Brain Informatics最新文献

In this study, we propose a hybrid decoding scheme for classifying consumer intent in a binary decision-making scenario ("Buy" vs. "NoBuy"), using simultaneous electroencephalography (EEG) and eye-tracking data. The proposed framework integrates graph signal processing-based features derived from EEG functional connectivity with descriptive statistics from eye movement patterns. Given the imbalanced nature of the targeted classification task, the performance of the proposed hybrid scheme is being assessed at the individual subject level via the employment of Cohen's kappa and F1-score metrics, both of which are well-suited for handling class imbalance by accounting for agreement beyond chance and balancing precision and recall, respectively. The reported results showcase the superiority of the proposed hybrid decoding scheme, as the averaged scores for both Cohen's kappa and F1-score are exceeding (with statistical significance at 0.05) the presented competing approaches by 0.08-0.30 and 0.06-0.23 respectively. Additionally, our connectivity analysis confirmed two key findings: (i) strong couplings were consistently observed between electrodes spanning distinct brain regions, such as the prefrontal and occipital cortices, in addition to the commonly reported frontal dipoles; and (ii) the most salient functional connections varied across individuals, with only a limited subset shared among subjects. These results highlight the potential of multimodal decoding approaches and subject-specific connectivity patterns in advancing the classification of consumer decision behavior.

Traumatic brain injury (TBI) is still considered a major cause of morbidity and mortality worldwide, and its prevalence is increasing daily. TBI patients are facing difficult diagnostic, management, and rehabilitative challenges. This review article represents the most relevant recent findings in all areas of TBI concerning pathophysiology, diagnostics, therapeutics, rehabilitation approaches and neuroplasticity. In recent years, the diagnosis of TBI has improved more often due to advancements in neuroimaging, biomarkers, and artificial intelligence. Pharmacological treatments, stem cell therapy, and neuroprotective strategies are also associated with a wide range of therapeutic innovations that could open new fields of acute management. Consequently, practice has also changed, and cross professional treatments have been adopted with the aid of the latest technology for acute TBI recovery. TBI management faces multiple challenges in special populations, such as pediatric patients, elderly people, and soldiers. Personalized medicine, big data analytics, and global collaboration are emphasized as future research directions. This detailed study should serve to remind researchers and clinicians alike of the ongoing need for innovation to deliver better care pathways appropriate for TBI patients.

This paper introduces the conceptual parallel between the ANN training process and the learning mechanisms of the human brain. Then, we briefly discuss a set of recently achieved experimental findings from a prior study that delves into various scenarios, aiding in comprehending the functionality of impaired or damaged neurons within a neural system. The key contribution of this paper is to present a novel variant of the Adam optimizer that incorporates a dynamic momentum adjustment factor, adaptive learning rate, and elastic weight consolidation technique. This enhanced version draws inspiration from biological processes to improve learning stability in artificial neural networks, with conceivable relevance to neural adaptation and rehabilitation research.

Brain computer interface (BCI) provides a promising and intelligent rehabilitation method for motor function, and it is crucial to acquire the patient's movement intentions accurately through decoding motor imagery EEG (MI-EEG) . Because of the inter-individual heterogeneity, the decoding model should demonstrate dynamic adaptation abilities.Domain adaptation (DA) is effective to enhance model generalization by reducing the inherent distribution difference among subjects. However, the existing DA methods usually mix the multiple source domains into a new domain, the resulting multi-source domain conflict may cause negative transfer. In this paper, we propose a multi-source dynamic conditional domain adaptation network (MSDCDA). First, a multi-channel attention block is employed in the feature extractor to focus on the channels relevant to the corresponding MI task. Subsequently, the shallow spatial-temporal features are extracted using a spatial-temporal convolution block. And a dynamic residual block is applied in the feature extractor to dynamically adapt specific features of each subject to alleviate conflicts among multiple source domains since each domain is viewed as a distribution of electroencephalogram (EEG) signals. Furthermore, we employ the Margin Disparity Discrepancy (MDD) as the metric to achieve conditional distribution domain adaptation between the source and target domains through adversarial learning with an auxiliary classifier. MSDCDA achieved accuracies of 78.55 $\%$ and 85.08 $\%$ on Datasets IIa and IIb of BCI Competition IV, respectively. Our experimental results demonstrate that MSDCDA can effectively address multi-source domain conflicts and significantly enhance the decoding performance of target subjects. This study positively facilitates the application of BCI based on motor function rehabilitation.

