Publications by authors named "James H Cole"

62 Publications

Deep learning to automate the labelling of head MRI datasets for computer vision applications.

Eur Radiol 2021 Jul 20. Epub 2021 Jul 20.

School of Biomedical Engineering & Imaging Sciences, Kings College London, Rayne Institute, 4th Floor, Lambeth Wing, London, SE1 7EH, UK.

Objectives: The purpose of this study was to build a deep learning model to derive labels from neuroradiology reports and assign these to the corresponding examinations, overcoming a bottleneck to computer vision model development.

Methods: Reference-standard labels were generated by a team of neuroradiologists for model training and evaluation. Three thousand examinations were labelled for the presence or absence of any abnormality by manually scrutinising the corresponding radiology reports ('reference-standard report labels'); a subset of these examinations (n = 250) were assigned 'reference-standard image labels' by interrogating the actual images. Separately, 2000 reports were labelled for the presence or absence of 7 specialised categories of abnormality (acute stroke, mass, atrophy, vascular abnormality, small vessel disease, white matter inflammation, encephalomalacia), with a subset of these examinations (n = 700) also assigned reference-standard image labels. A deep learning model was trained using labelled reports and validated in two ways: comparing predicted labels to (i) reference-standard report labels and (ii) reference-standard image labels. The area under the receiver operating characteristic curve (AUC-ROC) was used to quantify model performance. Accuracy, sensitivity, specificity, and F1 score were also calculated.

Results: Accurate classification (AUC-ROC > 0.95) was achieved for all categories when tested against reference-standard report labels. A drop in performance (ΔAUC-ROC > 0.02) was seen for three categories (atrophy, encephalomalacia, vascular) when tested against reference-standard image labels, highlighting discrepancies in the original reports. Once trained, the model assigned labels to 121,556 examinations in under 30 min.

Conclusions: Our model accurately classifies head MRI examinations, enabling automated dataset labelling for downstream computer vision applications.

Key Points: • Deep learning is poised to revolutionise image recognition tasks in radiology; however, a barrier to clinical adoption is the difficulty of obtaining large labelled datasets for model training. • We demonstrate a deep learning model which can derive labels from neuroradiology reports and assign these to the corresponding examinations at scale, facilitating the development of downstream computer vision models. • We rigorously tested our model by comparing labels predicted on the basis of neuroradiology reports with two sets of reference-standard labels: (1) labels derived by manually scrutinising each radiology report and (2) labels derived by interrogating the actual images.
View Article and Find Full Text PDF

Download full-text PDF

Source
http://dx.doi.org/10.1007/s00330-021-08132-0DOI Listing
July 2021

Network Modeling Sex Differences in Brain Integrity and Metabolic Health.

Front Aging Neurosci 2021 29;13:691691. Epub 2021 Jun 29.

Department of Psychology, The University of Texas at Austin, Austin, TX, United States.

Hypothesis-driven studies have demonstrated that sex moderates many of the relationships between brain health and cardiometabolic disease, which impacts risk for later-life cognitive decline. In the present study, we sought to further our understanding of the associations between multiple markers of brain integrity and cardiovascular risk in a midlife sample of 266 individuals by using network analysis, a technique specifically designed to examine complex associations among multiple systems at once. Separate network models were constructed for male and female participants to investigate sex differences in the biomarkers of interest, selected based on evidence linking them with risk for late-life cognitive decline: all components of metabolic syndrome (obesity, hypertension, dyslipidemia, and hyperglycemia); neuroimaging-derived brain-predicted age minus chronological age; ratio of white matter hyperintensities to whole brain volume; seed-based resting state functional connectivity in the Default Mode Network, and ratios of N-acetyl aspartate, glutamate and myo-inositol to creatine, measured through proton magnetic resonance spectroscopy. Males had a sparse network (87.2% edges = 0) relative to females (69.2% edges = 0), indicating fewer relationships between measures of cardiometabolic risk and brain integrity. The edges in the female network provide meaningful information about potential mechanisms between brain integrity and cardiometabolic health. Additionally, Apolipoprotein ϵ4 (ApoE ϵ4) status and waist circumference emerged as central nodes in the female model. Our study demonstrates that network analysis is a promising technique for examining relationships between risk factors for cognitive decline in a midlife population and that investigating sex differences may help optimize risk prediction and tailor individualized treatments in the future.
View Article and Find Full Text PDF

Download full-text PDF

Source
http://dx.doi.org/10.3389/fnagi.2021.691691DOI Listing
http://www.ncbi.nlm.nih.gov/pmc/articles/PMC8275835PMC
June 2021

Traumatic brain injury: a comparison of diffusion and volumetric magnetic resonance imaging measures.

Brain Commun 2021 2;3(2):fcab006. Epub 2021 Jan 2.

Division of Brain Sciences, Computational, Cognitive and Clinical Neuroimaging Laboratory, Imperial College London, Hammersmith Hospital, London, UK.

Cognitive impairment after traumatic brain injury remains hard to predict. This is partly because axonal injury, which is of fundamental importance, is difficult to measure clinically. Advances in MRI allow axonal injury to be detected after traumatic brain injury, but the most sensitive approach is unclear. Here, we compare the performance of diffusion tensor imaging, neurite orientation dispersion and density-imaging and volumetric measures of brain atrophy in the identification of white-matter abnormalities after traumatic brain injury. Thirty patients with moderate-severe traumatic brain injury in the chronic phase and 20 age-matched controls had T1-weighted and diffusion MRI. Neuropsychological tests of processing speed, executive functioning and memory were used to detect cognitive impairment. Extensive abnormalities in neurite density index and orientation dispersion index were observed, with distinct spatial patterns. Fractional anisotropy and mean diffusivity also indicated widespread abnormalities of white-matter structure. Neurite density index was significantly correlated with processing speed. Slower processing speed was also related to higher mean diffusivity in the corticospinal tracts. Lower white-matter volumes were seen after brain injury with greater effect sizes compared to diffusion metrics; however, volume was not sensitive to changes in cognitive performance. Volume was the most sensitive at detecting change between groups but was not specific for determining relationships with cognition. Abnormalities in fractional anisotropy and mean diffusivity were the most sensitive diffusion measures; however, neurite density index and orientation dispersion index may be more spatially specific. Lower neurite density index may be a useful metric for examining slower processing speed.
View Article and Find Full Text PDF

Download full-text PDF

Source
http://dx.doi.org/10.1093/braincomms/fcab006DOI Listing
http://www.ncbi.nlm.nih.gov/pmc/articles/PMC8105496PMC
January 2021

Beyond the average patient: how neuroimaging models can address heterogeneity in dementia.

Brain 2021 Apr 23. Epub 2021 Apr 23.

Centre for Medical Image Computing, Medical Physics and Biomedical Engineering, University College London, London, UK.

