RESUMEN
Biophysically detailed neural models are a powerful technique to study neural dynamics in health and disease with a growing number of established and openly available models. A major challenge in the use of such models is that parameter inference is an inherently difficult and unsolved problem. Identifying unique parameter distributions that can account for observed neural dynamics, and differences across experimental conditions, is essential to their meaningful use. Recently, simulation based inference (SBI) has been proposed as an approach to perform Bayesian inference to estimate parameters in detailed neural models. SBI overcomes the challenge of not having access to a likelihood function, which has severely limited inference methods in such models, by leveraging advances in deep learning to perform density estimation. While the substantial methodological advancements offered by SBI are promising, their use in large scale biophysically detailed models is challenging and methods for doing so have not been established, particularly when inferring parameters that can account for time series waveforms. We provide guidelines and considerations on how SBI can be applied to estimate time series waveforms in biophysically detailed neural models starting with a simplified example and extending to specific applications to common MEG/EEG waveforms using the the large scale neural modeling framework of the Human Neocortical Neurosolver. Specifically, we describe how to estimate and compare results from example oscillatory and event related potential simulations. We also describe how diagnostics can be used to assess the quality and uniqueness of the posterior estimates. The methods described provide a principled foundation to guide future applications of SBI in a wide variety of applications that use detailed models to study neural dynamics.
Asunto(s)
Teorema de Bayes , Humanos , Simulación por ComputadorRESUMEN
The Brain Imaging Data Structure (BIDS) is a community-driven standard for the organization of data and metadata from a growing range of neuroscience modalities. This paper is meant as a history of how the standard has developed and grown over time. We outline the principles behind the project, the mechanisms by which it has been extended, and some of the challenges being addressed as it evolves. We also discuss the lessons learned through the project, with the aim of enabling researchers in other domains to learn from the success of BIDS.
RESUMEN
Background: Electroencephalography (EEG) is increasingly used for monitoring the depth of general anaesthesia, but EEG data from general anaesthesia monitoring are rarely reused for research. Here, we explored repurposing EEG monitoring from general anaesthesia for brain-age modelling using machine learning. We hypothesised that brain age estimated from EEG during general anaesthesia is associated with perioperative risk. Methods: We reanalysed four-electrode EEGs of 323 patients under stable propofol or sevoflurane anaesthesia to study four EEG signatures (95% of EEG power <8-13 Hz) for age prediction: total power, alpha-band power (8-13 Hz), power spectrum, and spatial patterns in frequency bands. We constructed age-prediction models from EEGs of a healthy reference group (ASA 1 or 2) during propofol anaesthesia. Although all signatures were informative, state-of-the-art age-prediction performance was unlocked by parsing spatial patterns across electrodes along the entire power spectrum (mean absolute error=8.2 yr; R2=0.65). Results: Clinical exploration in ASA 1 or 2 patients revealed that brain age was positively correlated with intraoperative burst suppression, a risk factor for general anaesthesia complications. Surprisingly, brain age was negatively correlated with burst suppression in patients with higher ASA scores, suggesting hidden confounders. Secondary analyses revealed that age-related EEG signatures were specific to propofol anaesthesia, reflected by limited model generalisation to anaesthesia maintained with sevoflurane. Conclusions: Although EEG from general anaesthesia may enable state-of-the-art age prediction, differences between anaesthetic drugs can impact the effectiveness and validity of brain-age models. To unleash the dormant potential of EEG monitoring for clinical research, larger datasets from heterogeneous populations with precisely documented drug dosage will be essential.
RESUMEN
Biophysically detailed neural models are a powerful technique to study neural dynamics in health and disease with a growing number of established and openly available models. A major challenge in the use of such models is that parameter inference is an inherently difficult and unsolved problem. Identifying unique parameter distributions that can account for observed neural dynamics, and differences across experimental conditions, is essential to their meaningful use. Recently, simulation based inference (SBI) has been proposed as an approach to perform Bayesian inference to estimate parameters in detailed neural models. SBI overcomes the challenge of not having access to a likelihood function, which has severely limited inference methods in such models, by leveraging advances in deep learning to perform density estimation. While the substantial methodological advancements offered by SBI are promising, their use in large scale biophysically detailed models is challenging and methods for doing so have not been established, particularly when inferring parameters that can account for time series waveforms. We provide guidelines and considerations on how SBI can be applied to estimate time series waveforms in biophysically detailed neural models starting with a simplified example and extending to specific applications to common MEG/EEG waveforms using the the large scale neural modeling framework of the Human Neocortical Neurosolver. Specifically, we describe how to estimate and compare results from example oscillatory and event related potential simulations. We also describe how diagnostics can be used to assess the quality and uniqueness of the posterior estimates. The methods described provide a principled foundation to guide future applications of SBI in a wide variety of applications that use detailed models to study neural dynamics.
