Denis Alexander Engemann

Assessing the robustness of deep learning based brain age prediction models across multiple EEG datasets

This study evaluates deep learning models for predicting brain age from EEG data across multiple datasets, finding that performance varies with dataset shifts and that certain hyperparameters improve generalization.

Neurologically altered brain activity may not look like aged brain activity: Implications for brain-age modeling and biomarker strategies

This study shows that brain-age gaps from EEG spectral power in neurological populations do not reflect accelerated aging, challenging the use of EEG as a biomarker for neurodegeneration.

GREEN: a lightweight architecture using learnable wavelets and Riemannian geometry for biomarker exploration

GREEN is a lightweight neural network that combines wavelet transforms and Riemannian geometry for EEG biomarker analysis, outperforming non-deep models and large DL models with fewer parameters.

Machine learning of brain-specific biomarkers from EEG

This study uses machine learning to analyze EEG data and shows that both brain and peripheral signals contribute to predicting age and sex, but brain signals are more effective for CNS-specific biomarkers.

Do try this at home: Age prediction from sleep and meditation with large-scale low-cost mobile EEG

This study predicts age from at-home EEG data during sleep and meditation, achieving R2 scores of 0.3-0.5, comparable to lab-grade EEG benchmarks.

Harmonizing and aligning M/EEG datasets with covariance-based techniques to enhance predictive regression modeling

This paper improves M/EEG-based regression models by applying covariance-based domain adaptation techniques to address dataset shifts across different recording contexts.

Event-related modulation of alpha rhythm explains the auditory P300 evoked response in EEG

The paper links the P300 evoked response and alpha oscillations in EEG through a baseline-shift mechanism, showing they share temporal, spatial, and cognitive correlations.

A reusable benchmark of brain-age prediction from M/EEG resting-state signals

This paper benchmarks machine learning approaches for brain age prediction using M/EEG signals across four international cohorts, finding that spatially aware models achieve the highest performance.

Population modeling with machine learning can enhance measures of mental health

This paper uses machine learning on brain imaging and sociodemographic data from the UK Biobank to create proxy measures of psychological constructs, which are as useful or more useful than traditional assessments for predicting health behaviors.

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

The paper predicts future cognitive decline using non-brain and multimodal brain imaging data in healthy and pathological aging, finding that non-brain data and structural MRI improve predictions.

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

This paper develops predictive models for continuous biomedical outcomes from M/EEG data, comparing supervised spatial filtering and Riemannian geometry approaches, and finds Riemannian methods are more robust to anatomical distortions.

Combining electrophysiology with MRI enhances learning of surrogate-biomarkers

The paper combines MEG, MRI, and fMRI to predict age as a surrogate biomarker, showing additive effects and demonstrating robustness to missing data.

Combined behavioral and electrophysiological evidence for a direct cortical effect of prefrontal tDCS on disorders of consciousness

This study shows that tDCS applied to the prefrontal cortex improves behavior and EEG markers of consciousness in some DoC patients.

Emergence of β and γ networks following multisensory training

The paper shows that multisensory training leads to increased beta and gamma network synchronization in prefrontal, parietal, and visual cortices, improving perceptual task efficiency.

Semantic coding in the occipital cortex of early blind individuals

This study investigates whether the visual cortex of early blind individuals codes for word meaning by comparing neuronal activity during a semantic decision task using MEG between blind and sighted participants.

MEG/EEG group study with MNE: recommendations, quality assessments and best practices

The paper reanalyzes an open MEG/EEG dataset using MNE to compare different analysis strategies and provide best practices for group studies.

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

The paper compares statistical inference and prediction methods in biomedical data, showing they often diverge in performance and interpretation.