Data-driven modelling of neurodegenerative disease progression: thinking outside the black box

Nature reviews. Neuroscience, Год журнала: 2024, Номер 25(2), С. 111 - 130

Опубликована: Янв. 8, 2024

Язык: Английский

---

A synergetic turn in cognitive neuroscience of brain diseases

Trends in Cognitive Sciences, Год журнала: 2024, Номер 28(4), С. 319 - 338

Опубликована: Янв. 21, 2024

Язык: Английский

---

Visual deep learning of unprocessed neuroimaging characterises dementia subtypes and generalises across non-stereotypic samples

EBioMedicine, Год журнала: 2023, Номер 90, С. 104540 - 104540

Опубликована: Март 25, 2023

Dementia's diagnostic protocols are mostly based on standardised neuroimaging data collected in the Global North from homogeneous samples. In other non-stereotypical samples (participants with diverse admixture, genetics, demographics, MRI signals, or cultural origins), classifications of disease difficult due to demographic and region-specific sample heterogeneities, lower quality scanners, non-harmonised pipelines.We implemented a fully automatic computer-vision classifier using deep learning neural networks. A DenseNet was applied raw (unpreprocessed) 3000 participants (behavioural variant frontotemporal dementia-bvFTD, Alzheimer's disease-AD, healthy controls; both male female as self-reported by participants). We tested our results demographically matched unmatched discard possible biases performed multiple out-of-sample validations.Robust classification across all groups were achieved 3T North, which also generalised Latin America. Moreover, non-standardised, routine 1.5T clinical images These generalisations robust heterogenous recordings not confounded demographics (i.e., samples, when incorporating variables multifeatured model). Model interpretability analysis occlusion sensitivity evidenced core pathophysiological regions for each (mainly hippocampus AD, insula bvFTD) demonstrating biological specificity plausibility.The generalisable approach outlined here could be used future aid clinician decision-making samples.The specific funding this article is provided acknowledgements section.

Язык: Английский

---

Model-based whole-brain perturbational landscape of neurodegenerative diseases

eLife, Год журнала: 2023, Номер 12

Опубликована: Март 30, 2023

The treatment of neurodegenerative diseases is hindered by lack interventions capable steering multimodal whole-brain dynamics towards patterns indicative preserved brain health. To address this problem, we combined deep learning with a model reproducing functional connectivity in patients diagnosed Alzheimer’s disease (AD) and behavioral variant frontotemporal dementia (bvFTD). These models included disease-specific atrophy maps as priors to modulate local parameters, revealing increased stability hippocampal insular signatures AD bvFTD, respectively. Using variational autoencoders, visualized different pathologies their severity the evolution trajectories low-dimensional latent space. Finally, perturbed reveal key AD- bvFTD-specific regions induce transitions from pathological healthy states. Overall, obtained novel insights on progression control means external stimulation, while identifying dynamical mechanisms that underlie alterations neurodegeneration.

Язык: Английский

---

Heterogeneous factors influence social cognition across diverse settings in brain health and age-related diseases

Nature Mental Health, Год журнала: 2024, Номер 2(1), С. 63 - 75

Опубликована: Янв. 2, 2024

Abstract Aging diminishes social cognition, and changes in this capacity can indicate brain diseases. However, the relative contribution of age, diagnosis reserve to especially among older adults global settings, remains unclear when considering other factors. Here, using a computational approach, we combined predictors cognition from diverse sample 1,063 across nine countries. Emotion recognition, mentalizing overall were predicted via support vector regressions various factors, including (subjective cognitive complaints, mild impairment, Alzheimer’s disease behavioral variant frontotemporal dementia), demographics, cognition/executive function, motion artifacts functional magnetic resonance imaging recordings. Higher cognitive/executive functions education ranked top predictors, outweighing reserve. Network connectivity did not show predictive values. The results challenge traditional interpretations age-related decline, patient–control differences associations emphasizing importance heterogeneous

Язык: Английский

---

The BrainLat project, a multimodal neuroimaging dataset of neurodegeneration from underrepresented backgrounds

Scientific Data, Год журнала: 2023, Номер 10(1)