Emotion is an integral part of human cognitive processes and behaviors. Automatic detection and classification of human emotion has been a goal of applied research. This study presents an approach to detecting emotion from multivariate electroencephalogram (EEG) with signal processing methods applied in the temporal, spectral, and spatial domains. In this work, the noise-assisted multivariate empirical mode decomposition (NA-MEMD) is applied to EEG to extract a set of narrow-band intrinsic mode functions (IMF), upon which spectral analysis and spatial connectivity analysis are performed. Applying Hilbert spectral analysis to those IMFs results in the marginal Hilbert spectrum (MHS). MHS is computed for each EEG channel to obtain the spectral energy of each segment. The spectral energy across multiple EEG channels within the same segment is aggregated while the consecutive frames are stacked to give spectral-temporal feature representation. Again, connectivity analysis is performed at each instant with a non-linear measure named phase locking value (PLV) to construct the connectivity map containing spatial-temporal features. A 2D CNN-BiLSTM is adopted to perform emotion detection with the MHS and the PLV features. On classifying high versus low states in valence, arousal, dominance, and liking, PLV showed better performance than MHS with 97.61%, 96.09%, 96.75%, and 97.23% accuracy, respectively, for DEAP dataset. Meanwhile, the highest accuracy of 94.71% is attained on 4-class task. PLV of high oscillatory IMFs outperforms the reported systems with conventional EEG features.

We propose a method that uses a two-species ordinary differential equation (ODE) model for subject-specific misfolded tau protein spreading in Alzheimer's disease (AD) and calibrates it from magnetic resonance imaging (MRI) and positron emission tomography (PET) scans. The ODE model is a variant of the heterodimer Fisher-Kolmogorov (HFK) model. The unknown model parameters are the initial condition (IC) for tau and three scalar parameters representing the migration, proliferation, and clearance of tau proteins. Driven by imaging data, these parameters are estimated by formulating a constrained optimization problem with a sparsity regularization for the IC. This optimization problem is solved with a projection-based quasi-Newton algorithm. We evaluate the performance of our method on both synthetic and clinical data. Subjects are from the AD Neuroimaging Initiative (ADNI) datasets: 455 cognitively normal (CN), 212 mild cognitive impairment (MCI), and 45 AD subjects. We compare the performance of our approach to the commonly used Fisher-Kolmogorov (FK) model with a fixed IC at the entorhinal cortex (EC). Our method demonstrates an average improvement of 19.6% relative error compared to the FK model on the AD dataset. HFK also achieves an R-squared score of 0.591 for fitting AD data compared with 0.256 from FK model results with IC fixing at EC. The inverted IC from our scheme indicates that the EC is the most likely initial seeding region if subcortical regions are excluded from the analysis. However, other regions also have probability to be the IC seeding regions. Furthermore, for cases that have longitudinal data, we estimate a subject-specific AD onset time.

In cognitive neuroscience and brain-computer interface research, accurately predicting imagined stimuli is crucial. This study investigates the effectiveness of Domain Adaptation (DA) in enhancing imagery prediction using primarily visual data from fMRI scans of 18 subjects. Initially, we train a baseline model on visual stimuli to predict imagined stimuli, utilizing data from 14 brain regions. We then develop several models to improve imagery prediction, comparing different DA methods. Our results demonstrate that DA significantly enhances imagery prediction in binary classification on our dataset, as well as in multiclass classification on a publicly available dataset. We then conduct a DA-enhanced searchlight analysis, followed by permutation-based statistical tests to identify brain regions where imagery decoding is consistently above chance across subjects. Our DA-enhanced searchlight predicts imagery contents in a highly distributed set of brain regions, including the visual cortex and the frontoparietal cortex, thereby outperforming standard cross-domain classification methods. The complete code and data for this paper have been made openly available for the use of the scientific community.

