1
|
Ahmed MAO, Satar YA, Darwish EM, Zanaty EA. Synergistic integration of Multi-View Brain Networks and advanced machine learning techniques for auditory disorders diagnostics. Brain Inform 2024; 11:3. [PMID: 38219249 PMCID: PMC10788326 DOI: 10.1186/s40708-023-00214-7] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [Abstract] [Key Words] [Grants] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Received: 09/21/2023] [Accepted: 12/06/2023] [Indexed: 01/16/2024] Open
Abstract
In the field of audiology, achieving accurate discrimination of auditory impairments remains a formidable challenge. Conditions such as deafness and tinnitus exert a substantial impact on patients' overall quality of life, emphasizing the urgent need for precise and efficient classification methods. This study introduces an innovative approach, utilizing Multi-View Brain Network data acquired from three distinct cohorts: 51 deaf patients, 54 with tinnitus, and 42 normal controls. Electroencephalogram (EEG) recording data were meticulously collected, focusing on 70 electrodes attached to an end-to-end key with 10 regions of interest (ROI). This data is synergistically integrated with machine learning algorithms. To tackle the inherently high-dimensional nature of brain connectivity data, principal component analysis (PCA) is employed for feature reduction, enhancing interpretability. The proposed approach undergoes evaluation using ensemble learning techniques, including Random Forest, Extra Trees, Gradient Boosting, and CatBoost. The performance of the proposed models is scrutinized across a comprehensive set of metrics, encompassing cross-validation accuracy (CVA), precision, recall, F1-score, Kappa, and Matthews correlation coefficient (MCC). The proposed models demonstrate statistical significance and effectively diagnose auditory disorders, contributing to early detection and personalized treatment, thereby enhancing patient outcomes and quality of life. Notably, they exhibit reliability and robustness, characterized by high Kappa and MCC values. This research represents a significant advancement in the intersection of audiology, neuroimaging, and machine learning, with transformative implications for clinical practice and care.
Collapse
Affiliation(s)
- Muhammad Atta Othman Ahmed
- Department of Computer Science, Faculty of Computers and Information, Luxor University, 85951, Luxor, Egypt.
| | - Yasser Abdel Satar
- Mathematics Department, Faculty of Science, Sohag University, 82511, Sohag, Egypt
| | - Eed M Darwish
- Physics Department, College of Science, Taibah University, Medina, 41411, Saudi Arabia
- Physics Department, Faculty of Science, Sohag University, 82524, Sohag, Egypt
| | - Elnomery A Zanaty
- Department of Computer Science, Faculty of Computers and Artificial Intelligence, Sohag University, 82511, Sohag, Egypt
| |
Collapse
|
2
|
Features of beta-gamma phase-amplitude coupling in cochlear implant users derived from EEG. Hear Res 2023; 428:108668. [PMID: 36543037 DOI: 10.1016/j.heares.2022.108668] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [Abstract] [Key Words] [Track Full Text] [Journal Information] [Submit a Manuscript] [Subscribe] [Scholar Register] [Received: 09/22/2022] [Revised: 12/07/2022] [Accepted: 12/12/2022] [Indexed: 12/15/2022]
Abstract
Cochlear implants (CIs) allow patients with severe to profound hearing loss to gain or regain their sense of hearing. However, the objective assessment of auditory rehabilitation in CI users remains a challenge. In particular, the utility of phase-amplitude coupling (PAC) for evaluating postoperative rehabilitation of CI users remains unknown. In the present study, we conducted an oddball paradigm with stimuli varying in sample speech syllables and collected electroencephalography (EEG) signals for 10 CI users at the time the implant was activated and 180 days after activation. Twelve normal-hearing subjects served as controls. We explored the oscillatory properties of the neural response to syllable incongruence and the cross-frequency coupling between multiple frequencies in CI users. We found that beta-gamma coupling appeared to be enhanced in CI users compared with normal controls and this difference gradually disappeared with increasing implantation time. The present results suggest that predictively encoded auditory pathways are gradually restored in CI users. In addition, the PAC feature in unilateral CI users was found to be lateralized in the auditory cortex, which was consistent with previous studies of auditory-evoked cortical activity. Therefore, PAC may be a reference biomarker for the rehabilitation of speech discrimination in CI users.
