacialmovements AT mingjiezhou identifyingpsychologicalsymptomsbasedonfacialmovements AT baobinli identifyingpsychologicalsymptomsbasedonfacialmovements AT baobinli identifyingpsychologicalsymptomsbasedonfacialmovements AT xiaoqianliu identifyingpsychologicalsymptomsbasedonfacialmovements AT xiaoqianliu identifyingpsychologicalsymptomsbasedonfacialmovements AT tingshaozhu identifyingpsychologicalsymptomsbasedonfacialmovements AT tingshaozhu identifyingpsychologicalsymptomsbasedonfacialmovements |