1
|
Yu WY, Sun TH, Hsu KC, Wang CC, Chien SY, Tsai CH, Yang YW. Comparative analysis of machine learning algorithms for Alzheimer's disease classification using EEG signals and genetic information. Comput Biol Med 2024; 176:108621. [PMID: 38763067 DOI: 10.1016/j.compbiomed.2024.108621] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [Abstract] [Key Words] [MESH Headings] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Received: 01/29/2024] [Revised: 05/13/2024] [Accepted: 05/15/2024] [Indexed: 05/21/2024]
Abstract
Alzheimer's disease (AD) is a progressive neurodegenerative disorder characterized by cognitive decline, memory impairments, and behavioral changes. The presence of abnormal beta-amyloid plaques and tau protein tangles in the brain is known to be associated with AD. However, current limitations of imaging technology hinder the direct detection of these substances. Consequently, researchers are exploring alternative approaches, such as indirect assessments involving monitoring brain signals, cognitive decline levels, and blood biomarkers. Recent studies have highlighted the potential of integrating genetic information into these approaches to enhance early detection and diagnosis, offering a more comprehensive understanding of AD pathology beyond the constraints of existing imaging methods. Our study utilized electroencephalography (EEG) signals, genotypes, and polygenic risk scores (PRSs) as features for machine learning models. We compared the performance of gradient boosting (XGB), random forest (RF), and support vector machine (SVM) to determine the optimal model. Statistical analysis revealed significant correlations between EEG signals and clinical manifestations, demonstrating the ability to distinguish the complexity of AD from other diseases by using genetic information. By integrating EEG with genetic data in an SVM model, we achieved exceptional classification performance, with an accuracy of 0.920 and an area under the curve of 0.916. This study presents a novel approach of utilizing real-time EEG data and genetic background information for multimodal machine learning. The experimental results validate the effectiveness of this concept, providing deeper insights into the actual condition of patients with AD and overcoming the limitations associated with single-oriented data.
Collapse
Affiliation(s)
- Wei-Yang Yu
- Artificial Intelligence Center, China Medical University Hospital, Taichung, 40447, Taiwan
| | - Ting-Hsuan Sun
- Artificial Intelligence Center, China Medical University Hospital, Taichung, 40447, Taiwan
| | - Kai-Cheng Hsu
- Artificial Intelligence Center, China Medical University Hospital, Taichung, 40447, Taiwan; Department of Neurology, China Medical University Hospital, Taichung, 40447, Taiwan; Department of Medicine, China Medical University, Taichung, 40402, Taiwan
| | - Chia-Chun Wang
- Artificial Intelligence Center, China Medical University Hospital, Taichung, 40447, Taiwan
| | - Shang-Yu Chien
- Artificial Intelligence Center, China Medical University Hospital, Taichung, 40447, Taiwan
| | - Chon-Haw Tsai
- Department of Neurology, China Medical University Hospital, Taichung, 40447, Taiwan; School of Medicine, College of Medicine, China Medical University, Taichung, 40402, Taiwan; Neuroscience Laboratory, Department of Neurology, China Medical University Hospital, Taichung, 40447, Taiwan; Neuroscience and Brain Disease Center, College of Medicine, China Medical University, 40402, Taichung, Taiwan
| | - Yu-Wan Yang
- Department of Neurology, China Medical University Hospital, Taichung, 40447, Taiwan; School of Medicine, College of Medicine, China Medical University, Taichung, 40402, Taiwan.
| |
Collapse
|
2
|
Ue S, Nakahama K, Hayashi J, Ohgomori T. Cortical activity associated with the maintenance of balance during unstable stances. PeerJ 2024; 12:e17313. [PMID: 38708344 PMCID: PMC11067896 DOI: 10.7717/peerj.17313] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [Abstract] [Key Words] [MESH Headings] [Track Full Text] [Figures] [Journal Information] [Subscribe] [Scholar Register] [Received: 02/02/2024] [Accepted: 04/08/2024] [Indexed: 05/07/2024] Open
Abstract
Background Humans continuously maintain and adjust posture during gait, standing, and sitting. The difficulty of postural control is reportedly increased during unstable stances, such as unipedal standing and with closed eyes. Although balance is slightly impaired in healthy young adults in such unstable stances, they rarely fall. The brain recognizes the change in sensory inputs and outputs motor commands to the musculoskeletal system. However, such changes in cortical activity associated with the maintenance of balance following periods of instability require further clarified. Methods In this study, a total of 15 male participants performed two postural control tasks and the center of pressure displacement and electroencephalogram were simultaneously measured. In addition, the correlation between amplitude of center of pressure displacement and power spectral density of electroencephalogram was analyzed. Results The movement of the center of pressure was larger in unipedal standing than in bipedal standing under both eye open and eye closed conditions. It was also larger under the eye closed condition compared with when the eyes were open in unipedal standing. The amplitude of high-frequency bandwidth (1-3 Hz) of the center of pressure displacement was larger during more difficult postural tasks than during easier ones, suggesting that the continuous maintenance of posture was required. The power spectral densities of the theta activity in the frontal area and the gamma activity in the parietal area were higher during more difficult postural tasks than during easier ones across two postural control tasks, and these correlate with the increase in amplitude of high-frequency bandwidth of the center of pressure displacement. Conclusions Taken together, specific activation patterns of the neocortex are suggested to be important for the postural maintenance during unstable stances.