Dementia is a highly heterogeneous condition, with pronounced individual differences in onset age, clinical presentation, progression rates and neuropathological hallmarks, even within a specific diagnostic group. However, the most common statistical designs used in dementia research studies and clinical trials overlook this heterogeneity, instead relying on the comparison of group average differences (e.g., patient versus control, treatment versus placebo), implicitly assuming within-group homogeneity. This one-size-fits-all approach potentially limits our understanding of dementia aetiology, hindering the identification of effective treatments. Neuroimaging has enabled characterisation of the average neuroanatomical substrates of dementias; however, the increasing availability of large open neuroimaging datasets provides the opportunity to examine patterns of neuroanatomical variability in individual patients. In this Update review we outline the causes and consequences of heterogeneity in dementia and discuss recent research which aims to directly tackle heterogeneity, rather than assume that dementia affects everyone in the same way. We introduce spatial normative modelling as an emerging data-driven technique which can be applied to dementia data to model neuroanatomical variation, capturing individualised neurobiological "fingerprints". Such methods have the potential to detect clinically relevant subtypes, track an individual's disease progression or evaluate treatment responses, with the goal of moving towards precision medicine for dementia.
View Article and Find Full Text PDF

Download full-text PDF

Source
http://dx.doi.org/10.1093/brain/awab165DOI Listing
April 2021

Prediction of brain age and cognitive age: Quantifying brain and cognitive maintenance in aging.

Hum Brain Mapp 2021 Apr 14;42(6):1626-1640. Epub 2020 Dec 14.

Department of Psychiatry, University of Oxford, Oxford, UK.

The concept of brain maintenance refers to the preservation of brain integrity in older age, while cognitive reserve refers to the capacity to maintain cognition in the presence of neurodegeneration or aging-related brain changes. While both mechanisms are thought to contribute to individual differences in cognitive function among older adults, there is currently no "gold standard" for measuring these constructs. Using machine-learning methods, we estimated brain and cognitive age based on deviations from normative aging patterns in the Whitehall II MRI substudy cohort (N = 537, age range = 60.34-82.76), and tested the degree of correspondence between these constructs, as well as their associations with premorbid IQ, education, and lifestyle trajectories. In line with established literature highlighting IQ as a proxy for cognitive reserve, higher premorbid IQ was linked to lower cognitive age independent of brain age. No strong evidence was found for associations between brain or cognitive age and lifestyle trajectories from midlife to late life based on latent class growth analyses. However, post hoc analyses revealed a relationship between cumulative lifestyle measures and brain age independent of cognitive age. In conclusion, we present a novel approach to characterizing brain and cognitive maintenance in aging, which may be useful for future studies seeking to identify factors that contribute to brain preservation and cognitive reserve mechanisms in older age.
View Article and Find Full Text PDF

Download full-text PDF

Source
http://dx.doi.org/10.1002/hbm.25316DOI Listing
http://www.ncbi.nlm.nih.gov/pmc/articles/PMC7978127PMC
April 2021

Editorial: Deep Learning in Aging Neuroscience.

Front Neuroinform 2020 26;14:573974. Epub 2020 Oct 26.

German Center for Neurodegenerative Diseases (DZNE), Rostock, Germany.

View Article and Find Full Text PDF

Download full-text PDF

Source
http://dx.doi.org/10.3389/fninf.2020.573974DOI Listing
http://www.ncbi.nlm.nih.gov/pmc/articles/PMC7649163PMC
October 2020

Diffuse axonal injury predicts neurodegeneration after moderate-severe traumatic brain injury.

Brain 2020 12;143(12):3685-3698

Department of Brain Sciences, Division of Medicine, Imperial College London, London, UK.

Traumatic brain injury is associated with elevated rates of neurodegenerative diseases such as Alzheimer's disease and chronic traumatic encephalopathy. In experimental models, diffuse axonal injury triggers post-traumatic neurodegeneration, with axonal damage leading to Wallerian degeneration and toxic proteinopathies of amyloid and hyperphosphorylated tau. However, in humans the link between diffuse axonal injury and subsequent neurodegeneration has yet to be established. Here we test the hypothesis that the severity and location of diffuse axonal injury predicts the degree of progressive post-traumatic neurodegeneration. We investigated longitudinal changes in 55 patients in the chronic phase after moderate-severe traumatic brain injury and 19 healthy control subjects. Fractional anisotropy was calculated from diffusion tensor imaging as a measure of diffuse axonal injury. Jacobian determinant atrophy rates were calculated from serial volumetric T1 scans as a measure of measure post-traumatic neurodegeneration. We explored a range of potential predictors of longitudinal post-traumatic neurodegeneration and compared the variance in brain atrophy that they explained. Patients showed widespread evidence of diffuse axonal injury, with reductions of fractional anisotropy at baseline and follow-up in large parts of the white matter. No significant changes in fractional anisotropy over time were observed. In contrast, abnormally high rates of brain atrophy were seen in both the grey and white matter. The location and extent of diffuse axonal injury predicted the degree of brain atrophy: fractional anisotropy predicted progressive atrophy in both whole-brain and voxelwise analyses. The strongest relationships were seen in central white matter tracts, including the body of the corpus callosum, which are most commonly affected by diffuse axonal injury. Diffuse axonal injury predicted substantially more variability in white matter atrophy than other putative clinical or imaging measures, including baseline brain volume, age, clinical measures of injury severity and microbleeds (>50% for fractional anisotropy versus <5% for other measures). Grey matter atrophy was not predicted by diffuse axonal injury at baseline. In summary, diffusion MRI measures of diffuse axonal injury are a strong predictor of post-traumatic neurodegeneration. This supports a causal link between axonal injury and the progressive neurodegeneration that is commonly seen after moderate/severe traumatic brain injury but has been of uncertain aetiology. The assessment of diffuse axonal injury with diffusion MRI is likely to improve prognostic accuracy and help identify those at greatest neurodegenerative risk for inclusion in clinical treatment trials.
View Article and Find Full Text PDF

Download full-text PDF

Source
http://dx.doi.org/10.1093/brain/awaa316DOI Listing
December 2020

Multimodal brain-age prediction and cardiovascular risk: The Whitehall II MRI sub-study.

Neuroimage 2020 11 21;222:117292. Epub 2020 Aug 21.

Department of Psychiatry, University of Oxford, Oxford, UK.

Brain age is becoming a widely applied imaging-based biomarker of neural aging and potential proxy for brain integrity and health. We estimated multimodal and modality-specific brain age in the Whitehall II (WHII) MRI cohort using machine learning and imaging-derived measures of gray matter (GM) morphology, white matter microstructure (WM), and resting state functional connectivity (FC). The results showed that the prediction accuracy improved when multiple imaging modalities were included in the model (R = 0.30, 95% CI [0.24, 0.36]). The modality-specific GM and WM models showed similar performance (R = 0.22 [0.16, 0.27] and R = 0.24 [0.18, 0.30], respectively), while the FC model showed the lowest prediction accuracy (R = 0.002 [-0.005, 0.008]), indicating that the FC features were less related to chronological age compared to structural measures. Follow-up analyses showed that FC predictions were similarly low in a matched sub-sample from UK Biobank, and although FC predictions were consistently lower than GM predictions, the accuracy improved with increasing sample size and age range. Cardiovascular risk factors, including high blood pressure, alcohol intake, and stroke risk score, were each associated with brain aging in the WHII cohort. Blood pressure showed a stronger association with white matter compared to gray matter, while no differences in the associations of alcohol intake and stroke risk with these modalities were observed. In conclusion, machine-learning based brain age prediction can reduce the dimensionality of neuroimaging data to provide meaningful biomarkers of individual brain aging. However, model performance depends on study-specific characteristics including sample size and age range, which may cause discrepancies in findings across studies.
View Article and Find Full Text PDF

Download full-text PDF

Source
http://dx.doi.org/10.1016/j.neuroimage.2020.117292DOI Listing
http://www.ncbi.nlm.nih.gov/pmc/articles/PMC8121758PMC
November 2020

Cannabis use in patients with early psychosis is associated with alterations in putamen and thalamic shape.

