Diagnosis of Parkinson’s disease by eliciting trait-specific eye movements in multi-visual tasks
Abstract Background Parkinson’s Disease (PD) is a neurodegenerative disorder, and eye movement abnormalities are a significant symptom of its diagnosis. In this paper, we developed a multi-task driven by eye movement in a virtual reality (VR) environment to elicit PD-specific eye movement abnormalit...
Saved in:
| Main Authors: | , , , , , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
BMC
2025-01-01
|
| Series: | Journal of Translational Medicine |
| Subjects: | |
| Online Access: | https://doi.org/10.1186/s12967-024-06044-3 |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1832594516167622656 |
|---|---|
| author | Maosong Jiang Yanzhi Liu Yanlu Cao Shufeng Xia Fei Teng Wenzhi Zhao Yongzhong Lin Wenlong Liu |
| author_facet | Maosong Jiang Yanzhi Liu Yanlu Cao Shufeng Xia Fei Teng Wenzhi Zhao Yongzhong Lin Wenlong Liu |
| author_sort | Maosong Jiang |
| collection | DOAJ |
| description | Abstract Background Parkinson’s Disease (PD) is a neurodegenerative disorder, and eye movement abnormalities are a significant symptom of its diagnosis. In this paper, we developed a multi-task driven by eye movement in a virtual reality (VR) environment to elicit PD-specific eye movement abnormalities. The abnormal features were subsequently modeled by using the proposed deep learning algorithm to achieve an auxiliary diagnosis of PD. Methods We recruited 114 PD patients and 125 healthy controls and collected their eye-tracking data in a VR environment. Participants completed a series of specific VR tasks, including gaze stability, pro-saccades, anti-saccades, and smooth pursuit. After the tasks, eye movement features were extracted from the behaviors of fixations, saccades, and smooth pursuit to establish a PD diagnostic model. Results The performance of the models was evaluated through cross-validation, revealing a recall of 97.65%, an accuracy of 92.73%, and a receiver operator characteristic area under the curve (ROC-AUC) of 97.08% for the proposed model. Conclusion We extracted PD-specific eye movement features from the behaviors of fixations, saccades, and smooth pursuit in a VR environment to create a model with high accuracy and recall for PD diagnosis. Our method provides physicians with a new auxiliary tool to improve the prognosis and quality of life of PD patients. |
| format | Article |
| id | doaj-art-deb16c70caa543b7bc1497a589b4c344 |
| institution | Kabale University |
| issn | 1479-5876 |
| language | English |
| publishDate | 2025-01-01 |
| publisher | BMC |
| record_format | Article |
| series | Journal of Translational Medicine |
| spelling | doaj-art-deb16c70caa543b7bc1497a589b4c3442025-01-19T12:37:08ZengBMCJournal of Translational Medicine1479-58762025-01-0123111310.1186/s12967-024-06044-3Diagnosis of Parkinson’s disease by eliciting trait-specific eye movements in multi-visual tasksMaosong Jiang0Yanzhi Liu1Yanlu Cao2Shufeng Xia3Fei Teng4Wenzhi Zhao5Yongzhong Lin6Wenlong Liu7School of Information and Communication Engineering, Dalian University of TechnologyDepartment of Neurology, The Second Affiliated Hospital of Dalian Medical UniversitySchool of Information and Communication Engineering, Dalian University of TechnologySchool of Information and Communication Engineering, Dalian University of TechnologyDepartment of Geriatrics, Central Hospital of Dalian University of TechnologyDepartment of Orthopedic Surgery, The Second Affiliated Hospital of Dalian Medical UniversityDepartment of Neurology, The Second Affiliated Hospital of Dalian Medical UniversitySchool of Information and Communication Engineering, Dalian University of TechnologyAbstract Background Parkinson’s Disease (PD) is a neurodegenerative disorder, and eye movement abnormalities are a significant symptom of its diagnosis. In this paper, we developed a multi-task driven by eye movement in a virtual reality (VR) environment to elicit PD-specific eye movement abnormalities. The abnormal features were subsequently modeled by using the proposed deep learning algorithm to achieve an auxiliary diagnosis of PD. Methods We recruited 114 PD patients and 125 healthy controls and collected their eye-tracking data in a VR environment. Participants completed a series of specific VR tasks, including gaze stability, pro-saccades, anti-saccades, and smooth pursuit. After the tasks, eye movement features were extracted from the behaviors of fixations, saccades, and smooth pursuit to establish a PD diagnostic model. Results The performance of the models was evaluated through cross-validation, revealing a recall of 97.65%, an accuracy of 92.73%, and a receiver operator characteristic area under the curve (ROC-AUC) of 97.08% for the proposed model. Conclusion We extracted PD-specific eye movement features from the behaviors of fixations, saccades, and smooth pursuit in a VR environment to create a model with high accuracy and recall for PD diagnosis. Our method provides physicians with a new auxiliary tool to improve the prognosis and quality of life of PD patients.https://doi.org/10.1186/s12967-024-06044-3Parkinson’s diseaseEye movement abnormalitiesVirtual realityEye trackingDeep learning |
| spellingShingle | Maosong Jiang Yanzhi Liu Yanlu Cao Shufeng Xia Fei Teng Wenzhi Zhao Yongzhong Lin Wenlong Liu Diagnosis of Parkinson’s disease by eliciting trait-specific eye movements in multi-visual tasks Journal of Translational Medicine Parkinson’s disease Eye movement abnormalities Virtual reality Eye tracking Deep learning |
| title | Diagnosis of Parkinson’s disease by eliciting trait-specific eye movements in multi-visual tasks |
| title_full | Diagnosis of Parkinson’s disease by eliciting trait-specific eye movements in multi-visual tasks |
| title_fullStr | Diagnosis of Parkinson’s disease by eliciting trait-specific eye movements in multi-visual tasks |
| title_full_unstemmed | Diagnosis of Parkinson’s disease by eliciting trait-specific eye movements in multi-visual tasks |
| title_short | Diagnosis of Parkinson’s disease by eliciting trait-specific eye movements in multi-visual tasks |
| title_sort | diagnosis of parkinson s disease by eliciting trait specific eye movements in multi visual tasks |
| topic | Parkinson’s disease Eye movement abnormalities Virtual reality Eye tracking Deep learning |
| url | https://doi.org/10.1186/s12967-024-06044-3 |
| work_keys_str_mv | AT maosongjiang diagnosisofparkinsonsdiseasebyelicitingtraitspecificeyemovementsinmultivisualtasks AT yanzhiliu diagnosisofparkinsonsdiseasebyelicitingtraitspecificeyemovementsinmultivisualtasks AT yanlucao diagnosisofparkinsonsdiseasebyelicitingtraitspecificeyemovementsinmultivisualtasks AT shufengxia diagnosisofparkinsonsdiseasebyelicitingtraitspecificeyemovementsinmultivisualtasks AT feiteng diagnosisofparkinsonsdiseasebyelicitingtraitspecificeyemovementsinmultivisualtasks AT wenzhizhao diagnosisofparkinsonsdiseasebyelicitingtraitspecificeyemovementsinmultivisualtasks AT yongzhonglin diagnosisofparkinsonsdiseasebyelicitingtraitspecificeyemovementsinmultivisualtasks AT wenlongliu diagnosisofparkinsonsdiseasebyelicitingtraitspecificeyemovementsinmultivisualtasks |