Deep Learning Model to Evaluate Sensorimotor System Ability in Patients With Dizziness for Postural Control
Balanced posture without dizziness is achieved via harmonious coordination of visual, vestibular, and somatosensory systems. Specific frequency bands of center of pressure (COP) signals during quiet standing are closely related to the sensory inputs of the sensorimotor system. In this study, we prop...
| Main Authors: | , , , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
IEEE
2024-01-01
|
| Series: | IEEE Transactions on Neural Systems and Rehabilitation Engineering |
| Subjects: | |
| Online Access: | https://ieeexplore.ieee.org/document/10474395/ |
| _version_ | 1797243403232083968 |
|---|---|
| author | Ahnryul Choi Euyhyun Park Tae Hyong Kim Seungheon Chae Gi Jung Im Joung Hwan Mun |
| author_facet | Ahnryul Choi Euyhyun Park Tae Hyong Kim Seungheon Chae Gi Jung Im Joung Hwan Mun |
| author_sort | Ahnryul Choi |
| collection | DOAJ |
| description | Balanced posture without dizziness is achieved via harmonious coordination of visual, vestibular, and somatosensory systems. Specific frequency bands of center of pressure (COP) signals during quiet standing are closely related to the sensory inputs of the sensorimotor system. In this study, we proposed a deep learning-based novel protocol using the COP signal frequencies to estimate the equilibrium score (ES), a sensory system contribution. Sensory organization test was performed with normal controls (n=125), patients with Meniere’s disease (n=72) and vestibular neuritis (n=105). The COP signals preprocessed via filtering, detrending and augmenting during quiet standing were converted to frequency domains utilizing Short-time Fourier Transform. Four different types of CNN backbone including GoogleNet, ResNet-18, SqueezeNet, and VGG16 were trained and tested using the frequency transformed data of COP and the ES under conditions #2 to #6. Additionally, the 100 original output classes (1 to 100 ESs) were encoded into 50, 20, 10 and 5 sub-classes to improve the performance of the prediction model. Absolute difference between the measured and predicted ES was about 1.7 (ResNet-18 with encoding of 20 sub-classes). The average error of each sensory analysis calculated using the measured ES and predicted ES was approximately 1.0%. The results suggest that the sensory system contribution of patients with dizziness can be quantitatively assessed using only the COP signal from a single test of standing posture. This study has potential to reduce balance testing time (spent on six conditions with three trials each in sensory organization test) and the size of computerized dynamic posturography (movable visual surround and force plate), and helps achieve the widespread application of the balance assessment. |
| first_indexed | 2024-04-24T18:54:33Z |
| format | Article |
| id | doaj.art-ea4f5197b3304220a276d32bd42a6602 |
| institution | Directory Open Access Journal |
| issn | 1558-0210 |
| language | English |
| last_indexed | 2024-04-24T18:54:33Z |
| publishDate | 2024-01-01 |
| publisher | IEEE |
| record_format | Article |
| series | IEEE Transactions on Neural Systems and Rehabilitation Engineering |
| spelling | doaj.art-ea4f5197b3304220a276d32bd42a66022024-03-26T17:47:04ZengIEEEIEEE Transactions on Neural Systems and Rehabilitation Engineering1558-02102024-01-01321292130110.1109/TNSRE.2024.337811210474395Deep Learning Model to Evaluate Sensorimotor System Ability in Patients With Dizziness for Postural ControlAhnryul Choi0Euyhyun Park1Tae Hyong Kim2https://orcid.org/0000-0001-7355-3886Seungheon Chae3Gi Jung Im4Joung Hwan Mun5https://orcid.org/0000-0003-4213-785XDepartment of Biomedical Engineering, College of Medical Convergence, Catholic Kwandong University, Gangneung, Republic of KoreaDepartment of Otorhinolaryngology-Head and Neck Surgery, Korea University College of Medicine, Seongbuk, Republic of KoreaDepartment of Bio-Mechatronic Engineering, College of Biotechnology and Bioengineering, Sungkyunkwan University, Jangan, Suwon, Republic of KoreaDepartment of Bio-Mechatronic Engineering, College of Biotechnology and Bioengineering, Sungkyunkwan University, Jangan, Suwon, Republic of