Hum Brain Mapp 2020 10 20;41(15):4386-4396. Epub 2020 Jul 20.

Institute of Psychiatry, Psychology and Neurosciences King's College London, London, UK.

Around half of patients with early psychosis have a history of cannabis use. We aimed to determine if there are neurobiological differences in these the subgroups of persons with psychosis with and without a history of cannabis use. We expected to see regional deflations in hippocampus as a neurotoxic effect and regional inflations in striatal regions implicated in addictive processes. Volumetric, T1w MRIs were acquired from people with a diagnosis psychosis with (PwP + C = 28) or without (PwP - C = 26) a history of cannabis use; and Controls with (C + C = 16) or without (C - C = 22) cannabis use. We undertook vertex-based shape analysis of the brainstem, amygdala, hippocampus, globus pallidus, nucleus accumbens, caudate, putamen, thalamus using FSL FIRST. Clusters were defined through Threshold Free Cluster Enhancement and Family Wise Error was set at p < .05. We adjusted analyses for age, sex, tobacco and alcohol use. The putamen (bilaterally) and the right thalamus showed regional enlargement in PwP + C versus PwP - C. There were no areas of regional deflation. There were no significant differences between C + C and C - C. Cannabis use in participants with psychosis is associated with morphological alterations in subcortical structures. Putamen and thalamic enlargement may be related to compulsivity in patients with a history of cannabis use.
View Article and Find Full Text PDF

Download full-text PDF

Source
http://dx.doi.org/10.1002/hbm.25131DOI Listing
http://www.ncbi.nlm.nih.gov/pmc/articles/PMC7502838PMC
October 2020

Nonlinear biomarker interactions in conversion from mild cognitive impairment to Alzheimer's disease.

Hum Brain Mapp 2020 10 9;41(15):4406-4418. Epub 2020 Jul 9.

Computational, Cognitive & Clinical Neuroimaging Laboratory, Department of Brain Sciences, Imperial College London, London, UK.

Multiple biomarkers can capture different facets of Alzheimer's disease. However, statistical models of biomarkers to predict outcomes in Alzheimer's rarely model nonlinear interactions between these measures. Here, we used Gaussian Processes to address this, modelling nonlinear interactions to predict progression from mild cognitive impairment (MCI) to Alzheimer's over 3 years, using Alzheimer's Disease Neuroimaging Initiative (ADNI) data. Measures included: demographics, APOE4 genotype, CSF (amyloid-β42, total tau, phosphorylated tau), [18 ]florbetapir, hippocampal volume and brain-age. We examined: (a) the independent value of each biomarker; and (b) whether modelling nonlinear interactions between biomarkers improved predictions. Each measured added complementary information when predicting conversion to Alzheimer's. A linear model classifying stable from progressive MCI explained over half the variance (R = 0.51, p < .001); the strongest independently contributing biomarker was hippocampal volume (R = 0.13). When comparing sensitivity of different models to progressive MCI (independent biomarker models, additive models, nonlinear interaction models), we observed a significant improvement (p < .001) for various two-way interaction models. The best performing model included an interaction between amyloid-β-PET and P-tau, while accounting for hippocampal volume (sensitivity = 0.77, AUC = 0.826). Closely related biomarkers contributed uniquely to predict conversion to Alzheimer's. Nonlinear biomarker interactions were also implicated, and results showed that although for some patients adding additional biomarkers may add little value (i.e., when hippocampal volume is high), for others (i.e., with low hippocampal volume) further invasive and expensive examination may be warranted. Our framework enables visualisation of these interactions, in individual patient biomarker 'space', providing information for personalised or stratified healthcare or clinical trial design.
View Article and Find Full Text PDF

Download full-text PDF

Source
http://dx.doi.org/10.1002/hbm.25133DOI Listing
http://www.ncbi.nlm.nih.gov/pmc/articles/PMC7502835PMC
October 2020

Brain aging in major depressive disorder: results from the ENIGMA major depressive disorder working group.

Mol Psychiatry 2020 May 18. Epub 2020 May 18.

Department of Psychiatry, University of Münster, Münster, Germany.

Major depressive disorder (MDD) is associated with an increased risk of brain atrophy, aging-related diseases, and mortality. We examined potential advanced brain aging in adult MDD patients, and whether this process is associated with clinical characteristics in a large multicenter international dataset. We performed a mega-analysis by pooling brain measures derived from T1-weighted MRI scans from 19 samples worldwide. Healthy brain aging was estimated by predicting chronological age (18-75 years) from 7 subcortical volumes, 34 cortical thickness and 34 surface area, lateral ventricles and total intracranial volume measures separately in 952 male and 1236 female controls from the ENIGMA MDD working group. The learned model coefficients were applied to 927 male controls and 986 depressed males, and 1199 female controls and 1689 depressed females to obtain independent unbiased brain-based age predictions. The difference between predicted "brain age" and chronological age was calculated to indicate brain-predicted age difference (brain-PAD). On average, MDD patients showed a higher brain-PAD of +1.08 (SE 0.22) years (Cohen's d = 0.14, 95% CI: 0.08-0.20) compared with controls. However, this difference did not seem to be driven by specific clinical characteristics (recurrent status, remission status, antidepressant medication use, age of onset, or symptom severity). This highly powered collaborative effort showed subtle patterns of age-related structural brain abnormalities in MDD. Substantial within-group variance and overlap between groups were observed. Longitudinal studies of MDD and somatic health outcomes are needed to further assess the clinical value of these brain-PAD estimates.
View Article and Find Full Text PDF

Download full-text PDF

Source
http://dx.doi.org/10.1038/s41380-020-0754-0DOI Listing
May 2020

An automated machine learning approach to predict brain age from cortical anatomical measures.

Hum Brain Mapp 2020 09 16;41(13):3555-3566. Epub 2020 May 16.

Department of Neuroimaging, Institute of Psychiatry, Psychology and Neuroscience, King's College London, London, UK.

