Biology subjects

Varoquaux, G.

Publications and source records attributed to Varoquaux, G..

8 recordsLinked to original sources

bioRxiv2020

Numerical Instabilities in Analytical Pipelines Lead to Large and Meaningful Variability in Brain Networks

The analysis of brain-imaging data requires complex processing pipelines to support findings on brain function or pathologies. Recent work has shown that variability in analytical decisions, small amounts of noise, or computational environments can lead to substantial differences in the results, endangering the trust in conclusions1-7. We explored the instability of results by instrumenting a connectome estimation pipeline with Monte Carlo Arithmetic8,9 to introduce random noise throughout. We evaluated the reliability of the connectomes, their features10,11, and the impact on analysis12,13. The stability of results was found to range from perfectly stable to highly unstable. This paper highlights the potential of leveraging induced variance in estimates of brain connectivity to reduce the bias in networks alongside increasing the robustness of their applications in the classification of individual differences. We demonstrate that stability evaluations are necessary for understanding error inherent to brain imaging experiments, and how numerical analysis can be applied to typical analytical workflows both in brain imaging and other domains of computational science. Overall, while the extreme variability in results due to analytical instabilities could severely hamper our understanding of brain organization, it also leads to an increase in the reliability of datasets.

neuroscience↗

bioRxiv2020

Beyond brain age: Empirically-derived proxy measures of mental health

BackgroundBiological aging is revealed by physical measures, e.g., DNA probes or brain scans. Instead, individual differences in mental function are explained by psychological constructs, e.g., intelligence or neuroticism. These constructs are typically assessed by tailored neuropsychological tests that build on expert judgement and require careful interpretation. Could machine learning on large samples from the general population be used to build proxy measures of these constructs that do not require human intervention? ResultsHere, we built proxy measures by applying machine learning on multimodal MR images and rich sociodemographic information from the largest biomedical cohort to date: the UK Biobank. Objective model comparisons revealed that all proxies captured the target constructs and were as useful, and sometimes more useful than the original measures for characterizing real-world health behavior (sleep, exercise, tobacco, alcohol consumption). We observed this complementarity of proxy measures and original measures when modeling from brain signals or sociodemographic data, capturing multiple health-related constructs. ConclusionsPopulation modeling with machine learning can derive measures of mental health from brain signals and questionnaire data, which may complement or even substitute for psychometric assessments in clinical populations. Key PointsO_LIWe applied machine learning on more than 10.000 individuals from the general population to define empirical approximations of health-related psychological measures that do not require human judgment. C_LIO_LIWe found that machine-learning enriched the given psychological measures via approximation from brain and sociodemographic data: Resulting proxy measures related as well or better to real-world health behavior than the original measures. C_LIO_LIModel comparisons showed that sociodemographic information contributed most to characterizing psychological traits beyond aging. C_LI

neuroscience↗

bioRxiv2020

Predicting future cognitive decline from non-brain and multimodal brain imaging data in healthy and pathological aging

Cognitive decline occurs in healthy and pathological aging, and both may be preceded by subtle changes in the brain -- offering a basis for cognitive predictions. Previous work has largely focused on predicting a diagnostic label from structural brain imaging. Our study broadens the scope of applications to cognitive decline in healthy aging by predicting future decline as a continuous trajectory, rather than a diagnostic label. Furthermore, since brain structure as well as function changes in aging, it is reasonable to expect predictive gains when using multiple brain imaging modalities. Here, we tested whether baseline multimodal neuroimaging data improve the prediction of future cognitive decline in healthy and pathological aging. Non-brain data (including demographics and clinical and neuropsychological scores) were combined with structural and functional connectivity MRI data from the OASIS-3 project (N = 662; age = 46 - 96y). The combined input data was entered into cross-validated multi-target random forest models to predict future cognitive decline (measured by the Clinical Dementia Rating and the Mini-Mental State Examination), on average 5.8y into the future. The analysis was preregistered and all analysis code is publicly available. We found that combining non-brain with structural data improved the continuous prediction of future cognitive decline (best test-set performance: R2 = 0.42) and that cognitive performance, daily functioning, and subcortical volume drove the performance of our model. In contrast, including functional connectivity did not improve predictive accuracy. In the future, the prognosis of age-related cognitive decline may enable earlier and more effective cognitive, pharmacological, and behavioral interventions to be tailored to the individual.

neuroscience↗

bioRxiv2019

Combining electrophysiology with MRI enhances learning of surrogate-biomarkers

Electrophysiological methods, i.e., M/EEG provide unique views into brain health. Yet, when building predictive models from brain data, it is often unclear how electrophysiology should be combined with other neuroimaging methods. Information can be redundant, useful common representations of multimodal data may not be obvious and multimodal data collection can be medically contraindicated, which reduces applicability. Here, we propose a multimodal model to robustly combine MEG, MRI and fMRI for prediction. We focus on age prediction as surrogate biomarker in 674 subjects from the Cam-CAN. Strikingly, MEG, fMRI and MRI showed additive effects supporting distinct brain-behavior associations. Moreover, the contribution of MEG was best explained by source-topography of power spectra between 8 and 30 Hz. Finally, we demonstrate that the model maintains benefits of stacking when data is missing. The proposed framework hence enables multimodal learning for a wide range of biomarkers from diverse types of brain signals.