Collapse
|
3
|
Derakhshan M, Ansarian HR, Ghomshei M. Temporal variations in COVID-19: an epidemiological discussion with a practical application. J Int Med Res 2021; 49:3000605211033208. [PMID: 34369194 PMCID: PMC8358523 DOI: 10.1177/03000605211033208] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [Abstract] [Key Words] [MESH Headings] [Track Full Text] [Download PDF] [Figures] [Journal Information] [Subscribe] [Scholar Register] [Received: 01/30/2021] [Accepted: 06/29/2021] [Indexed: 11/27/2022] Open
Abstract
OBJECTIVE We aimed to characterize the temporal variation in coronavirus disease 2019 (COVID-19) infection and mortality as a possible tool to monitor and control the spread of this disease. METHODS We analyzed cyclicity and synchronicity in cases of COVID-19 infection and time series of deaths using Fourier transform, its inverse method, and statistical treatments. Epidemiological indices (e.g., case fatality rate) were used to quantify the observations in the time series. The possible causes of short-term variations are reviewed. RESULTS We observed that were both short-term and long-term variations in the COVID-19 time series. The short cycles were 7 days and synchronized among all countries. This periodicity is believed to be caused by weekly cycles in community social factors, combined with diagnostic and reporting cycles. This could also be related to virus-host-community dynamics. CONCLUSION The observed synchronized weekly cycles could serve as herd defense by providing a form of social distancing in time. The effect of such temporal distancing could be enhanced if combined with spatial distancing. Integrated spatiotemporal distancing is therefore recommended to optimize infection control strategies, taking into account the quiescent and active intervals of COVID-19.
Collapse
Affiliation(s)
- Mahnaz Derakhshan
- Conovita Technologies Inc., Winnipeg, Canada
- Queen Mary University of London Alumni, London, UK
| | - Hamid Reza Ansarian
- Conovita Technologies Inc., Winnipeg, Canada
- Easton Place Medical Center, Selkirk, Canada
- University of Manitoba Alumni, Winnipeg, Canada
| | - Mory Ghomshei
- Conovita Technologies Inc., Winnipeg, Canada
- British Columbia Institute of Technology (BCIT), Burnaby, B.C., Canada
| |
Collapse
|
4
|
Huang L, Wang CD, Chao HY. oComm: Overlapping Community Detection in Multi-View Brain Network. IEEE/ACM TRANSACTIONS ON COMPUTATIONAL BIOLOGY AND BIOINFORMATICS 2021; 18:1582-1595. [PMID: 31494557 DOI: 10.1109/tcbb.2019.2939525] [Citation(s) in RCA: 2] [Impact Index Per Article: 0.7] [Reference Citation Analysis] [Abstract] [MESH Headings] [Track Full Text] [Subscribe] [Scholar Register] [Indexed: 06/10/2023]
Abstract
Many efforts have been made on developing multi-view network community detection approaches. However, most of them can only reveal non-overlapping community structure. In this paper, we propose a novel approach for Overlapping Community Detection in Multi-view Brain Network (oComm). For modeling the overlapping community structure, a community membership strength vector is introduced for each node in each view, based on which a network generative model is designed to measure the within-view community quality. For measuring the consistency of overlapping community structures across different views, the Jaccard similarity is adopted to measure the first-order structural consistency of one node across different views, based on which a cross-view community consistency model is established. One objective function is defined by integrating the above two components. By solving the objective function via the alternative coordinate gradient ascent method, the optimal community membership strength vectors are generated, from which the multi-view overlapping community structure is obtained. Additionally, this study collects a set of EEG data of 147 subjects from Department of Otolaryngology of Sun Yat-sen Memorial Hospital, Sun Yat-sen University, based on which three multi-view brain networks are constructed. Comparison results with several existing approaches have confirmed the effectiveness of the proposed method.