The use of machine learning (ML) algorithms has significantly increased in neuroscience. However, from the vast extent of possible ML algorithms, which one is the optimal model to predict the target variable? What are the hyperparameters for such a model? Given the plethora of possible answers to these questions, in the last years, automated ML (autoML) has been gaining attention. Here, we apply an autoML library called Tree-based Pipeline Optimisation Tool (TPOT) which uses a tree-based representation of ML pipelines and conducts a genetic programming-based approach to find the model and its hyperparameters that more closely predicts the subject's true age. To explore autoML and evaluate its efficacy within neuroimaging data sets, we chose a problem that has been the focus of previous extensive study: brain age prediction. Without any prior knowledge, TPOT was able to scan through the model space and create pipelines that outperformed the state-of-the-art accuracy for Freesurfer-based models using only thickness and volume information for anatomical structure. In particular, we compared the performance of TPOT (mean absolute error [MAE]: 4.612 ± .124 years) and a relevance vector regression (MAE 5.474 ± .140 years). TPOT also suggested interesting combinations of models that do not match the current most used models for brain prediction but generalise well to unseen data. AutoML showed promising results as a data-driven approach to find optimal models for neuroimaging applications.
View Article and Find Full Text PDF

Download full-text PDF

Source
http://dx.doi.org/10.1002/hbm.25028DOI Listing
http://www.ncbi.nlm.nih.gov/pmc/articles/PMC7416036PMC
September 2020

Multimodality neuroimaging brain-age in UK biobank: relationship to biomedical, lifestyle, and cognitive factors.

Authors:
James H Cole

Neurobiol Aging 2020 08 8;92:34-42. Epub 2020 Apr 8.

Department of Neuroimaging, Institute of Psychiatry, Psychology & Neuroscience, King's College London, London, UK; Centre for Medical Image Computing, Department of Computer Science, University College London, London, UK; Dementia Research Centre, Institute of Neurology, University College London, London, UK. Electronic address:

The brain-age paradigm is proving increasingly useful for exploring aging-related disease and can predict important future health outcomes. Most brain-age research uses structural neuroimaging to index brain volume. However, aging affects multiple aspects of brain structure and function, which can be examined using multimodality neuroimaging. Using UK Biobank, brain-age was modeled in n = 2205 healthy people with T1-weighted MRI, T2-FLAIR, T2∗, diffusion-MRI, task fMRI, and resting-state fMRI. In a held-out healthy validation set (n = 520), chronological age was accurately predicted (r = 0.78, mean absolute error = 3.55 years) using LASSO regression, higher than using any modality separately. Thirty-four neuroimaging phenotypes were deemed informative by the regression (after bootstrapping); predominantly gray-matter volume and white-matter microstructure measures. When applied to new individuals from UK Biobank (n = 14,701), significant associations with multimodality brain-predicted age difference (brain-PAD) were found for stroke history, diabetes diagnosis, smoking, alcohol intake and some, but not all, cognitive measures (corrected p < 0.05). Multimodality neuroimaging can improve brain-age prediction, and derived brain-PAD values are sensitive to biomedical and lifestyle factors that negatively impact brain and cognitive health.
View Article and Find Full Text PDF

Download full-text PDF

Source
http://dx.doi.org/10.1016/j.neurobiolaging.2020.03.014DOI Listing
http://www.ncbi.nlm.nih.gov/pmc/articles/PMC7280786PMC
August 2020

Longitudinal Assessment of Multiple Sclerosis with the Brain-Age Paradigm.

Ann Neurol 2020 07 6;88(1):93-105. Epub 2020 May 6.

Centre for Medical Image Computing, Department of Computer Science, University College London, London, UK.

Objective: During the natural course of multiple sclerosis (MS), the brain is exposed to aging as well as disease effects. Brain aging can be modeled statistically; the so-called "brain-age" paradigm. Here, we evaluated whether brain-predicted age difference (brain-PAD) was sensitive to the presence of MS, clinical progression, and future outcomes.

Methods: In a longitudinal, multicenter sample of 3,565 magnetic resonance imaging (MRI) scans, in 1,204 patients with MS and clinically isolated syndrome (CIS) and 150 healthy controls (mean follow-up time: patients 3.41 years, healthy controls 1.97 years), we measured "brain-predicted age" using T1-weighted MRI. We compared brain-PAD among patients with MS and patients with CIS and healthy controls, and between disease subtypes. Relationships between brain-PAD and Expanded Disability Status Scale (EDSS) were explored.

Results: Patients with MS had markedly higher brain-PAD than healthy controls (mean brain-PAD +10.3 years; 95% confidence interval [CI] = 8.5-12.1] versus 4.3 years; 95% CI = 2.1 to 6.4; p < 0.001). The highest brain-PADs were in secondary-progressive MS (+13.3 years; 95% CI = 11.3-15.3). Brain-PAD at study entry predicted time-to-disability progression (hazard ratio 1.02; 95% CI = 1.01-1.03; p < 0.001); although normalized brain volume was a stronger predictor. Greater annualized brain-PAD increases were associated with greater annualized EDSS score (r = 0.26; p < 0.001).

Interpretation: The brain-age paradigm is sensitive to MS-related atrophy and clinical progression. A higher brain-PAD at baseline was associated with more rapid disability progression and the rate of change in brain-PAD related to worsening disability. Potentially, "brain-age" could be used as a prognostic biomarker in early-stage MS, to track disease progression or stratify patients for clinical trial enrollment. ANN NEUROL 2020 ANN NEUROL 2020;88:93-105.
View Article and Find Full Text PDF

Download full-text PDF

Source
http://dx.doi.org/10.1002/ana.25746DOI Listing
July 2020

ENIGMA and global neuroscience: A decade of large-scale studies of the brain in health and disease across more than 40 countries.

Transl Psychiatry 2020 03 20;10(1):100. Epub 2020 Mar 20.

Department of Psychiatry & Behavioral Sciences, Stanford University, Stanford, CA, USA.

This review summarizes the last decade of work by the ENIGMA (Enhancing NeuroImaging Genetics through Meta Analysis) Consortium, a global alliance of over 1400 scientists across 43 countries, studying the human brain in health and disease. Building on large-scale genetic studies that discovered the first robustly replicated genetic loci associated with brain metrics, ENIGMA has diversified into over 50 working groups (WGs), pooling worldwide data and expertise to answer fundamental questions in neuroscience, psychiatry, neurology, and genetics. Most ENIGMA WGs focus on specific psychiatric and neurological conditions, other WGs study normal variation due to sex and gender differences, or development and aging; still other WGs develop methodological pipelines and tools to facilitate harmonized analyses of "big data" (i.e., genetic and epigenetic data, multimodal MRI, and electroencephalography data). These international efforts have yielded the largest neuroimaging studies to date in schizophrenia, bipolar disorder, major depressive disorder, post-traumatic stress disorder, substance use disorders, obsessive-compulsive disorder, attention-deficit/hyperactivity disorder, autism spectrum disorders, epilepsy, and 22q11.2 deletion syndrome. More recent ENIGMA WGs have formed to study anxiety disorders, suicidal thoughts and behavior, sleep and insomnia, eating disorders, irritability, brain injury, antisocial personality and conduct disorder, and dissociative identity disorder. Here, we summarize the first decade of ENIGMA's activities and ongoing projects, and describe the successes and challenges encountered along the way. We highlight the advantages of collaborative large-scale coordinated data analyses for testing reproducibility and robustness of findings, offering the opportunity to identify brain systems involved in clinical syndromes across diverse samples and associated genetic, environmental, demographic, cognitive, and psychosocial factors.
View Article and Find Full Text PDF

Download full-text PDF

Source
http://dx.doi.org/10.1038/s41398-020-0705-1DOI Listing
http://www.ncbi.nlm.nih.gov/pmc/articles/PMC7083923PMC
March 2020

Commentary: Correction procedures in brain-age prediction.

Neuroimage Clin 2020 24;26:102229. Epub 2020 Feb 24.