Опубликована: Дек. 9, 2023

Abstract The Latin American Brain Health Institute (BrainLat) has released a unique multimodal neuroimaging dataset of 780 participants from American. includes 530 patients with neurodegenerative diseases such as Alzheimer’s disease (AD), behavioral variant frontotemporal dementia (bvFTD), multiple sclerosis (MS), Parkinson’s (PD), and 250 healthy controls (HCs). This (62.7 ± 9.5 years, age range 21–89 years) was collected through multicentric effort across five countries to address the need for affordable, scalable, available biomarkers in regions larger inequities. BrainLat is first regional collection clinical cognitive assessments, anatomical magnetic resonance imaging (MRI), resting-state functional MRI (fMRI), diffusion-weighted (DWI), high density electroencephalography (EEG) patients. In addition, it demographic information about harmonized recruitment assessment protocols. publicly encourage further research development tools health applications neurodegeneration based on neuroimaging, promoting variability inclusion underrepresented research.

Язык: Английский

---

Viscous dynamics associated with hypoexcitation and structural disintegration in neurodegeneration via generative whole‐brain modeling

Alzheimer s & Dementia, Год журнала: 2024, Номер 20(5), С. 3228 - 3250

Опубликована: Март 19, 2024

Alzheimer's disease (AD) and behavioral variant frontotemporal dementia (bvFTD) lack mechanistic biophysical modeling in diverse, underrepresented populations. Electroencephalography (EEG) is a high temporal resolution, cost-effective technique for studying globally, but lacks models produces non-replicable results.

Язык: Английский

---

Advancements in dementia research, diagnostics, and care in Latin America: Highlights from the 2023 Alzheimer's Association International conference satellite symposium in Mexico City

Alzheimer s & Dementia, Год журнала: 2024, Номер 20(7), С. 5009 - 5026

Опубликована: Май 27, 2024

While Latin America (LatAm) is facing an increasing burden of dementia due to the rapid aging population, it remains underrepresented in research, diagnostics, and care.

Язык: Английский

---

Virtual Brain Inference (VBI): A flexible and integrative toolkit for efficient probabilistic inference on virtual brain models

Опубликована: Май 21, 2025

Abstract Network neuroscience has proven essential for understanding the principles and mechanisms underlying complex brain (dys)function cognition. In this context, whole-brain network modeling–also known as virtual modeling–combines computational models of dynamics (placed at each node) with individual imaging data (to coordinate connect nodes), advancing our its neurobiological underpinnings. However, there remains a critical need automated model inversion tools to estimate control (bifurcation) parameters large scales across neuroimaging modalities, given their varying spatio-temporal resolutions. This study aims address gap by introducing flexible integrative toolkit efficient Bayesian inference on models, called Virtual Brain Inference (<monospace>VBI</monospace>). open-source provides fast simulations, taxonomy feature extraction, storage loading, probabilistic machine learning algorithms, enabling biophysically interpretable from non-invasive invasive recordings. Through in-silico testing, we demonstrate accuracy reliability commonly used associated data. <monospace>VBI</monospace> shows potential improve hypothesis evaluation in through uncertainty quantification, contribute advances precision medicine enhancing predictive power models.

Язык: Английский

---

Biophysical models applied to dementia patients reveal links between geographical origin, gender, disease duration, and loss of neural inhibition

Alzheimer s Research & Therapy, Год журнала: 2024, Номер 16(1)

Опубликована: Апрель 11, 2024

Abstract Background The hypothesis of decreased neural inhibition in dementia has been sparsely studied functional magnetic resonance imaging (fMRI) data across patients with different subtypes, and the role social demographic heterogeneities on this remains to be addressed. Methods We inferred regional by fitting a biophysical whole-brain model (dynamic mean field realistic inter-areal connectivity) fMRI from 414 participants, including Alzheimer’s disease, behavioral variant frontotemporal dementia, controls. then investigated effect disease condition, clinical variables local inhibitory feedback, variable related maintenance balanced excitation/inhibition. Results Decreased feedback was modeling results patients, specific brain areas presenting neurodegeneration. This loss correlated positively years showed differences regarding gender geographical origin patients. correctly reproduced known disease-related changes connectivity. Conclusions suggest critical link between abnormal circuit-level excitability levels, grey matter observed reorganization connectivity, while highlighting sensitivity underlying mechanism patient population.

Язык: Английский

---