neuroscience↗

bioRxiv2019

Predictive regression modeling with MEG/EEG: from source power to signals and cognitive states

Predicting biomedical outcomes from Magnetoencephalography and Electroencephalography (M/EEG) is central to applications like decoding, brain-computer-interfaces (BCI) or biomarker development and is facilitated by supervised machine learning. Yet most of the literature is concerned with classification of outcomes defined at the event-level. Here, we focus on predicting continuous outcomes from M/EEG signal defined at the subject-level, and analyze about 600 MEG recordings from Cam-CAN dataset and about 1000 EEG recordings from TUH dataset. Considering different generative mechanisms for M/EEG signals and the biomedical outcome, we propose statistically-consistent predictive models that avoid source-reconstruction based on the covariance as representation. Our mathematical analysis and ground truth simulations demonstrated that consistent function approximation can be obtained with supervised spatial filtering or by embedding with Riemannian geometry. Additional simulations revealed that Riemannian methods were more robust to model violations, in particular geometric distortions induced by individual anatomy. To estimate the relative contribution of brain dynamics and anatomy to prediction performance, we propose a novel model inspection procedure based on biophysical forward modeling. Applied to prediction of outcomes at the subject-level, the analysis revealed that the Riemannian model better exploited anatomical information while sensitivity to brain dynamics was similar across methods. We then probed the robustness of the models across different data cleaning options. Environmental denoising was globally important but Riemannian models were strikingly robust and continued performing well even without preprocessing. Our results suggest each method has its niche: supervised spatial filtering is practical for event-level prediction while the Riemannian model may enable simple end-to-end learning.

neuroscience↗

bioRxiv2018

Brain-based ranking of cognitive domains to predict schizophrenia

Schizophrenia is a devastating brain disorder that disturbs sensory perception, motor action, and abstract thought. Its clinical phenotype implies dysfunction of various mental domains, which has motivated a series of theories regarding the underlying pathophysiology. Aiming at a predictive benchmark of a catalogue of cognitive functions, we developed a bottom-up machine-learning strategy and provide a proof of principle in a multi-site clinical dataset (n=324). Existing neuroscientific knowledge on diverse cognitive domains was first condensed into neuro-topographical maps. We then examined how the ensuing meta-analytic cognitive priors can distinguish patients and controls using brain morphology and intrinsic functional connectivity. Some affected cognitive domains supported well-studied directions of research on auditory evaluation and social cognition. However, rarely suspected cognitive domains also emerged as disease-relevant, including self-oriented processing of bodily sensations in gustation and pain. Such algorithmic charting of the cognitive landscape can be used to make targeted recommendations for future mental health research.

neuroscience↗

bioRxiv2018

Prediction and inference diverge in biomedicine:Simulations and real-world data

In the 20th century many advances in biological knowledge and evidence-based medicine were supported by p-values and accompanying methods. In the beginning 21st century, ambitions towards precision medicine put a premium on detailed predictions for single individuals. The shift causes tension between traditional methods used to infer statistically significant group differences and burgeoning machine-learning tools suited to forecast an individuals future. This comparison applies the linear model for identifying significant contributing variables and for finding the most predictive variable sets. In systematic data simulations and common medical datasets, we explored how statistical inference and pattern recognition can agree and diverge. Across analysis scenarios, even small predictive performances typically coincided with finding underlying significant statistical relationships. However, even statistically strong findings with very low p-values shed little light on their value for achieving accurate prediction in the same dataset. More complete understanding of different ways to define important associations is a prerequisite for reproducible research findings that can serve to personalize clinical care.

bioinformatics↗

bioRxiv2016

Predicting brain-age from multimodal imaging data captures cognitive impairment

The disparity between the chronological age of an individual and their brain-age measured based on biological information has the potential to offer clinically-relevant biomarkers of neurological syndromes that emerge late in the lifespan. While prior brain-age prediction studies have relied exclusively on either structural or functional brain data, here we investigate how multimodal brainimaging data improves age prediction. Using cortical anatomy and whole-brain functional connectivity on a large adult lifespan sample (N = 2354, age 19-82), we found that multimodal data improves brain-based age prediction, resulting in a mean absolute prediction error of 4.29 years. Furthermore, we found that the discrepancy between predicted age and chronological age captures cognitive impairment. Importantly, the brain-age measure was robust to confounding effects: head motion did not drive brain-based age prediction and our models generalized reasonably to an independent dataset acquired at a different site (N = 475). Generalization performance was increased by training models on a larger and more heterogeneous dataset. The robustness of multimodal brain-age prediction to confounds, generalizability across sites, and sensitivity to clinically-relevant impairments, suggests promising future application to the early prediction of neurocognitive disorders.\n\nHighlightsO_LIBrain-based age prediction is improved with multimodal neuroimaging data.\nC_LIO_LIParticipants with cognitive impairment show increased brain aging.\nC_LIO_LIAge prediction models are robust to motion and generalize to independent datasets from other sites.\nC_LI

neuroscience↗