Centre for Medical Image Computing, Department of Computer Science, University College London, London, UK; Dementia Research Centre, Institute of Neurology, University College London, London, UK.

View Article and Find Full Text PDF

Download full-text PDF

Source
http://dx.doi.org/10.1016/j.nicl.2020.102229DOI Listing
http://www.ncbi.nlm.nih.gov/pmc/articles/PMC7049655PMC
September 2020

Attitudes to ageing, biomarkers of ageing and mortality: the Lothian Birth Cohort 1936.

J Epidemiol Community Health 2020 04 28;74(4):377-383. Epub 2020 Jan 28.

Psychology, The University of Edinburgh, Edinburgh, UK

Objective: To investigate whether people with more positive attitudes to ageing are biologically younger as defined by leucocyte telomere length, accelerated DNA methylation GrimAge (AgeAccelGrim) and brain-predicted age difference, and whether these biomarkers explain relationships between attitudes to ageing and mortality.

Methods: We used linear regression to examine cross-sectionally attitudes to ageing (measured using the Attitudes to Ageing Questionnaire) and the three biomarkers in 758 adults, mean age 72.5 years, from the Lothian Birth Cohort 1936. We used Cox proportional hazards models to examine longitudinally attitudes to ageing and mortality and the role of the biomarkers.

Results: More positive attitude to physical change was associated with younger biological age, as measured by AgeAccelGrim and brain-predicted age difference in age-adjusted and sex-adjusted models: for an SD higher score, AgeAccelGrim was lower by -0.73 (95% CI -1.03 to -0.42) of a year, and brain-predicted age difference was lower by -0.87 (1.51 to 0.23) of a year. Both associations were attenuated by adjustment for covariates and not significant after simultaneous adjustment for all covariates and correction for multiple testing. More positive attitudes to physical change were associated with lower mortality: for an SD higher score the age-adjusted and sex-adjusted HR (95% CI) was 0.66 (0.56 to 0.78). Adjustment for AgeAccelGrim or brain-predicted age difference attenuated this association slightly. It remained significant after adjustment for all covariates.

Conclusion: We found partial evidence that attitudes to ageing are linked with ageing biomarkers but they accounted for only a little of the association between attitudes and mortality.
View Article and Find Full Text PDF

Download full-text PDF

Source
http://dx.doi.org/10.1136/jech-2019-213462DOI Listing
http://www.ncbi.nlm.nih.gov/pmc/articles/PMC7079194PMC
April 2020

Active Acquisition for multimodal neuroimaging.

Wellcome Open Res 2018 23;3:145. Epub 2019 Sep 23.

Department of Neuroimaging, Institute of Psychiatry, Psychology and Neurosciences, King's College London, London, UK.

In many clinical and scientific situations the optimal neuroimaging sequence may not be known prior to scanning and may differ for each individual being scanned, depending on the exact nature and location of abnormalities. Despite this, the standard approach to data acquisition, in such situations, is to specify the sequence of neuroimaging scans prior to data acquisition and to apply the same scans to all individuals. In this paper, we propose and illustrate an alternative approach, in which data would be analysed as it is acquired and used to choose the future scanning sequence: Active Acquisition. We propose three Active Acquisition scenarios based around multiple MRI modalities. In Scenario 1, we propose a simple use of near-real time analysis to decide whether to acquire more or higher resolution data, or acquire data with a different field of view. In Scenario 2, we simulate how multimodal MR data could be actively acquired and combined with a decision tree to classify a known outcome variable (in the simple example here, age). In Scenario 3, we simulate using Bayesian optimisation to actively search across multiple MRI modalities to find those which are most abnormal. These simulations suggest that by actively acquiring data, the scanning sequence can be adapted to each individual. We also consider the many outstanding practical and technical challenges involving normative data acquisition, MR physics, statistical modelling and clinical relevance. Despite these, we argue that Active Acquisition allows for potentially far more powerful, sensitive or rapid data acquisition, and may open up different perspectives on individual differences, clinical conditions, and biomarker discovery.
View Article and Find Full Text PDF

Download full-text PDF

Source
http://dx.doi.org/10.12688/wellcomeopenres.14918.2DOI Listing
http://www.ncbi.nlm.nih.gov/pmc/articles/PMC6807153PMC
September 2019

Dopamine D2/D3 receptor abnormalities after traumatic brain injury and their relationship to post-traumatic depression.

Neuroimage Clin 2019 22;24:101950. Epub 2019 Jul 22.

Division of Brain Sciences, Department of Medicine, Imperial College London, UK. Electronic address:

Objective: To investigate dopamine D2/D3 receptor availability following traumatic brain injury (TBI) and their relationship to the presence of DSM-IV Major Depressive Disorder (MDD) and patterns of axonal injury.

Methods: Twelve moderate-severe TBI patients and 26 controls were imaged using [C]PHNO positron emission tomography (PET) and structural magnetic resonance imaging (MRI). TBI patients and a second group of 32 controls also underwent diffusion tensor imaging (DTI) and neuropsychological assessment. Patients included six with post-injury MDD (TBI-MDD) and six without (TBI-NON). Non-displaceable binding potential (BP) [C]PHNO values were used to index D2/D3 receptor availability, and were calculated using a reference region procedure. Differences in BP were examined using voxelwise and region-of-interest analyses. White matter microstructure integrity, quantified by fractional anisotropy (FA), was assessed and correlated with BP.

Results: Lower [C]PHNO BP was found in the caudate across all TBI patients when compared to controls. Lower [C]PHNO BP was observed in the caudate of TBI-MDD patients and increased [C]PHNO BP in the Amygdala of TBI-NON patients compared to controls. There were no significant differences in [C]PHNO BP between TBI-MDD and TBI-NON patients. Furthermore, DTI provided evidence of axonal injury following TBI. The uncinate fasciculus and cingulum had abnormally low FA, with the uncinate particularly affected in TBI-MDD patients. Caudate [C]PHNO BP correlated with FA within the nigro-caudate tract.

Conclusions: [C]PHNO BP is abnormal following TBI, which indicates post-traumatic changes in D2/D3 receptors. Patterns of [C]PHNO BP seen in patients with and without MDD suggest that further research would be beneficial to determine whether the use of dopaminergic treatment might be effective in the treatment of post-traumatic depression.
View Article and Find Full Text PDF

Download full-text PDF

Source
http://dx.doi.org/10.1016/j.nicl.2019.101950DOI Listing
http://www.ncbi.nlm.nih.gov/pmc/articles/PMC6664227PMC
September 2020

Validation of a Novel Multivariate Method of Defining HIV-Associated Cognitive Impairment.

Open Forum Infect Dis 2019 Jun 3;6(6):ofz198. Epub 2019 May 3.

Division of Infectious Diseases, Imperial College London, UK.

Background: The optimum method of defining cognitive impairment in virally suppressed people living with HIV is unknown. We evaluated the relationships between cognitive impairment, including using a novel multivariate method (NMM), patient- reported outcome measures (PROMs), and neuroimaging markers of brain structure across 3 cohorts.