RESUMEN
Considerable progress has recently been made in natural language processing: deep learning algorithms are increasingly able to generate, summarize, translate and classify texts. Yet, these language models still fail to match the language abilities of humans. Predictive coding theory offers a tentative explanation to this discrepancy: while language models are optimized to predict nearby words, the human brain would continuously predict a hierarchy of representations that spans multiple timescales. To test this hypothesis, we analysed the functional magnetic resonance imaging brain signals of 304 participants listening to short stories. First, we confirmed that the activations of modern language models linearly map onto the brain responses to speech. Second, we showed that enhancing these algorithms with predictions that span multiple timescales improves this brain mapping. Finally, we showed that these predictions are organized hierarchically: frontoparietal cortices predict higher-level, longer-range and more contextual representations than temporal cortices. Overall, these results strengthen the role of hierarchical predictive coding in language processing and illustrate how the synergy between neuroscience and artificial intelligence can unravel the computational bases of human cognition.
Asunto(s)
Inteligencia Artificial , Habla , Humanos , Habla/fisiología , Percepción Auditiva/fisiología , Encéfalo/diagnóstico por imagen , Encéfalo/fisiología , Lóbulo Temporal/fisiologíaRESUMEN
Human neuromagnetic activity is characterised by a complex combination of transient bursts with varying spatial and temporal characteristics. The characteristics of these transient bursts change during task performance and normal ageing in ways that can inform about underlying cortical sources. Many methods have been proposed to detect transient bursts, with the most successful ones being those that employ multi-channel, data-driven approaches to minimize bias in the detection procedure. There has been little research, however, into the application of these data-driven methods to large datasets for group-level analyses. In the current work, we apply a data-driven convolutional dictionary learning (CDL) approach to detect neuromagnetic transient bursts in a large group of healthy participants from the Cam-CAN dataset. CDL was used to extract repeating spatiotemporal motifs in 538 participants between the ages of 18-88 during a sensorimotor task. Motifs were then clustered across participants based on similarity, and relevant task-related clusters were analysed for age-related trends in their spatiotemporal characteristics. Seven task-related motifs resembling known transient burst types were identified through this analysis, including beta, mu, and alpha type bursts. All burst types showed positive trends in their activation levels with age that could be explained by increasing burst rate with age. This work validated the data-driven CDL approach for transient burst detection on a large dataset and identified robust information about the complex characteristics of human brain signals and how they change with age.
Asunto(s)
Encéfalo , Aprendizaje , Humanos , Adolescente , Adulto Joven , Adulto , Persona de Mediana Edad , Anciano , Anciano de 80 o más Años , Encéfalo/fisiología , EnvejecimientoRESUMEN
Objective.The use of deep learning for electroencephalography (EEG) classification tasks has been rapidly growing in the last years, yet its application has been limited by the relatively small size of EEG datasets. Data augmentation, which consists in artificially increasing the size of the dataset during training, can be employed to alleviate this problem. While a few augmentation transformations for EEG data have been proposed in the literature, their positive impact on performance is often evaluated on a single dataset and compared to one or two competing augmentation methods. This work proposes to better validate the existing data augmentation approaches through a unified and exhaustive analysis.Approach.We compare quantitatively 13 different augmentations with two different predictive tasks, datasets and models, using three different types of experiments.Main results.We demonstrate that employing the adequate data augmentations can bring up to 45% accuracy improvements in low data regimes compared to the same model trained without any augmentation. Our experiments also show that there is no single best augmentation strategy, as the good augmentations differ on each task.Significance.Our results highlight the best data augmentations to consider for sleep stage classification and motor imagery brain-computer interfaces. More broadly, it demonstrates that EEG classification tasks benefit from adequate data augmentation.
