1
|
Zhang N, Chen S, Jiang K, Ge W, Im H, Guan S, Li Z, Wei C, Wang P, Zhu Y, Zhao G, Liu L, Chen C, Chang H, Wang Q. Individualized prediction of anxiety and depressive symptoms using gray matter volume in a non-clinical population. Cereb Cortex 2024; 34:bhae121. [PMID: 38584086 DOI: 10.1093/cercor/bhae121] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [Abstract] [Key Words] [MESH Headings] [Grants] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Received: 01/24/2024] [Revised: 03/03/2024] [Accepted: 03/05/2024] [Indexed: 04/09/2024] Open
Abstract
Machine learning is an emerging tool in clinical psychology and neuroscience for the individualized prediction of psychiatric symptoms. However, its application in non-clinical populations is still in its infancy. Given the widespread morphological changes observed in psychiatric disorders, our study applies five supervised machine learning regression algorithms-ridge regression, support vector regression, partial least squares regression, least absolute shrinkage and selection operator regression, and Elastic-Net regression-to predict anxiety and depressive symptom scores. We base these predictions on the whole-brain gray matter volume in a large non-clinical sample (n = 425). Our results demonstrate that machine learning algorithms can effectively predict individual variability in anxiety and depressive symptoms, as measured by the Mood and Anxiety Symptoms Questionnaire. The most discriminative features contributing to the prediction models were primarily located in the prefrontal-parietal, temporal, visual, and sub-cortical regions (e.g. amygdala, hippocampus, and putamen). These regions showed distinct patterns for anxious arousal and high positive affect in three of the five models (partial least squares regression, support vector regression, and ridge regression). Importantly, these predictions were consistent across genders and robust to demographic variability (e.g. age, parental education, etc.). Our findings offer critical insights into the distinct brain morphological patterns underlying specific components of anxiety and depressive symptoms, supporting the existing tripartite theory from a neuroimaging perspective.
Collapse
Affiliation(s)
- Ning Zhang
- School of Mathematical Sciences, Tianjin Normal University, Tianjin 300387, China
| | - Shuning Chen
- Faculty of Psychology, Tianjin Normal University, Tianjin 300387, China
| | - Keying Jiang
- Faculty of Psychology, Tianjin Normal University, Tianjin 300387, China
| | - Wei Ge
- Faculty of Psychology, Tianjin Normal University, Tianjin 300387, China
| | - Hohjin Im
- Independent Researcher, United States
| | - Shunping Guan
- Faculty of Psychology, Tianjin Normal University, Tianjin 300387, China
| | - Zixi Li
- Faculty of Psychology, Tianjin Normal University, Tianjin 300387, China
| | - Chuqiao Wei
- Faculty of Psychology, Tianjin Normal University, Tianjin 300387, China
| | - Pinchun Wang
- Faculty of Psychology, Tianjin Normal University, Tianjin 300387, China
| | - Ye Zhu
- Faculty of Psychology, Tianjin Normal University, Tianjin 300387, China
| | - Guang Zhao
- Faculty of Psychology, Tianjin Normal University, Tianjin 300387, China
| | - Liqing Liu
- Faculty of Psychology, Tianjin Normal University, Tianjin 300387, China
| | - Chunhui Chen
- State Key Laboratory of Cognitive Neuroscience and Learning & IDG/McGovern Institute for Brain Research, Beijing Normal University, Beijing 100875, China
| | - Huibin Chang
- School of Mathematical Sciences, Tianjin Normal University, Tianjin 300387, China
| | - Qiang Wang
- Faculty of Psychology, Tianjin Normal University, Tianjin 300387, China
- Key Laboratory of Philosophy and Social Science of Anhui Province on Adolescent Mental Health and Crisis Intelligence Intervention, Hefei Normal University, Hefei, 230061, China
| |
Collapse
|
2
|
Hyde MK, Chambers SK, Shum D, Ip D, Dunn J. Psycho-oncology assessment in Chinese populations: a systematic review of quality of life and psychosocial measures. Eur J Cancer Care (Engl) 2015; 25:691-718. [PMID: 26292029 DOI: 10.1111/ecc.12367] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [Abstract] [Key Words] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Accepted: 07/02/2015] [Indexed: 11/26/2022]
Abstract
This systematic review describes psychosocial and quality of life (QOL) measures used in psycho-oncology research with cancer patients and caregivers in China. Medline and PsycINFO databases were searched (1980-2014). Studies reviewed met the following criteria: English language; peer-reviewed; sampled Chinese cancer patients/caregivers; developed, validated or assessed psychometric properties of psychosocial or QOL outcome measures; and reported validation data. The review examined characteristics of measures and participants, translation and cultural adaptation processes and psychometric properties of the measures. Ninety five studies met review criteria. Common characteristics of studies reviewed were they: assessed primarily QOL measures, sampled patients with breast, colorectal, or head and neck cancer, and validated existing measures (>80%) originating in North America or Europe. Few studies reported difficulties translating measures. Regarding psychometric properties of the measures >50% of studies reported subscale reliabilities <α = 0.70, <50% reported test-retest reliability, and <30% reported divergent validity. Few reported sensitivity, specificity or responsiveness. Improved accuracy and transparency of reporting for translation, cultural adaptation and psychometric testing of psychosocial measures is needed. Developing support structures for translating and validating psychosocial measures would enable this and ensure Chinese psycho-oncology clinical practice and research keeps pace with international focus on patient reported outcome measures and data management.
Collapse
Affiliation(s)
- M K Hyde
- Menzies Health Institute Queensland, Griffith University, Gold Coast, Qld, Australia.,Cancer Council Queensland, Spring Hill, Qld, Australia
| | - S K Chambers
- Menzies Health Institute Queensland, Griffith University, Gold Coast, Qld, Australia.,Cancer Council Queensland, Spring Hill, Qld, Australia.,Health and Wellness Institute, Edith Cowan University, Perth, WA, Australia.,Centre for Clinical Research, The University of Queensland, Herston, Qld, Australia.,Prostate Cancer Foundation of Australia, St Leonards, NSW, Australia
| | - D Shum
- Menzies Health Institute Queensland, Griffith University, Gold Coast, Qld, Australia
| | - D Ip
- The Hong Kong Polytechnic University, Hung Hom, Kowloon, Hong Kong
| | - J Dunn
- Menzies Health Institute Queensland, Griffith University, Gold Coast, Qld, Australia.,Cancer Council Queensland, Spring Hill, Qld, Australia.,School of Social Science, The University of Queensland, St Lucia, Qld, Australia
| |
Collapse
|