1
|
Rajeswari J, Jagannath M. Brain connectivity analysis based classification of obstructive sleep apnea using electroencephalogram signals. Sci Rep 2024; 14:5561. [PMID: 38448538 PMCID: PMC10917737 DOI: 10.1038/s41598-024-56384-9] [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: 12/21/2023] [Accepted: 03/05/2024] [Indexed: 03/08/2024] Open
Abstract
Obstructive sleep apnea (OSA) is a disorder which blocks the upper airway during sleep. The severity of OSA will lead heart attack, stroke and end of life. This proposed study explored the classification of OSA and healthy subjects using brain connectivity analysis from electroencephalogram (EEG) signals. Institute of System and Robotics-University of Coimbra (ISRUC) database were used for acquiring 50 EEG signals using 4 channels and noise removal has been accomplished by 50 Hz notch filter. The Institute of System and Robotics-University of Coimbra (ISRUC) database contained 50 EEG signals, with four channels, and a 50 Hz notch filter was applied to remove noise. Wavelet packet decomposition method was performing the segregation of EEG signals into five bands; Gamma (γ), beta (β), alpha (α), theta (θ) and delta (δ). A total of 4 electrode positions were used for the brain connectivity analysis for each EEG band. Pearson correlation method was effectively used for measuring the correlation between healthy and OSA subjects. The nodes and edges were highlighted the connection between brain and subjects. The highest correlation was achieved in delta band of OSA subjects which starts from 0.7331 to 0.9172 respectively. For healthy subjects, the positive correlation achieved was 0.6995. The delta band has been correlated well with brain when compared other bands. It has been noted that the positive correlation well associated with brain in OSA subjects, which classifies OSA from healthy subjects.
Collapse
Affiliation(s)
- J Rajeswari
- Department of Electronics and Communication Engineering, Agni College of Technology, Chennai, Tamil Nadu, India
| | - M Jagannath
- School of Electronics Engineering, Vellore Institute of Technology (VIT) Chennai, Chennai, Tamil Nadu, India.
| |
Collapse
|
2
|
Tran K, Salazar BH, Boone TB, Khavari R, Karmonik C. Classification of multiple sclerosis women with voiding dysfunction using machine learning: Is functional connectivity or structural connectivity a better predictor? BJUI COMPASS 2023; 4:277-284. [PMID: 37025479 PMCID: PMC10071087 DOI: 10.1002/bco2.217] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [Abstract] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Received: 10/10/2022] [Revised: 12/19/2022] [Accepted: 12/30/2022] [Indexed: 01/29/2023] Open
Abstract
Introduction Machine learning (ML) is an established technique that uses sets of training data to develop algorithms and perform data classification without using human intervention/supervision. This study aims to determine how functional and anatomical brain connectivity (FC and SC) data can be used to classify voiding dysfunction (VD) in female MS patients using ML. Methods Twenty-seven ambulatory MS individuals with lower urinary tract dysfunction were recruited and divided into two groups (Group 1: voiders [V, n = 14]; Group 2: VD [n = 13]). All patients underwent concurrent functional MRI/urodynamics testing. Results Best-performing ML algorithms, with highest area under the curve (AUC), were partial least squares (PLS, AUC = 0.86) using FC alone and random forest (RF) when using SC alone (AUC = 0.93) and combined (AUC = 0.96) as inputs. Our results show 10 predictors with the highest AUC values were associated with FC, indicating that although white matter was affected, new connections may have formed to preserve voiding initiation. Conclusions MS patients with and without VD exhibit distinct brain connectivity patterns when performing a voiding task. Our results demonstrate FC (grey matter) is of higher importance than SC (white matter) for this classification. Knowledge of these centres may help us further phenotype patients to appropriate centrally focused treatments in the future.