Asunto(s)
Interfaces Cerebro-Computador , Electroencefalografía , Electroencefalografía/métodos , Imágenes en Psicoterapia , Fases del Sueño , SueñoRESUMEN
Deep language algorithms, like GPT-2, have demonstrated remarkable abilities to process text, and now constitute the backbone of automatic translation, summarization and dialogue. However, whether these models encode information that relates to human comprehension still remains controversial. Here, we show that the representations of GPT-2 not only map onto the brain responses to spoken stories, but they also predict the extent to which subjects understand the corresponding narratives. To this end, we analyze 101 subjects recorded with functional Magnetic Resonance Imaging while listening to 70 min of short stories. We then fit a linear mapping model to predict brain activity from GPT-2's activations. Finally, we show that this mapping reliably correlates ([Formula: see text]) with subjects' comprehension scores as assessed for each story. This effect peaks in the angular, medial temporal and supra-marginal gyri, and is best accounted for by the long-distance dependencies generated in the deep layers of GPT-2. Overall, this study shows how deep language models help clarify the brain computations underlying language comprehension.
Asunto(s)
Lenguaje , Semántica , Alanina Transaminasa , Algoritmos , Encéfalo/diagnóstico por imagen , Comprensión , HumanosRESUMEN
Previous literature has focused on predicting a diagnostic label from structural brain imaging. Since subtle changes in the brain precede a cognitive decline in healthy and pathological aging, our study predicts future decline as a continuous trajectory instead. Here, we tested whether baseline multimodal neuroimaging data improve the prediction of future cognitive decline in healthy and pathological aging. Nonbrain data (demographics, clinical, and neuropsychological scores), structural MRI, and functional connectivity data from OASIS-3 (N = 662; age = 46-96 years) were entered into cross-validated multitarget random forest models to predict future cognitive decline (measured by CDR and MMSE), on average 5.8 years into the future. The analysis was preregistered, and all analysis code is publicly available. Combining non-brain with structural data improved the continuous prediction of future cognitive decline (best test-set performance: R2 = 0.42). Cognitive performance, daily functioning, and subcortical volume drove the performance of our model. Including functional connectivity did not improve predictive accuracy. In the future, the prognosis of age-related cognitive decline may enable earlier and more effective individualized cognitive, pharmacological, and behavioral interventions.
Asunto(s)
Envejecimiento/patología , Envejecimiento/fisiología , Encéfalo/patología , Disfunción Cognitiva/diagnóstico por imagen , Actividades Cotidianas , Anciano , Anciano de 80 o más Años , Encéfalo/diagnóstico por imagen , Disfunción Cognitiva/patología , Humanos , Imagen por Resonancia Magnética/métodos , Persona de Mediana Edad , NeuroimagenRESUMEN
Population-level modeling can define quantitative measures of individual aging by applying machine learning to large volumes of brain images. These measures of brain age, obtained from the general population, helped characterize disease severity in neurological populations, improving estimates of diagnosis or prognosis. Magnetoencephalography (MEG) and Electroencephalography (EEG) have the potential to further generalize this approach towards prevention and public health by enabling assessments of brain health at large scales in socioeconomically diverse environments. However, more research is needed to define methods that can handle the complexity and diversity of M/EEG signals across diverse real-world contexts. To catalyse this effort, here we propose reusable benchmarks of competing machine learning approaches for brain age modeling. We benchmarked popular classical machine learning pipelines and deep learning architectures previously used for pathology decoding or brain age estimation in 4 international M/EEG cohorts from diverse countries and cultural contexts, including recordings from more than 2500 participants. Our benchmarks were built on top of the M/EEG adaptations of the BIDS standard, providing tools that can be applied with minimal modification on any M/EEG dataset provided in the BIDS format. Our results suggest that, regardless of whether classical machine learning or deep learning was used, the highest performance was reached by pipelines and architectures involving spatially aware representations of the M/EEG signals, leading to R2 scores between 0.60-0.74. Hand-crafted features paired with random forest regression provided robust benchmarks even in situations in which other approaches failed. Taken together, this set of benchmarks, accompanied by open-source software and high-level Python scripts, can serve as a starting point and quantitative reference for future efforts at developing M/EEG-based measures of brain aging. The generality of the approach renders this benchmark reusable for other related objectives such as modeling specific cognitive variables or clinical endpoints.
