Search citation statements
Paper Sections
Citation Types
Year Published
Publication Types
Relationship
Authors
Journals
<b><i>Introduction:</i></b> Hippocampal atrophy is an established biomarker for conversion from the normal ageing process to developing cognitive impairment and dementia. This study used a novel hypothesis-free machine-learning approach, to uncover potential risk factors of lower hippocampal volume using information from the world’s largest brain imaging study. <b><i>Methods:</i></b> A combination of machine learning and conventional statistical methods were used to identify predictors of low hippocampal volume. We run gradient boosting decision tree modelling including 2,891 input features measured before magnetic resonance imaging assessments (median 9.2 years, range 4.2–13.8 years) using data from 42,152 dementia-free UK Biobank participants. Logistic regression analyses were run on 87 factors identified as important for prediction based on Shapley values. False discovery rate-adjusted <i>p</i> value <0.05 was used to declare statistical significance. <b><i>Results:</i></b> Older age, male sex, greater height, and whole-body fat-free mass were the main predictors of low hippocampal volume with the model also identifying associations with lung function and lifestyle factors including smoking, physical activity, and coffee intake (corrected <i>p</i> < 0.05 for all). Red blood cell count and several red blood cell indices such as haemoglobin concentration, mean corpuscular haemoglobin, mean corpuscular volume, mean reticulocyte volume, mean sphered cell volume, and red blood cell distribution width were among many biomarkers associated with low hippocampal volume. <b><i>Conclusion:</i></b> Lifestyles, physical measures, and biomarkers may affect hippocampal volume, with many of the characteristics potentially reflecting oxygen supply to the brain. Further studies are required to establish causality and clinical relevance of these findings.
<b><i>Introduction:</i></b> Hippocampal atrophy is an established biomarker for conversion from the normal ageing process to developing cognitive impairment and dementia. This study used a novel hypothesis-free machine-learning approach, to uncover potential risk factors of lower hippocampal volume using information from the world’s largest brain imaging study. <b><i>Methods:</i></b> A combination of machine learning and conventional statistical methods were used to identify predictors of low hippocampal volume. We run gradient boosting decision tree modelling including 2,891 input features measured before magnetic resonance imaging assessments (median 9.2 years, range 4.2–13.8 years) using data from 42,152 dementia-free UK Biobank participants. Logistic regression analyses were run on 87 factors identified as important for prediction based on Shapley values. False discovery rate-adjusted <i>p</i> value <0.05 was used to declare statistical significance. <b><i>Results:</i></b> Older age, male sex, greater height, and whole-body fat-free mass were the main predictors of low hippocampal volume with the model also identifying associations with lung function and lifestyle factors including smoking, physical activity, and coffee intake (corrected <i>p</i> < 0.05 for all). Red blood cell count and several red blood cell indices such as haemoglobin concentration, mean corpuscular haemoglobin, mean corpuscular volume, mean reticulocyte volume, mean sphered cell volume, and red blood cell distribution width were among many biomarkers associated with low hippocampal volume. <b><i>Conclusion:</i></b> Lifestyles, physical measures, and biomarkers may affect hippocampal volume, with many of the characteristics potentially reflecting oxygen supply to the brain. Further studies are required to establish causality and clinical relevance of these findings.
Background Neurodegeneration and structural changes in the brain due to amyloid deposition have been observed even in individuals with mild cognitive impairment (MCI). EEG measurement is considered an effective tool because it is noninvasive, has few restrictions on the measurement environment, and is simple and easy to use. In this study, we investigated the neurophysiological characteristics of community-dwelling older adults with MCI using EEG. Methods Demographic characteristics, cognitive function, physical function, resting-state MRI and electroencephalogram (rs-EEG), event-related potentials (ERPs) during Simon tasks, and task proportion of correct responses and reaction times (RTs) were obtained from 402 healthy controls (HC) and 47 MCI participants. We introduced exact low-resolution brain electromagnetic tomography-independent component analysis (eLORETA-ICA) to assess the rs-EEG network in community-dwelling older adults with MCI. Results A lower proportion of correct responses to the Simon task and slower RTs were observed in the MCI group (p < 0.01). Despite no difference in brain volume between the HC and MCI groups, significant decreases in dorsal attention network (DAN) activity (p < 0.05) and N2 amplitude of ERP (p < 0.001) were observed in the MCI group. Moreover, DAN activity demonstrated a correlation with education (Rs = 0.32, p = 0.027), global cognitive function (Rs = 0.32, p = 0.030), and processing speed (Rs = 0.37, p = 0.010) in the MCI group. The discrimination accuracy for MCI with the addition of the eLORETA-ICA network ranged from 0.7817 to 0.7929, and the area under the curve ranged from 0.8492 to 0.8495. Conclusions The eLORETA-ICA approach of rs-EEG using noninvasive and relatively inexpensive EEG demonstrates specific changes in elders with MCI. It may provide a simple and valid assessment method with few restrictions on the measurement environment and may be useful for early detection of MCI in community-dwelling older adults.
scite is a Brooklyn-based organization that helps researchers better discover and understand research articles through Smart Citations–citations that display the context of the citation and describe whether the article provides supporting or contrasting evidence. scite is used by students and researchers from around the world and is funded in part by the National Science Foundation and the National Institute on Drug Abuse of the National Institutes of Health.
hi@scite.ai
10624 S. Eastern Ave., Ste. A-614
Henderson, NV 89052, USA
Copyright © 2024 scite LLC. All rights reserved.
Made with 💙 for researchers
Part of the Research Solutions Family.