Accurate detection of cortical infarct is critical for timely treatment and improved patient outcomes. Current brain imaging methods often require invasive procedures that primarily assess blood vessel and structural white matter damage. There is a need for non-invasive approaches, such as functional MRI (fMRI), that better reflect neuronal viability. This study utilized automated machine learning (auto-ML) techniques to identify novel infarct-specific fMRI biomarkers specifically related to chronic cortical infarcts. We analyzed resting-state fMRI data from the multi-center ADNI dataset, which included 20 chronic infarct patients and 30 cognitively normal (CN) controls. This study utilized automated machine learning (auto-ML) techniques to identify novel fMRI biomarkers specifically related to chronic cortical infarcts. Surface-based registration methods were applied to minimize partial-volume effects typically associated with lower resolution fMRI data. We evaluated the performance of 7 previously known fMRI biomarkers alongside 107 new auto-generated fMRI biomarkers across 33 different classification models. Our analysis identified 6 new fMRI biomarkers that substantially improved infarct detection performance compared to previously established metrics. The best-performing combination of biomarkers and classifiers achieved a cross-validation ROC score of 0.791, closely matching the accuracy of diffusion-weighted imaging methods used in acute stroke detection. Our proposed auto-ML fMRI infarct-detection technique demonstrated robustness across diverse imaging sites and scanner types, highlighting the potential of automated feature extraction to significantly enhance non-invasive infarct detection.

Reliable classification of cognitive states in longitudinal Alzheimer's Disease (AD) studies is critical for early diagnosis and intervention. However, inconsistencies in diagnostic labeling, arising from subjective assessments, evolving clinical criteria, and measurement variability, introduce noise that can impact machine learning (ML) model performance. This study explores the potential of explainable artificial intelligence to detect and characterize noisy labels in longitudinal datasets. A predictive model is trained using a Leave-One-Subject-Out validation strategy, ensuring robustness across subjects while enabling individual-level interpretability. By leveraging SHapley Additive exPlanations values, we analyze the temporal variations in feature importance across multiple patient visits, aiming to identify transitions that may reflect either genuine cognitive changes or inconsistencies in labeling. Using statistical thresholds derived from cognitively stable individuals, we propose an approach to flag potential misclassifications while preserving clinical labels. Rather than modifying diagnoses, this framework provides a structured way to highlight cases where diagnostic reassessment may be warranted. By integrating explainability into the assessment of cognitive state transitions, this approach enhances the reliability of longitudinal analyses and supports a more robust use of ML in AD research.

Purpose: Effective patient monitoring is crucial for timely healthcare interventions and improved outcomes, especially in managing conditions influenced by stress and depression, which can manifest through physiological changes. Traditional monitoring systems often struggle with the complexity and dynamic nature of such conditions, leading to delays in identifying critical scenarios. This study proposes a novel multi-agent deep reinforcement learning (DRL) framework to address these challenges by monitoring vital signs and providing real-time decision-making capabilities.

Methods: Our framework deploys multiple learning agents, each dedicated to monitoring specific physiological features such as heart rate, respiration, and temperature. These agents interact with a generic healthcare monitoring environment, learn patients' behavior patterns, and estimate the level of emergency to alert Medical Emergency Teams (METs) accordingly. The study evaluates the proposed system using two real-world datasets-PPG-DaLiA and WESAD-designed to capture physiological and stress-related data. The performance is compared with baseline models, including Q-Learning, PPO, Actor-Critic, Double DQN, and DDPG, as well as existing monitoring frameworks like WISEML and CA-MAQL. Hyperparameter optimization is also performed to fine-tune learning rates and discount factors.

Results: Experimental results demonstrate that the proposed multi-agent DRL framework outperforms baseline models in accurately monitoring patients' vital signs under stress and varying conditions. The optimized agents adapt effectively to dynamic environments, ensuring timely detection of critical health deviations. Comparative evaluations reveal superior performance in metrics related to decision-making accuracy and response efficiency, highlighting the robustness of the framework.

Conclusions: The proposed AI-driven monitoring system offers significant advancements over traditional methods by handling complex and uncertain environments, adapting to varying patient conditions influenced by stress and depression, and making autonomous, real-time decisions. While the framework demonstrates high accuracy and adaptability, challenges related to data scale and future vital sign prediction remain. Future research will focus on extending predictive capabilities to further enhance proactive healthcare interventions.