Asunto(s)
Benchmarking , Interfaces Cerebro-Computador , Algoritmos , Encéfalo , Mapeo Encefálico/métodos , Electroencefalografía/métodos , HumanosRESUMEN
Accurate lesion segmentation is critical in stroke rehabilitation research for the quantification of lesion burden and accurate image processing. Current automated lesion segmentation methods for T1-weighted (T1w) MRIs, commonly used in stroke research, lack accuracy and reliability. Manual segmentation remains the gold standard, but it is time-consuming, subjective, and requires neuroanatomical expertise. We previously released an open-source dataset of stroke T1w MRIs and manually-segmented lesion masks (ATLAS v1.2, N = 304) to encourage the development of better algorithms. However, many methods developed with ATLAS v1.2 report low accuracy, are not publicly accessible or are improperly validated, limiting their utility to the field. Here we present ATLAS v2.0 (N = 1271), a larger dataset of T1w MRIs and manually segmented lesion masks that includes training (n = 655), test (hidden masks, n = 300), and generalizability (hidden MRIs and masks, n = 316) datasets. Algorithm development using this larger sample should lead to more robust solutions; the hidden datasets allow for unbiased performance evaluation via segmentation challenges. We anticipate that ATLAS v2.0 will lead to improved algorithms, facilitating large-scale stroke research.
Asunto(s)
Encéfalo , Accidente Cerebrovascular , Algoritmos , Encéfalo/diagnóstico por imagen , Encéfalo/patología , Humanos , Procesamiento de Imagen Asistido por Computador , Imagen por Resonancia Magnética , Neuroimagen , Accidente Cerebrovascular/diagnóstico por imagen , Accidente Cerebrovascular/patologíaRESUMEN
Building machine learning models using EEG recorded outside of the laboratory setting requires methods robust to noisy data and randomly missing channels. This need is particularly great when working with sparse EEG montages (1-6 channels), often encountered in consumer-grade or mobile EEG devices. Neither classical machine learning models nor deep neural networks trained end-to-end on EEG are typically designed or tested for robustness to corruption, and especially to randomly missing channels. While some studies have proposed strategies for using data with missing channels, these approaches are not practical when sparse montages are used and computing power is limited (e.g., wearables, cell phones). To tackle this problem, we propose dynamic spatial filtering (DSF), a multi-head attention module that can be plugged in before the first layer of a neural network to handle missing EEG channels by learning to focus on good channels and to ignore bad ones. We tested DSF on public EEG data encompassing â¼4000 recordings with simulated channel corruption and on a private dataset of â¼100 at-home recordings of mobile EEG with natural corruption. Our proposed approach achieves the same performance as baseline models when no noise is applied, but outperforms baselines by as much as 29.4% accuracy when significant channel corruption is present. Moreover, DSF outputs are interpretable, making it possible to monitor the effective channel importance in real-time. This approach has the potential to enable the analysis of EEG in challenging settings where channel corruption hampers the reading of brain signals.
Asunto(s)
Interfaces Cerebro-Computador , Electroencefalografía , Algoritmos , Encéfalo , Electroencefalografía/métodos , Humanos , Aprendizaje Automático , Redes Neurales de la ComputaciónRESUMEN
Beamforming is a popular method for functional source reconstruction using magnetoencephalography (MEG) and electroencephalography (EEG) data. Beamformers, which were first proposed for MEG more than two decades ago, have since been applied in hundreds of studies, demonstrating that they are a versatile and robust tool for neuroscience. However, certain characteristics of beamformers remain somewhat elusive and there currently does not exist a unified documentation of the mathematical underpinnings and computational subtleties of beamformers as implemented in the most widely used academic open source software packages for MEG analysis (Brainstorm, FieldTrip, MNE, and SPM). Here, we provide such documentation that aims at providing the mathematical background of beamforming and unifying the terminology. Beamformer implementations are compared across toolboxes and pitfalls of beamforming analyses are discussed. Specifically, we provide details on handling rank deficient covariance matrices, prewhitening, the rank reduction of forward fields, and on the combination of heterogeneous sensor types, such as magnetometers and gradiometers. The overall aim of this paper is to contribute to contemporary efforts towards higher levels of computational transparency in functional neuroimaging.
