Using interictal seizure-free EEG data to recognise patients with epilepsy based on machine learning of brain functional connectivity

2021 ◽  
Vol 67 ◽  
pp. 102554
Author(s):  
Jun Cao ◽  
Kacper Grajcar ◽  
Xiaocai Shan ◽  
Yifan Zhao ◽  
Jiaru Zou ◽  
...  
Keyword(s):  
Machine Learning ◽  
Functional Connectivity ◽  
Eeg Data ◽  
Brain Functional Connectivity ◽  
Patients With Epilepsy

Association between abnormal brain functional connectivity in children and psychopathology: A study based on graph theory and machine learning

2017 ◽  
Vol 19 (2) ◽  
pp. 119-129 ◽  
Author(s):  
João Ricardo Sato ◽  
Claudinei Eduardo Biazoli ◽  
Giovanni Abrahão Salum ◽  
Ary Gadelha ◽  
Nicolas Crossley ◽  
...  
Keyword(s):  
Machine Learning ◽  
Graph Theory ◽  
Functional Connectivity ◽  
Brain Functional Connectivity ◽  
Abnormal Brain

scholarly journals Multi-Order Brain Functional Connectivity Network-Based Machine Learning Method for Recognition of Delayed Neurocognitive Recovery in Older Adults Undergoing Non-cardiac Surgery

2021 ◽  
Vol 15 ◽  
Author(s):  
Guoqing Wu ◽  
Zhaoshun Jiang ◽  
Yuxi Cai ◽  
Xixue Zhang ◽  
Yating Lv ◽  
...  
Keyword(s):  
Machine Learning ◽  
Functional Connectivity ◽  
Brain Region ◽  
Characteristic Curve ◽  
Brain Regions ◽  
Machine Learning Method ◽  
Learning Method ◽  
Recognition Model ◽  
Operative Recovery ◽  
Brain Functional Connectivity

Objectives: Delayed neurocognitive recovery (DNR) seriously affects the post-operative recovery of elderly surgical patients, but there is still a lack of effective methods to recognize high-risk patients with DNR. This study proposed a machine learning method based on a multi-order brain functional connectivity (FC) network to recognize DNR.Method: Seventy-four patients who completed assessments were included in this study, in which 16/74 (21.6%) had DNR following surgery. Based on resting-state functional magnetic resonance imaging (rs-fMRI), we first constructed low-order FC networks of 90 brain regions by calculating the correlation of brain region signal changing in the time dimension. Then, we established high-order FC networks by calculating correlations among each pair of brain regions. Afterward, we built sparse representation-based machine learning model to recognize DNR on the extracted multi-order FC network features. Finally, an independent testing was conducted to validate the established recognition model.Results: Three hundred ninety features of FC networks were finally extracted to identify DNR. After performing the independent-sample T test between these features and the categories, 15 features showed statistical differences (P < 0.05) and 3 features had significant statistical differences (P < 0.01). By comparing DNR and non-DNR patients’ brain region connection matrices, it is found that there are more connections among brain regions in DNR patients than in non-DNR patients. For the machine learning recognition model based on multi-feature combination, the area under the receiver operating characteristic curve (AUC), accuracy, sensitivity, and specificity of the classifier reached 95.61, 92.00, 66.67, and 100.00%, respectively.Conclusion: This study not only reveals the significance of preoperative rs-fMRI in recognizing post-operative DNR in elderly patients but also establishes a promising machine learning method to recognize DNR.

scholarly journals Growth faltering is associated with altered brain functional connectivity and cognitive outcomes in urban Bangladeshi children exposed to early adversity

BMC Medicine ◽  
2019 ◽  
Vol 17 (1) ◽  
Author(s):  
Wanze Xie ◽  
Sarah K. G. Jensen ◽  
Mark Wade ◽  
Swapna Kumar ◽  
Alissa Westerlund ◽  
...  
Keyword(s):  
Cognitive Development ◽  
Functional Connectivity ◽  
Path Analysis ◽  
Indirect Effect ◽  
Child Growth ◽  
Cognitive Outcomes ◽  
Physical Growth ◽  
Frequency Bands ◽  
Eeg Data ◽  
Brain Functional Connectivity