Collapse
|
5
|
Wang S, Lin M, Sun L, Chen X, Fu X, Yan L, Li C, Zhang X. Neural Mechanisms of Hearing Recovery for Cochlear-Implanted Patients: An Electroencephalogram Follow-Up Study. Front Neurosci 2021; 14:624484. [PMID: 33633529 PMCID: PMC7901906 DOI: 10.3389/fnins.2020.624484] [Citation(s) in RCA: 4] [Impact Index Per Article: 1.3] [Reference Citation Analysis] [Abstract] [Key Words] [Track Full Text] [Download PDF] [Figures] [Journal Information] [Subscribe] [Scholar Register] [Received: 10/31/2020] [Accepted: 12/22/2020] [Indexed: 12/11/2022] Open
Abstract
Background Patients with severe profound hearing loss could benefit from cochlear implantation (CI). However, the neural mechanism of such benefit is still unclear. Therefore, we analyzed the electroencephalogram (EEG) and behavioral indicators of auditory function remodeling in patients with CI. Both indicators were sampled at multiple time points after implantation (1, 90, and 180 days). Methods First, the speech perception ability was evaluated with the recording of a list of Chinese words and sentences in 15 healthy controls (HC group) and 10 patients with CI (CI group). EEG data were collected using an oddball paradigm. Then, the characteristics of event-related potentials (ERPs) and mismatch negative (MMN) were compared between the CI group and the HC group. In addition, we analyzed the phase lag indices (PLI) in the CI group and the HC group and calculated the difference in functional connectivity between the two groups at different stages after implantation. Results The behavioral indicator, speech recognition ability, in CI patients improved as the implantation time increased. The MMN analysis showed that CI patients could recognize the difference between standard and deviation stimuli just like the HCs 90 days after cochlear implantation. Comparing the latencies of N1/P2/MMN between the CI group and the HC group, we found that the latency of N1/P2 in CI patients was longer, while the latency of MMN in CI users was shorter. In addition, PLI-based whole-brain functional connectivity (PLI-FC) showed that the difference between the CI group and the HC group mainly exists in electrode pairs between the bilateral auditory area and the frontal area. Furthermore, all those differences gradually decreased with the increase in implantation time. Conclusion The N1 amplitude, N1/P2/MMN latency, and PLI-FC in the alpha band may reflect the process of auditory function remodeling and could be an objective index for the assessment of speech perception ability and the effect of cochlear implantation.
Collapse
Affiliation(s)
- Songjian Wang
- School of Biomedical Engineering, Capital Medical University, Beijing, China.,Beijing Key Laboratory of Fundamental Research on Biomechanics in Clinical Application, Capital Medical University, Beijing, China
| | - Meng Lin
- School of Biomedical Engineering, Capital Medical University, Beijing, China.,Beijing Key Laboratory of Fundamental Research on Biomechanics in Clinical Application, Capital Medical University, Beijing, China
| | - Liwei Sun
- School of Biomedical Engineering, Capital Medical University, Beijing, China.,Beijing Key Laboratory of Fundamental Research on Biomechanics in Clinical Application, Capital Medical University, Beijing, China
| | - Xueqing Chen
- Key Laboratory of Otolaryngology Head and Neck Surgery, Beijing Tongren Hospital, Beijing Institute of Otolaryngology, Ministry of Education, Beijing, China
| | - Xinxing Fu
- Key Laboratory of Otolaryngology Head and Neck Surgery, Beijing Tongren Hospital, Beijing Institute of Otolaryngology, Ministry of Education, Beijing, China
| | - LiLi Yan
- Key Laboratory of Otolaryngology Head and Neck Surgery, Beijing Tongren Hospital, Beijing Institute of Otolaryngology, Ministry of Education, Beijing, China
| | - Chunlin Li
- School of Biomedical Engineering, Capital Medical University, Beijing, China.,Beijing Key Laboratory of Fundamental Research on Biomechanics in Clinical Application, Capital Medical University, Beijing, China
| | - Xu Zhang
- School of Biomedical Engineering, Capital Medical University, Beijing, China.,Beijing Key Laboratory of Fundamental Research on Biomechanics in Clinical Application, Capital Medical University, Beijing, China
| |
Collapse
|