Collapse
Affiliation(s)
- Khue Tran
- EnMed Program Texas A&M School of Engineering Medicine Houston Texas USA
| | - Betsy H. Salazar
- Department of Urology Houston Methodist Hospital Houston Texas USA
| | - Timothy B. Boone
- Department of Urology Houston Methodist Hospital Houston Texas USA
| | - Rose Khavari
- Department of Urology Houston Methodist Hospital Houston Texas USA
| | - Christof Karmonik
- Translational Imaging Center Houston Methodist Research Institute Houston Texas USA
| |
Collapse
|
3
|
Liu X, Wei Z, Chen L, Duan W, Li H, Kong L, Shu Y, Li P, Li K, Xie W, Zeng Y, Huang L, Long T, Peng D. Effects of 3-month CPAP therapy on brain structure in obstructive sleep apnea: A diffusion tensor imaging study. Front Neurol 2022; 13:913193. [PMID: 36071900 PMCID: PMC9441568 DOI: 10.3389/fneur.2022.913193] [Citation(s) in RCA: 1] [Impact Index Per Article: 0.5] [Reference Citation Analysis] [Abstract] [Track Full Text] [Download PDF] [Figures] [Journal Information] [Subscribe] [Scholar Register] [Received: 04/05/2022] [Accepted: 07/25/2022] [Indexed: 12/02/2022] Open
Abstract
White matter (WM) fiber alterations in patients with obstructive sleep apnea (OSA) is associated with cognitive impairment, which can be alleviated by continuous positive airway pressure (CPAP). In this study, we aimed to investigate the changes in WM in patients with OSA at baseline (pre-CPAP) and 3 months after CPAP adherence treatment (post-CPAP), and to provide a basis for understanding the reversible changes after WM alteration in this disease. Magnetic resonance imaging (MRI) was performed on 20 severely untreated patients with OSA and 20 good sleepers. Tract-based spatial statistics was used to evaluate the fractional anisotropy (FA), mean diffusion coefficient, axial diffusion coefficient, and radial diffusion coefficient (RD) of WM. To assess the efficacy of treatment, 20 patients with pre-CPAP OSA underwent MRI again 3 months later. A correlation analysis was conducted to evaluate the relationship between WM injury and clinical evaluation. Compared with good sleepers, patients with OSA had decreased FA and increased RD in the anterior thalamic radiation, forceps major, inferior fronto-occipital tract, inferior longitudinal tract, and superior longitudinal tract, and decreased FA in the uncinate fasciculus, corticospinal tract, and cingulate gyrus (P < 0.05). No significant change in WM in patients with post-CPAP OSA compared with those with pre-CPAP OSA. Abnormal changes in WM in untreated patients with OSA were associated with oxygen saturation, Montreal cognitive score, and the apnea hypoventilation index. WM fiber was extensively alteration in patients with severe OSA, which is associated with cognitive impairment. Meanwhile, cognitive recovery was not accompanied by reversible changes in WM microstructure after short-term CPAP therapy.
Collapse
Affiliation(s)
- Xiang Liu
- Department of Radiology, The First Affiliated Hospital of Nanchang University, Nanchang, China
| | - Zhipeng Wei
- Department of Radiology, The Second Affiliated Hospital of Nanchang University, Nanchang, China
| | - Liting Chen
- Medical Imaging Center, First Affiliated Hospital of Jinan University, Guangzhou, China
| | - Wenfeng Duan
- Department of Radiology, The First Affiliated Hospital of Nanchang University, Nanchang, China
| | - Haijun Li
- Department of Radiology, The First Affiliated Hospital of Nanchang University, Nanchang, China
| | - Linghong Kong
- Department of Radiology, The First Affiliated Hospital of Nanchang University, Nanchang, China
| | - Yongqiang Shu
- Department of Radiology, The First Affiliated Hospital of Nanchang University, Nanchang, China
| | - Panmei Li
- Department of Radiology, The First Affiliated Hospital of Nanchang University, Nanchang, China
| | - Kunyao Li
- Department of Radiology, The First Affiliated Hospital of Nanchang University, Nanchang, China
| | - Wei Xie
- Department of Radiology, The First Affiliated Hospital of Nanchang University, Nanchang, China
| | - Yaping Zeng
- Department of Radiology, The First Affiliated Hospital of Nanchang University, Nanchang, China
| | - Ling Huang
- Department of Radiology, The First Affiliated Hospital of Nanchang University, Nanchang, China
| | - Ting Long
- Department of Radiology, The First Affiliated Hospital of Nanchang University, Nanchang, China
| | - Dechang Peng
- Department of Radiology, The First Affiliated Hospital of Nanchang University, Nanchang, China
- *Correspondence: Dechang Peng
| |
Collapse
|