Methods: Differences in the prevalence of cognitive impairment, PROMs, and neuroimaging data from the COBRA, CHARTER, and POPPY cohorts (total n = 908) were determined between HIV-positive participants with and without cognitive impairment defined using the HIV-associated neurocognitive disorders (HAND), global deficit score (GDS), and NMM criteria.

Results: The prevalence of cognitive impairment varied by up to 27% between methods used to define impairment (eg, 48% for HAND vs 21% for NMM in the CHARTER study). Associations between objective cognitive impairment and subjective cognitive complaints generally were weak. Physical and mental health summary scores (SF-36) were lowest for NMM-defined impairment ( < .05).There were no differences in brain volumes or cortical thickness between participants with and without cognitive impairment defined using the HAND and GDS measures. In contrast, those identified with cognitive impairment by the NMM had reduced mean cortical thickness in both hemispheres ( < .05), as well as smaller brain volumes ( < .01). The associations with measures of white matter microstructure and brain-predicted age generally were weaker.

Conclusion: Different methods of defining cognitive impairment identify different people with varying symptomatology and measures of brain injury. Overall, NMM-defined impairment was associated with most neuroimaging abnormalities and poorer self-reported health status. This may be due to the statistical advantage of using a multivariate approach.
View Article and Find Full Text PDF

Download full-text PDF

Source
http://dx.doi.org/10.1093/ofid/ofz198DOI Listing
http://www.ncbi.nlm.nih.gov/pmc/articles/PMC6590980PMC
June 2019

Stratifying drug treatment of cognitive impairments after traumatic brain injury using neuroimaging.

Brain 2019 08;142(8):2367-2379

Computational, Cognitive and Clinical Neuroimaging Laboratory, Imperial College London, Division of Brain Sciences, Hammersmith Hospital, London, UK.

Cognitive impairment is common following traumatic brain injury. Dopaminergic drugs can enhance cognition after traumatic brain injury, but individual responses are highly variable. This may be due to variability in dopaminergic damage between patients. We investigate whether measuring dopamine transporter levels using 123I-ioflupane single-photon emission computed tomography (SPECT) predicts response to methylphenidate, a stimulant with dopaminergic effects. Forty patients with moderate-severe traumatic brain injury and cognitive impairments completed a randomized, double-blind, placebo-controlled, crossover study. 123I-ioflupane SPECT, MRI and neuropsychological testing were performed. Patients received 0.3 mg/kg of methylphenidate or placebo twice a day in 2-week blocks. Subjects received neuropsychological assessment after each block and completed daily home cognitive testing during the trial. The primary outcome measure was change in choice reaction time produced by methylphenidate and its relationship to stratification of patients into groups with normal and low dopamine transporter binding in the caudate. Overall, traumatic brain injury patients showed slow information processing speed. Patients with low caudate dopamine transporter binding showed improvement in response times with methylphenidate compared to placebo [median change = -16 ms; 95% confidence interval (CI): -28 to -3 ms; P = 0.02]. This represents a 27% improvement in the slowing produced by traumatic brain injury. Patients with normal dopamine transporter binding did not improve. Daily home-based choice reaction time results supported this: the low dopamine transporter group improved (median change -19 ms; 95% CI: -23 to -7 ms; P = 0.002) with no change in the normal dopamine transporter group (P = 0.50). The low dopamine transporter group also improved on self-reported and caregiver apathy assessments (P = 0.03 and P = 0.02, respectively). Both groups reported improvements in fatigue (P = 0.03 and P = 0.007). The cognitive effects of methylphenidate after traumatic brain injury were only seen in patients with low caudate dopamine transporter levels. This shows that identifying patients with a hypodopaminergic state after traumatic brain injury can help stratify the choice of cognitive enhancing therapy.
View Article and Find Full Text PDF

Download full-text PDF

Source
http://dx.doi.org/10.1093/brain/awz149DOI Listing
August 2019

Increased brain age in adults with Prader-Willi syndrome.

Neuroimage Clin 2019 10;21:101664. Epub 2019 Jan 10.

Cambridge Intellectual and Developmental Disabilities Research Group, Academic Department of Psychiatry, University of Cambridge, Cambridge, UK. Electronic address:

Prader-Willi syndrome (PWS) is the most common genetic obesity syndrome, with associated learning difficulties, neuroendocrine deficits, and behavioural and psychiatric problems. As the life expectancy of individuals with PWS increases, there is concern that alterations in brain structure associated with the syndrome, as a direct result of absent expression of PWS genes, and its metabolic complications and hormonal deficits, might cause early onset of physiological and brain aging. In this study, a machine learning approach was used to predict brain age based on grey matter (GM) and white matter (WM) maps derived from structural neuroimaging data using T1-weighted magnetic resonance imaging (MRI) scans. Brain-predicted age difference (brain-PAD) scores, calculated as the difference between chronological age and brain-predicted age, are designed to reflect deviations from healthy brain aging, with higher brain-PAD scores indicating premature aging. Two separate adult cohorts underwent brain-predicted age calculation. The main cohort consisted of adults with PWS (n = 20; age mean 23.1 years, range 19.8-27.7; 70.0% male; body mass index (BMI) mean 30.1 kg/m, 21.5-47.7; n = 19 paternal chromosome 15q11-13 deletion) and age- and sex-matched controls (n = 40; age 22.9 years, 19.6-29.0; 65.0% male; BMI 24.1 kg/m, 19.2-34.2) adults (BMI PWS vs. control P = .002). Brain-PAD was significantly greater in PWS than controls (effect size mean ± SEM +7.24 ± 2.20 years [95% CI 2.83, 11.63], P = .002). Brain-PAD remained significantly greater in PWS than controls when restricting analysis to a sub-cohort matched for BMI consisting of n = 15 with PWS with BMI range 21.5-33.7 kg/m, and n = 29 controls with BMI 21.7-34.2 kg/m (effect size +5.51 ± 2.56 years [95% CI 3.44, 10.38], P = .037). In the PWS group, brain-PAD scores were not associated with intelligence quotient (IQ), use of hormonal and psychotropic medications, nor severity of repetitive or disruptive behaviours. A 24.5 year old man (BMI 36.9 kg/m) with PWS from a SNORD116 microdeletion also had increased brain PAD of 12.87 years, compared to 0.84 ± 6.52 years in a second control adult cohort (n = 95; age mean 34.0 years, range 19.9-55.5; 38.9% male; BMI 28.7 kg/m, 19.1-43.1). This increase in brain-PAD in adults with PWS indicates abnormal brain structure that may reflect premature brain aging or abnormal brain development. The similar finding in a rare patient with a SNORD116 microdeletion implicates a potential causative role for this PWS region gene cluster in the structural brain abnormalities associated primarily with the syndrome and/or its complications. Further longitudinal neuroimaging studies are needed to clarify the natural history of this increase in brain age in PWS, its relationship with obesity, and whether similar findings are seen in those with PWS from maternal uniparental disomy.
View Article and Find Full Text PDF

Download full-text PDF

Source
http://dx.doi.org/10.1016/j.nicl.2019.101664DOI Listing
http://www.ncbi.nlm.nih.gov/pmc/articles/PMC6412082PMC
January 2020

Associations between polygenic risk scores for four psychiatric illnesses and brain structure using multivariate pattern recognition.