KoreaDepartment of Otorhinolaryngology-Head and Neck Surgery, Korea University College of Medicine, Seongbuk, Republic of KoreaDepartment of Bio-Mechatronic Engineering, College of Biotechnology and Bioengineering, Sungkyunkwan University, Jangan, Suwon, Republic of KoreaBalanced posture without dizziness is achieved via harmonious coordination of visual, vestibular, and somatosensory systems. Specific frequency bands of center of pressure (COP) signals during quiet standing are closely related to the sensory inputs of the sensorimotor system. In this study, we proposed a deep learning-based novel protocol using the COP signal frequencies to estimate the equilibrium score (ES), a sensory system contribution. Sensory organization test was performed with normal controls (n=125), patients with Meniere’s disease (n=72) and vestibular neuritis (n=105). The COP signals preprocessed via filtering, detrending and augmenting during quiet standing were converted to frequency domains utilizing Short-time Fourier Transform. Four different types of CNN backbone including GoogleNet, ResNet-18, SqueezeNet, and VGG16 were trained and tested using the frequency transformed data of COP and the ES under conditions #2 to #6. Additionally, the 100 original output classes (1 to 100 ESs) were encoded into 50, 20, 10 and 5 sub-classes to improve the performance of the prediction model. Absolute difference between the measured and predicted ES was about 1.7 (ResNet-18 with encoding of 20 sub-classes). The average error of each sensory analysis calculated using the measured ES and predicted ES was approximately 1.0%. The results suggest that the sensory system contribution of patients with dizziness can be quantitatively assessed using only the COP signal from a single test of standing posture. This study has potential to reduce balance testing time (spent on six conditions with three trials each in sensory organization test) and the size of computerized dynamic posturography (movable visual surround and force plate), and helps achieve the widespread application of the balance assessment.https://ieeexplore.ieee.org/document/10474395/Sensorimotor systembalancedizziness rehabilitationpostural controldeep learningMeniere’s disease |
| spellingShingle | Ahnryul Choi Euyhyun Park Tae Hyong Kim Seungheon Chae Gi Jung Im Joung Hwan Mun Deep Learning Model to Evaluate Sensorimotor System Ability in Patients With Dizziness for Postural Control IEEE Transactions on Neural Systems and Rehabilitation Engineering Sensorimotor system balance dizziness rehabilitation postural control deep learning Meniere’s disease |
| title | Deep Learning Model to Evaluate Sensorimotor System Ability in Patients With Dizziness for Postural Control |
| title_full | Deep Learning Model to Evaluate Sensorimotor System Ability in Patients With Dizziness for Postural Control |
| title_fullStr | Deep Learning Model to Evaluate Sensorimotor System Ability in Patients With Dizziness for Postural Control |
| title_full_unstemmed | Deep Learning Model to Evaluate Sensorimotor System Ability in Patients With Dizziness for Postural Control |
| title_short | Deep Learning Model to Evaluate Sensorimotor System Ability in Patients With Dizziness for Postural Control |
| title_sort | deep learning model to evaluate sensorimotor system ability in patients with dizziness for postural control |
| topic | Sensorimotor system balance dizziness rehabilitation postural control deep learning Meniere’s disease |
| url | https://ieeexplore.ieee.org/document/10474395/ |
| work_keys_str_mv | AT ahnryulchoi deeplearningmodeltoevaluatesensorimotorsystemabilityinpatientswithdizzinessforposturalcontrol AT euyhyunpark deeplearningmodeltoevaluatesensorimotorsystemabilityinpatientswithdizzinessforposturalcontrol AT taehyongkim deeplearningmodeltoevaluatesensorimotorsystemabilityinpatientswithdizzinessforposturalcontrol AT seungheonchae deeplearningmodeltoevaluatesensorimotorsystemabilityinpatientswithdizzinessforposturalcontrol AT gijungim deeplearningmodeltoevaluatesensorimotorsystemabilityinpatientswithdizzinessforposturalcontrol AT jounghwanmun deeplearningmodeltoevaluatesensorimotorsystemabilityinpatientswithdizzinessforposturalcontrol |