Identifying depression with mixed features: the potential value of eye-tracking features
Eye-tracking features, especially the velocity of overlapping saccades and free viewing task completion time, hold potential as non-invasive biomarkers for the identification of DMF. The integration of these parameters into the XGBoost machine learning model significantly improved the accuracy of DMF diagnosis, offering a promising approach for enhancing clinical decision-making in psychiatric settings.
Authors
- Huang Xue-jun (ORCID: https://orcid.org/0000-0003-2501-8840)
- Wenjie Ou
- Qiaoyan Guan
- Mali Jiang (ORCID: https://orcid.org/0000-0003-3934-2668)
- Hong-Bei Chen
- Zhen Xiao
- Yan Huang
- Yu-Jiun Lin (ORCID: https://orcid.org/0000-0003-2349-195X)
- Yuefeng Ji (ORCID: https://orcid.org/0000-0002-6618-272X)
- Qian-Ting Yu (ORCID: https://orcid.org/0009-0005-9603-273X)
- Jifan Zhang
- Xingchang Liu (ORCID: https://orcid.org/0000-0001-8109-3795)
- Ming Chen (ORCID: https://orcid.org/0000-0001-9869-4036)
- Yarong Wang (ORCID: https://orcid.org/0000-0002-0551-5412)
- Qiao Xiao (ORCID: https://orcid.org/0000-0002-9819-2818)
Institutions
- First Affiliated Hospital of Guangzhou Medical University (CN)
- Guangdong Academy of Medical Sciences (CN)
- Guangdong Provincial People's Hospital (CN)
- Southern Medical University (CN)
- Guangzhou Medical University (CN)
Publication Details
- Journal
- Frontiers in Neurology
- Published
- 2025-03-19
- DOI
- https://doi.org/10.3389/fneur.2025.1555630
- Citations
- 3
- Primary Topic
- Bipolar Disorder and Treatment
- Type
- article
- Field-Weighted Citation Impact
- 4.41