Asunto(s)
Mapeo Encefálico/métodos , Corteza Cerebral/fisiología , Electroencefalografía/métodos , Magnetoencefalografía/métodos , Adulto , Humanos , Modelos TeóricosRESUMEN
Convolutional dictionary learning (CDL) estimates shift invariant basis adapted to represent signals or images. CDL has proven useful for image denoising or inpainting, as well as for pattern discovery on multivariate signals. Contrarily to standard patch-based dictionary learning, patterns estimated by CDL can be positioned anywhere in signals or images. Optimization techniques consequently face the difficulty of working with extremely large inputs with millions of pixels or time samples. To address this optimization problem, we propose a distributed and asynchronous algorithm, employing locally greedy coordinate descent and a soft-locking mechanism that does not require a central server. Computation can be distributed on a number of workers which scales linearly with the size of the data. The parallel computation accelerates the parameter estimation and the distributed setting allows our algorithm to be used with data that do not fit into a single computer's RAM. Experiments confirm the theoretical scaling properties of the algorithm. This allows to demonstrate an improved pattern recovery as images grow in size, and to learn patterns on images from the Hubble Space Telescope containing tens of millions of pixels.
RESUMEN
(1) Background: Based on its antiviral activity, anti-inflammatory properties, and functional inhibition effects on the acid sphingomyelinase/ceramide system (FIASMA), we sought to examine the potential usefulness of the H1 antihistamine hydroxyzine in patients hospitalized for COVID-19. (2) Methods: In a multicenter observational study, we included 15,103 adults hospitalized for COVID-19, of which 164 (1.1%) received hydroxyzine within the first 48 h of hospitalization, administered orally at a median daily dose of 25.0 mg (SD = 29.5). We compared mortality rates between patients who received hydroxyzine at hospital admission and those who did not, using a multivariable logistic regression model adjusting for patients' characteristics, medical conditions, and use of other medications. (3) Results: This analysis showed a significant association between hydroxyzine use and reduced mortality (AOR, 0.51; 95%CI, 0.29-0.88, p = 0.016). This association was similar in multiple sensitivity analyses. (4) Conclusions: In this retrospective observational multicenter study, the use of the FIASMA hydroxyzine was associated with reduced mortality in patients hospitalized for COVID-19. Double-blind placebo-controlled randomized clinical trials of hydroxyzine for COVID-19 are needed to confirm these results, as are studies to examine the potential usefulness of this medication for outpatients and as post-exposure prophylaxis for individuals at high risk for severe COVID-19.
RESUMEN
BACKGROUND: Independent Component Analysis (ICA) is a widespread tool for exploration and denoising of electroencephalography (EEG) or magnetoencephalography (MEG) signals. In its most common formulation, ICA assumes that the signal matrix is a noiseless linear mixture of independent sources that are assumed non-Gaussian. A limitation is that it enforces to estimate as many sources as sensors or to rely on a detrimental PCA step. METHODS: We present the Spectral Matching ICA (SMICA) model. Signals are modelled as a linear mixing of independent sources corrupted by additive noise, where sources and the noise are stationary Gaussian time series. Thanks to the Gaussian assumption, the negative log-likelihood has a simple expression as a sum of 'divergences' between the empirical spectral covariance matrices of the signals and those predicted by the model. The model parameters can then be estimated by the expectation-maximization (EM) algorithm. RESULTS: On phantom MEG datasets with low amplitude dipole sources (20â¯nAm), SMICA makes a median dipole localization error of 1.5â¯mm while competing methods make an error ≥7â¯mm. Experiments on EEG datasets show that SMICA identifies a source subspace which contains sources that have less pairwise mutual information, and are better explained by the projection of a single dipole on the scalp. With 10 sources, the number of strongly dipolar sources (dipolarity >90%) is more than 80% for SMICA while competing methods do not exceed 65%. COMPARISON WITH EXISTING METHODS: With the noisy model of SMICA, the number of sources to be recovered is controlled by choosing the size of the mixing matrix to be fitted rather than by a preprocessing step of dimension reduction which is required in traditional noise-free ICA methods. CONCLUSIONS: SMICA is a promising alternative to other noiseless ICA models based on non-Gaussian assumptions.
