Combining magnetoencephalography with magnetic resonance imaging enhances learning of surrogate-biomarkers
Abstract
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 a surrogate biomarker in 674 subjects from the Cam-CAN dataset. Strikingly, MEG, fMRI and MRI showed additive effects supporting distinct brain-behavior associations. Moreover, the contribution of MEG was best explained by cortical power spectra between 8 and 30 Hz. Finally, we demonstrate that the model preserves benefits of stacking when some data is missing. The proposed framework, hence, enables multimodal learning for a wide range of biomarkers from diverse types of brain signals.
Data availability
We used the publicly available Cam-CAN dataset. All software and code necessary to obtain the derivative data is shared on github: https://github.com/dengemann/meg-mri-surrogate-biomarkers-aging-2020
Article and author information
Author details
Funding
H2020 European Research Council (SLAB ERC-YStG-676943)
- Alexandre Gramfort
French National Institute of Computer Science (Medecine Numerique)
- Denis Alexander Engemann
The funders had no role in study design, data collection and interpretation, or the decision to submit the work for publication.
Ethics
Human subjects: This study is conducted in compliance with the Helsinki Declaration. No experiments on living beings were performed for this study. The data that we used was acquired by the Cam-CAN consortium and has been approved by the local ethics committee, Cambridgeshire 2 Research Ethics Committee (reference: 10/H0308/50).
Copyright
© 2020, Engemann et al.
This article is distributed under the terms of the Creative Commons Attribution License permitting unrestricted use and redistribution provided that the original author and source are credited.
Metrics
-
- 5,363
- views
-
- 612
- downloads
-
- 92
- citations
Views, downloads and citations are aggregated across all versions of this paper published by eLife.
Download links
Downloads (link to download the article as PDF)
Open citations (links to open the citations from this article in various online reference manager services)
Cite this article (links to download the citations from this article in formats compatible with various reference manager tools)
Further reading
-
- Neuroscience
A classic distinction from the domain of external attention is that between anticipatory orienting and subsequent re-orienting of attention to unexpected events. Whether and how humans also re-orient attention ‘in mind’ following expected and unexpected working-memory tests remains elusive. We leveraged spatial modulations in neural activity and gaze to isolate re-orienting within the spatial layout of visual working memory following central memory tests of certain, expected, or unexpected mnemonic content. Besides internal orienting after predictive cues, we unveil a second stage of internal attentional deployment following both expected and unexpected memory tests. Following expected tests, internal attentional deployment was not contingent on prior orienting, suggesting an additional verification – ‘double checking’ – in memory. Following unexpected tests, re-focusing of alternative memory content was prolonged. This brings attentional re-orienting to the domain of working memory and underscores how memory tests can invoke either a verification or a revision of our internal focus.
-
- Computational and Systems Biology
- Neuroscience
Accumulating evidence to make decisions is a core cognitive function. Previous studies have tended to estimate accumulation using either neural or behavioral data alone. Here, we develop a unified framework for modeling stimulus-driven behavior and multi-neuron activity simultaneously. We applied our method to choices and neural recordings from three rat brain regions—the posterior parietal cortex (PPC), the frontal orienting fields (FOF), and the anterior-dorsal striatum (ADS)—while subjects performed a pulse-based accumulation task. Each region was best described by a distinct accumulation model, which all differed from the model that best described the animal’s choices. FOF activity was consistent with an accumulator where early evidence was favored while the ADS reflected near perfect accumulation. Neural responses within an accumulation framework unveiled a distinct association between each brain region and choice. Choices were better predicted from all regions using a comprehensive, accumulation-based framework and different brain regions were found to differentially reflect choice-related accumulation signals: FOF and ADS both reflected choice but ADS showed more instances of decision vacillation. Previous studies relating neural data to behaviorally inferred accumulation dynamics have implicitly assumed that individual brain regions reflect the whole-animal level accumulator. Our results suggest that different brain regions represent accumulated evidence in dramatically different ways and that accumulation at the whole-animal level may be constructed from a variety of neural-level accumulators.