Collapse
Affiliation(s)
- Shoma Ue
- Department of Rehabilitation, Osaka Kawasaki Rehabilitation University, Kaizuka, Osaka, Japan
| | - Kakeru Nakahama
- Department of Rehabilitation, Osaka Kawasaki Rehabilitation University, Kaizuka, Osaka, Japan
| | - Junpei Hayashi
- Department of Rehabilitation, Osaka Kawasaki Rehabilitation University, Kaizuka, Osaka, Japan
| | - Tomohiro Ohgomori
- Department of Rehabilitation, Osaka Kawasaki Rehabilitation University, Kaizuka, Osaka, Japan
| |
Collapse
|
3
|
Zhang H, Zhou QQ, Chen H, Hu XQ, Li WG, Bai Y, Han JX, Wang Y, Liang ZH, Chen D, Cong FY, Yan JQ, Li XL. The applied principles of EEG analysis methods in neuroscience and clinical neurology. Mil Med Res 2023; 10:67. [PMID: 38115158 PMCID: PMC10729551 DOI: 10.1186/s40779-023-00502-7] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [Abstract] [Key Words] [MESH Headings] [Grants] [Track Full Text] [Journal Information] [Submit a Manuscript] [Subscribe] [Scholar Register] [Received: 10/25/2023] [Accepted: 11/23/2023] [Indexed: 12/21/2023] Open
Abstract
Electroencephalography (EEG) is a non-invasive measurement method for brain activity. Due to its safety, high resolution, and hypersensitivity to dynamic changes in brain neural signals, EEG has aroused much interest in scientific research and medical fields. This article reviews the types of EEG signals, multiple EEG signal analysis methods, and the application of relevant methods in the neuroscience field and for diagnosing neurological diseases. First, three types of EEG signals, including time-invariant EEG, accurate event-related EEG, and random event-related EEG, are introduced. Second, five main directions for the methods of EEG analysis, including power spectrum analysis, time-frequency analysis, connectivity analysis, source localization methods, and machine learning methods, are described in the main section, along with different sub-methods and effect evaluations for solving the same problem. Finally, the application scenarios of different EEG analysis methods are emphasized, and the advantages and disadvantages of similar methods are distinguished. This article is expected to assist researchers in selecting suitable EEG analysis methods based on their research objectives, provide references for subsequent research, and summarize current issues and prospects for the future.
Collapse
Affiliation(s)
- Hao Zhang
- School of Systems Science, Beijing Normal University, Beijing, 100875, China
| | - Qing-Qi Zhou
- College of Electrical and Control Engineering, North China University of Technology, Beijing, 100041, China
| | - He Chen
- School of Automation Science and Engineering, South China University of Technology, Guangzhou, 510641, China
| | - Xiao-Qing Hu
- Department of Psychology, the State Key Laboratory of Brain and Cognitive Sciences, The University of Hong Kong, Hong Kong SAR, 999077, China
- HKU-Shenzhen Institute of Research and Innovation, Shenzhen, 518057, Guangdong, China
| | - Wei-Guang Li
- Department of Health Technology and Informatics, The Hong Kong Polytechnic University, Hong Kong SAR, 999077, China
| | - Yang Bai
- Department of Rehabilitation Medicine, the First Affiliated Hospital of Nanchang University, Nanchang, 330006, China
- Rehabilitation Medicine Clinical Research Center of Jiangxi Province, Nanchang, 330006, China
| | - Jun-Xia Han
- Beijing Key Laboratory of Learning and Cognition, School of Psychology, Capital Normal University, Beijing, 100048, China
| | - Yao Wang
- School of Communication Science, Beijing Language and Culture University, Beijing, 100083, China
| | - Zhen-Hu Liang
- Institute of Electrical Engineering, Yanshan University, Qinhuangdao, 066004, Hebei, China.
| | - Dan Chen
- School of Computer Science, Wuhan University, Wuhan, 430072, China.
| | - Feng-Yu Cong
- School of Biomedical Engineering, Faculty of Electronic Information and Electrical Engineering, Dalian University of Technology, Dalian, 116081, Liaoning, China.
| | - Jia-Qing Yan
- College of Electrical and Control Engineering, North China University of Technology, Beijing, 100041, China.
| | - Xiao-Li Li
- School of Automation Science and Engineering, South China University of Technology, Guangzhou, 510641, China.
- Guangdong Artificial Intelligence and Digital Economy Laboratory (Guangzhou), Guangzhou, 510335, China.
| |
Collapse
|