Asunto(s)
Electroencefalografía , Procesamiento de Señales Asistido por Computador , Algoritmos , Simulación por Computador , MagnetoencefalografíaRESUMEN
INTRODUCTION: Chlorpromazine has been suggested as being potentially useful in patients with coronavirus disease 2019 (COVID-19) on the grounds of its potential antiviral and anti-inflammatory effects. OBJECTIVE: The aim of this study was to examine the association between chlorpromazine use and mortality among adult patients hospitalized for COVID-19. METHODS: We conducted an observational, multicenter, retrospective study at Assistance Publique-Hôpitaux de Paris (AP-HP) Greater Paris University hospitals. Study baseline was defined as the date of first prescription of chlorpromazine during hospitalization for COVID-19. The primary endpoint was death. Among patients who had not been hospitalized in intensive care units (ICUs), we compared this endpoint between those who received chlorpromazine and those who did not, in time-to-event analyses adjusted for patient characteristics, clinical markers of disease severity, and other psychotropic medications. The primary analysis used a Cox regression model with inverse probability weighting. Multiple sensitivity analyses were performed. RESULTS: Of the 14,340 adult inpatients hospitalized outside ICUs for COVID-19, 55 patients (0.4%) received chlorpromazine. Over a mean follow-up of 14.3 days (standard deviation [SD] 18.2), death occurred in 13 patients (23.6%) who received chlorpromazine and 1289 patients (9.0%) who did not. In the primary analysis, there was no significant association between chlorpromazine use and mortality (hazard ratio [HR] 2.01, 95% confidence interval [CI] 0.75-5.40; p = 0.163). Sensitivity analyses included a Cox regression in a 1:5 ratio matched analytic sample that showed a similar result (HR 1.67, 95% CI 0.91-3.06; p = 0.100) and a multivariable Cox regression that indicated a significant positive association (HR 3.10, 95% CI 1.31-7.34; p = 0.010). CONCLUSION: Our results suggest that chlorpromazine prescribed at a mean daily dose of 70.8 mg (SD 65.3) was not associated with reduced mortality.
Asunto(s)
Tratamiento Farmacológico de COVID-19 , Clorpromazina/uso terapéutico , SARS-CoV-2 , Adolescente , Adulto , Anciano , Anciano de 80 o más Años , Femenino , Hospitalización , Humanos , Masculino , Persona de Mediana Edad , Modelos de Riesgos Proporcionales , Estudios Retrospectivos , Índice de Severidad de la Enfermedad , Adulto JovenRESUMEN
AIMS: To examine the association between dexamethasone use and mortality among patients hospitalized for COVID-19. METHODS: We examined the association between dexamethasone use and mortality at AP-HP Greater Paris University hospitals. Study baseline was defined as the date of hospital admission. The primary endpoint was time to death. We compared this endpoint between patients who received dexamethasone and those who did not in time-to-event analyses adjusted for patient characteristics (such as age, sex and comorbidity) and clinical and biological markers of clinical severity of COVID-19, and stratified by the need for respiratory support, i.e. mechanical ventilation or oxygen. The primary analysis was a multivariable Cox regression model. RESULTS: Of 12 217 adult patients hospitalized with a positive COVID-19 reverse transcriptase-polymerase chain reaction test, 171 (1.4%) received dexamethasone orally or by intravenous perfusion during the visit. Among patients who required respiratory support, the end-point occurred in 10/63 (15.9%) patients who received dexamethasone and 298/1129 (26.4%) patients who did not. In this group, there was a significant association between dexamethasone use and reduced mortality in the primary analysis (hazard ratio, 0.46; 95% confidence interval 0.22-0.96, P = .039). Among patients who did not require respiratory support, there was no significant association between dexamethasone use and the endpoint. CONCLUSIONS: In this multicentre observational study, dexamethasone use administered either orally or by intravenous injection at a cumulative dose between 60 mg and 150 mg was associated with reduced mortality among patients with COVID-19 requiring respiratory support.