Neuroimage Clin 2018 9;20:1026-1036. Epub 2018 Oct 9.

Department of Neuroimaging, Institute of Psychiatry, Psychology and Neuroscience, King's College London, London, UK; Department of Psychology, School of Arts and Social Sciences, City, University of London, London, UK. Electronic address:

Psychiatric illnesses are complex and polygenic. They are associated with widespread alterations in the brain, which are partly influenced by genetic factors. There have been some attempts to relate polygenic risk scores (PRS) - a measure of the overall genetic risk an individual carries for a disorder - to brain structure using univariate methods. However, PRS are likely associated with distributed and covarying effects across the brain. We therefore used multivariate machine learning in this proof-of-principle study to investigate associations between brain structure and PRS for four psychiatric disorders; attention deficit-hyperactivity disorder (ADHD), autism, bipolar disorder and schizophrenia. The sample included 213 individuals comprising patients with depression (69), bipolar disorder (33), and healthy controls (111). The five psychiatric PRSs were calculated based on summary data from the Psychiatric Genomics Consortium. T1-weighted magnetic resonance images were obtained and voxel-based morphometry was implemented in SPM12. Multivariate relevance vector regression was implemented in the Pattern Recognition for Neuroimaging Toolbox (PRoNTo). Across the whole sample, a multivariate pattern of grey matter significantly predicted the PRS for autism (r = 0.20, p = 0.03; MSE = 4.20 × 10, p = 0.02). For the schizophrenia PRS, the MSE was significant (MSE = 1.30 × 10, p = 0.02) although the correlation was not (r = 0.15, p = 0.06). These results lend support to the hypothesis that polygenic liability for autism and schizophrenia is associated with widespread changes in grey matter concentrations. These associations were seen in individuals not affected by these disorders, indicating that this is not driven by the expression of the disease, but by the genetic risk captured by the PRSs.
View Article and Find Full Text PDF

Download full-text PDF

Source
http://dx.doi.org/10.1016/j.nicl.2018.10.008DOI Listing
http://www.ncbi.nlm.nih.gov/pmc/articles/PMC6197704PMC
February 2019

Unravelling the GSK3β-related genotypic interaction network influencing hippocampal volume in recurrent major depressive disorder.

Psychiatr Genet 2018 10;28(5):77-84

Centre for Genomics and Experimental Medicine, Institute of Genetics and Molecular Medicine.

Objective: Glycogen synthase kinase 3β (GSK3β) has been implicated in mood disorders. We previously reported associations between a GSK3β polymorphism and hippocampal volume in major depressive disorder (MDD). We then reported similar associations for a subset of GSK3β-regulated genes. We now investigate an algorithm-derived comprehensive list of genes encoding proteins that directly interact with GSK3β to identify a genotypic network influencing hippocampal volume in MDD.

Participants And Methods: We used discovery (N=141) and replication (N=77) recurrent MDD samples. Our gene list was generated from the NetworKIN database. Hippocampal measures were derived using an optimized Freesurfer protocol. We identified interacting single nucleotide polymorphisms using the machine learning algorithm Random Forest and verified interactions using likelihood ratio tests between nested linear regression models.

Results: The discovery sample showed multiple two-single nucleotide polymorphism interactions with hippocampal volume. The replication sample showed a replicable interaction (likelihood ratio test: P=0.0088, replication sample; P=0.017, discovery sample; Stouffer's combined P=0.0007) between genes associated previously with endoplasmic reticulum stress, calcium regulation and histone modifications.

Conclusion: Our results provide genetic evidence supporting associations between hippocampal volume and MDD, which may reflect underlying cellular stress responses. Our study provides evidence of biological mechanisms that should be further explored in the search for disease-modifying therapeutic targets for depression.
View Article and Find Full Text PDF

Download full-text PDF

Source
http://dx.doi.org/10.1097/YPG.0000000000000203DOI Listing
http://www.ncbi.nlm.nih.gov/pmc/articles/PMC6531290PMC
October 2018

Clinical research cerebral MRI findings in HIV-positive subjects and appropriate controls.

AIDS 2018 09;32(14):2077-2081

Section of Infectious Diseases, Department of Medicine, Imperial College London.

: Abnormalities in cerebral MRI are frequently reported in persons living with HIV (PLWH). We compared clinical cerebral MRI reports in 59 PLWH and 29 lifestyle matched controls. Although clinical abnormalities were highly prevalent (47.7%), and included white-matter lesions (46.6%), microvascular disease (22.7%) and cerebral volume loss (11.4%), no differences were apparent between PLWH and controls, with abnormalities being associated with age and hypertension rather than HIV serostatus.
View Article and Find Full Text PDF

Download full-text PDF

Source
http://dx.doi.org/10.1097/QAD.0000000000001910DOI Listing
September 2018

Brain age and other bodily 'ages': implications for neuropsychiatry.

Mol Psychiatry 2019 02 11;24(2):266-281. Epub 2018 Jun 11.

Centre for Cognitive Ageing and Cognitive Epidemiology, University of Edinburgh, Edinburgh, UK.

As our brains age, we tend to experience cognitive decline and are at greater risk of neurodegenerative disease and dementia. Symptoms of chronic neuropsychiatric diseases are also exacerbated during ageing. However, the ageing process does not affect people uniformly; nor, in fact, does the ageing process appear to be uniform even within an individual. Here, we outline recent neuroimaging research into brain ageing and the use of other bodily ageing biomarkers, including telomere length, the epigenetic clock, and grip strength. Some of these techniques, using statistical approaches, have the ability to predict chronological age in healthy people. Moreover, they are now being applied to neurological and psychiatric disease groups to provide insights into how these diseases interact with the ageing process and to deliver individualised predictions about future brain and body health. We discuss the importance of integrating different types of biological measurements, from both the brain and the rest of the body, to build more comprehensive models of the biological ageing process. Finally, we propose seven steps for the field of brain-ageing research to take in coming years. This will help us reach the long-term goal of developing clinically applicable statistical models of biological processes to measure, track and predict brain and body health in ageing and disease.
View Article and Find Full Text PDF

Download full-text PDF

Source
http://dx.doi.org/10.1038/s41380-018-0098-1DOI Listing
http://www.ncbi.nlm.nih.gov/pmc/articles/PMC6344374PMC
February 2019

Neuroimaging Studies Illustrate the Commonalities Between Ageing and Brain Diseases.

Authors:
James H Cole

Bioessays 2018 07 8;40(7):e1700221. Epub 2018 Jun 8.

Department of Neuroimaging, Institute of Psychiatry, Psychology & Neuroscience King's College London, London, SE5 8AF, UK.

The lack of specificity in neuroimaging studies of neurological and psychiatric diseases suggests that these different diseases have more in common than is generally considered. Potentially, features that are secondary effects of different pathological processes may share common neurobiological underpinnings. Intriguingly, many of these mechanisms are also observed in studies of normal (i.e., non-pathological) brain ageing. Different brain diseases may be causing premature or accelerated ageing to the brain, an idea that is supported by a line of "brain ageing" research that combines neuroimaging data with machine learning analysis. In reviewing this field, I conclude that such observations could have important implications, suggesting that we should shift experimental paradigm: away from characterizing the average case-control brain differences resulting from a disease toward methods that place individuals in their age-appropriate context. This will also lead naturally to clinical applications, whereby neuroimaging can contribute to a personalized-medicine approach to improve brain health.
View Article and Find Full Text PDF

Download full-text PDF

Source
http://dx.doi.org/10.1002/bies.201700221DOI Listing
July 2018

Multivariate Pattern Analysis of Volumetric Neuroimaging Data and Its Relationship With Cognitive Function in Treated HIV Disease.