Abstract Background Stunting affects more than 161 million children worldwide and can compromise cognitive development beginning early in childhood. There is a paucity of research using neuroimaging tools in conjunction with sensitive behavioral assays in low-income settings, which has hindered researchers’ ability to explain how stunting impacts brain and behavioral development. We employed high-density EEG to examine associations among children’s physical growth, brain functional connectivity (FC), and cognitive development. Methods We recruited participants from an urban impoverished neighborhood in Dhaka, Bangladesh. One infant cohort consisted of 92 infants whose height (length) was measured at 3, 4.5, and 6 months; EEG data were collected at 6 months; and cognitive outcomes were assessed using the Mullen Scales of Early Learning at 27 months. A second, older cohort consisted of 118 children whose height was measured at 24, 30, and 36 months; EEG data were collected at 36 months; and Intelligence Quotient (IQ) scores were assessed at 48 months. Height-for-age (HAZ) z-scores were calculated based on the World Health Organization standard. EEG FC in different frequency bands was calculated in the cortical source space. Linear regression and longitudinal path analysis were conducted to test the associations between variables, as well as the indirect effect of child growth on cognitive outcomes via brain FC. Results In the older cohort, we found that HAZ was negatively related to brain FC in the theta and beta frequency bands, which in turn was negatively related to children’s IQ score at 48 months. Longitudinal path analysis showed an indirect effect of HAZ on children’s IQ via brain FC in both the theta and beta bands. There were no associations between HAZ and brain FC or cognitive outcomes in the infant cohort. Conclusions The association observed between child growth and brain FC may reflect a broad deleterious effect of malnutrition on children’s brain development. The mediation effect of FC on the relation between child growth and later IQ provides the first evidence suggesting that brain FC may serve as a neural pathway by which biological adversity impacts cognitive development.

scholarly journals Distinct Patterns of Functional Connectivity During the Comprehension of Natural, Narrative Speech

2020 ◽  
Vol 30 (03) ◽  
pp. 2050007 ◽  
Author(s):  
Yongjie Zhu ◽  
Jia Liu ◽  
Tapani Ristaniemi ◽  
Fengyu Cong
Keyword(s):  
Functional Connectivity ◽  
Time Window ◽  
Principal Component ◽  
Single Mode ◽  
Brain Regions ◽  
Speech Comprehension ◽  
Analysis Framework ◽  
Eeg Data ◽  
Source Level ◽  
Brain Functional Connectivity

Recent continuous task studies, such as narrative speech comprehension, show that fluctuations in brain functional connectivity (FC) are altered and enhanced compared to the resting state. Here, we characterized the fluctuations in FC during comprehension of speech and time-reversed speech conditions. The correlations of Hilbert envelope of source-level EEG data were used to quantify FC between spatially separate brain regions. A symmetric multivariate leakage correction was applied to address the signal leakage issue before calculating FC. The dynamic FC was estimated based on a sliding time window. Then, principal component analysis (PCA) was performed on individually concatenated and temporally concatenated FC matrices to identify FC patterns. We observed that the mode of FC induced by speech comprehension can be characterized with a single principal component. The condition-specific FC demonstrated decreased correlations between frontal and parietal brain regions and increased correlations between frontal and temporal brain regions. The fluctuations of the condition-specific FC characterized by a shorter time demonstrated that dynamic FC also exhibited condition specificity over time. The FC is dynamically reorganized and FC dynamic pattern varies along a single mode of variation during speech comprehension. The proposed analysis framework seems valuable for studying the reorganization of brain networks during continuous task experiments.

scholarly journals Localized prediction of glutamate from whole-brain functional connectivity of the pregenual anterior cingulate cortex

2020 ◽  
Author(s):  
Louise Martens ◽  
Nils B. Kroemer ◽  
Vanessa Teckentrup ◽  
Lejla Colic ◽  
Nicola Palomero-Gallagher ◽  
...  
Keyword(s):  
Machine Learning ◽  
Functional Connectivity ◽  
Anterior Cingulate Cortex ◽  
Cingulate Cortex ◽  
Anterior Cingulate ◽  
Resonance Spectroscopy ◽  
Learning Approaches ◽  
Least Squares Regression ◽  
Brain Functional Connectivity ◽  
Spatial Specificity

AbstractLocal measures of neurotransmitters provide crucial insights into neurobiological changes underlying altered functional connectivity in psychiatric disorders. However, non-invasive neuroimaging techniques such as magnetic resonance spectroscopy (MRS) may cover anatomically and functionally distinct areas, such as p32 and p24 of the pregenual anterior cingulate cortex (pgACC). Here, we aimed to overcome this low spatial specificity of MRS by predicting local glutamate and GABA based on functional characteristics and neuroanatomy, using complementary machine learning approaches. Functional connectivity profiles of pgACC area p32 predicted pgACC glutamate better than chance (R2 = .324) and explained more variance compared to area p24 using both elastic net and partial least squares regression. In contrast, GABA could not be robustly predicted. To summarize, machine learning helps exploit the high resolution of fMRI to improve the interpretation of local neurometabolism. Our augmented multimodal imaging analysis can deliver novel insights into neurobiology by using complementary information.

scholarly journals Acute and Chronic Effects of Betel Quid Chewing on Brain Functional Connectivity

2020 ◽  
Vol 11 ◽  
Author(s):  
Adellah Sariah ◽  
Shuixia Guo ◽  
Jing Zuo ◽  
Weidan Pu ◽  
Haihong Liu ◽  
...  
Keyword(s):  
Functional Connectivity ◽  
Betel Quid ◽  
Chronic Effects ◽  
Betel Quid Chewing ◽  
Brain Functional Connectivity ◽  
Acute And Chronic Effects
Sign in / Sign up

Export Citation Format

Share Document