J Acquir Immune Defic Syndr 2018 08;78(4):429-436

Division of Infectious Diseases, Imperial College London, United Kingdom.

Background: Accurate prediction of longitudinal changes in cognitive function would potentially allow for targeted intervention in those at greatest risk of cognitive decline. We sought to build a multivariate model using volumetric neuroimaging data alone to accurately predict cognitive function.

Methods: Volumetric T1-weighted neuroimaging data from virally suppressed HIV-positive individuals from the CHARTER cohort (n = 139) were segmented into gray and white matter and spatially normalized before entering into machine learning models. Prediction of cognitive function at baseline and longitudinally was determined using leave-one-out cross-validation. In addition, a multivariate model of brain aging was used to measure the deviation of apparent brain age from chronological age and assess its relationship with cognitive function.

Results: Cognitive impairment, defined using the global deficit score, was present in 37.4%. However, it was generally mild and occurred more commonly in those with confounding comorbidities (P < 0.001). Although multivariate prediction of cognitive impairment as a dichotomous variable at baseline was poor (area under the receiver operator curve 0.59), prediction of the global T-score was better than a comparable linear model (adjusted R = 0.08, P < 0.01 vs. adjusted R = 0.01, P = 0.14). Accurate prediction of longitudinal changes in cognitive function was not possible (P = 0.82). Brain-predicted age exceeded chronological age by mean (95% confidence interval) 1.17 (-0.14 to 2.53) years but was greatest in those with confounding comorbidities [5.87 (1.74 to 9.99) years] and prior AIDS [3.03 (0.00 to 6.06) years].

Conclusion: Accurate prediction of cognitive impairment using multivariate models using only T1-weighted data was not achievable, which may reflect the small sample size, heterogeneity of the data, or that impairment was usually mild.
View Article and Find Full Text PDF

Download full-text PDF

Source
http://dx.doi.org/10.1097/QAI.0000000000001687DOI Listing
http://www.ncbi.nlm.nih.gov/pmc/articles/PMC6019188PMC
August 2018

The 'COmorBidity in Relation to AIDS' (COBRA) cohort: Design, methods and participant characteristics.

PLoS One 2018 29;13(3):e0191791. Epub 2018 Mar 29.

Academisch Medisch Centrum, Universiteit van Amsterdam, Amsterdam, The Netherlands.

Background: Persons living with HIV on combination antiretroviral therapy (cART) may be at increased risk of the development of age-associated non-communicable comorbidities (AANCC) at relatively young age. It has therefore been hypothesised that such individuals, despite effective cART, may be prone to accelerated aging.

Objective: The COmorBidity in Relation to AIDS (COBRA) cohort study was designed to investigate the potential causal link between HIV and AANCC, amongst others, in a cohort of middle-aged individuals with HIV with sustained viral suppression on cART and otherwise comparable HIV-negative controls.

Methods: Longitudinal cohort study of HIV-positive subjects ≥45 years of age, with sustained HIV suppression on cART recruited from two large European HIV treatment centres and similarly-aged HIV-negative controls recruited from sexual health centres and targeted community groups. Both HIV-positive and HIV-negative subjects were assessed at study entry and again at follow-up after 2 years.

Results: Of the 134 HIV-positive individuals with a median (IQR) age of 56 (51, 62) years recruited, 93% were male, 88% of white ethnicity and 86% were men who have sex with men (MSM). Similarly, the 79 HIV-negative subjects had a median (IQR) age of 57 (52, 64) and 92% were male, 97% of white ethnicity and 80% were MSM.

Conclusions: The results from the COBRA study will be a significant resource to understand the link between HIV and AANCC and the pathogenic mechanisms underlying this link. COBRA will inform future development of novel prognostic tools for earlier diagnosis of AANCC and of novel interventions which, as an adjunct to cART, may prevent AANCC.
View Article and Find Full Text PDF

Download full-text PDF

Source
http://journals.plos.org/plosone/article?id=10.1371/journal.pone.0191791PLOS
http://www.ncbi.nlm.nih.gov/pmc/articles/PMC5875743PMC
June 2018

Bayesian Optimization for Neuroimaging Pre-processing in Brain Age Classification and Prediction.

Front Aging Neurosci 2018 12;10:28. Epub 2018 Feb 12.

Computational, Cognitive and Clinical Neuroimaging Laboratory, Division of Brain Sciences, Department of Medicine, Imperial College London, London, United Kingdom.

Neuroimaging-based age prediction using machine learning is proposed as a biomarker of brain aging, relating to cognitive performance, health outcomes and progression of neurodegenerative disease. However, even leading age-prediction algorithms contain measurement error, motivating efforts to improve experimental pipelines. T1-weighted MRI is commonly used for age prediction, and the pre-processing of these scans involves normalization to a common template and resampling to a common voxel size, followed by spatial smoothing. Resampling parameters are often selected arbitrarily. Here, we sought to improve brain-age prediction accuracy by optimizing resampling parameters using Bayesian optimization. Using data on = 2003 healthy individuals (aged 16-90 years) we trained support vector machines to (i) distinguish between young (<22 years) and old (>50 years) brains (classification) and (ii) predict chronological age (regression). We also evaluated generalisability of the age-regression model to an independent dataset (CamCAN, = 648, aged 18-88 years). Bayesian optimization was used to identify optimal voxel size and smoothing kernel size for each task. This procedure adaptively samples the parameter space to evaluate accuracy across a range of possible parameters, using independent sub-samples to iteratively assess different parameter combinations to arrive at optimal values. When distinguishing between young and old brains a classification accuracy of 88.1% was achieved, (optimal voxel size = 11.5 mm, smoothing kernel = 2.3 mm). For predicting chronological age, a mean absolute error (MAE) of 5.08 years was achieved, (optimal voxel size = 3.73 mm, smoothing kernel = 3.68 mm). This was compared to performance using default values of 1.5 mm and 4mm respectively, resulting in MAE = 5.48 years, though this 7.3% improvement was not statistically significant. When assessing generalisability, best performance was achieved when applying the entire Bayesian optimization framework to the new dataset, out-performing the parameters optimized for the initial training dataset. Our study outlines the proof-of-principle that neuroimaging models for brain-age prediction can use Bayesian optimization to derive case-specific pre-processing parameters. Our results suggest that different pre-processing parameters are selected when optimization is conducted in specific contexts. This potentially motivates use of optimization techniques at many different points during the experimental process, which may improve statistical sensitivity and reduce opportunities for experimenter-led bias.
View Article and Find Full Text PDF

Download full-text PDF

Source
http://dx.doi.org/10.3389/fnagi.2018.00028DOI Listing
http://www.ncbi.nlm.nih.gov/pmc/articles/PMC5816033PMC
February 2018
-->