Search for: All records

ABSTRACT ObjectiveNeighborhood perceptions are associated with physical and mental health outcomes; however, the biological associates of this relationship remain to be fully understood. Here, we evaluate the relationship between neighborhood perceptions and amygdala activity and connectivity with salience network (i.e., insula, anterior cingulate, thalamus) nodes. MethodsForty-eight older adults (mean age = 68 [7] years, 52% female, 47% non-Hispanic Black, 2% Hispanic) without dementia or depression completed the Perceptions of Neighborhood Environment Scale. Lower scores indicated less favorable perceptions of aesthetic quality, walking environment, availability of healthy food, safety, violence (i.e., more perceived violence), social cohesion, and participation in activities with neighbors. Participants separately underwent resting-state functional magnetic resonance imaging. ResultsLess favorable perceived safety (β= −0.33,p_FDR= .04) and participation in activities with neighbors (β= −0.35,p_FDR= .02) were associated with higher left amygdala activity, independent of covariates including psychosocial factors. Less favorable safety perceptions were also associated with enhanced left amygdala functional connectivity with the bilateral insular cortices and the left anterior insula (β= −0.34,p_FDR= .04). Less favorable perceived social cohesion was associated with enhanced left amygdala functional connectivity with the right thalamus (β =−0.42,p_FDR= .04), and less favorable perceptions about healthy food availability were associated with enhanced left amygdala functional connectivity with the bilateral anterior insula (right:β= −0.39,p_FDR= .04; left:β= −0.42,p_FDR= .02) and anterior cingulate gyrus (β= −0.37,p_FDR= .04). ConclusionsTaken together, our findings document relationships between select neighborhood perceptions and amygdala activity as well as connectivity with salience network nodes; if confirmed, targeted community-level interventions and existing community strengths may promote brain-behavior relationships. 

Graph neural networks (GNNs) are proficient machine learning models in handling irregularly structured data. Nevertheless, their generic formulation falls short when applied to the analysis of brain connectomes in Alzheimer’s Disease (AD), necessitating the incorporation of domain-specific knowledge to achieve optimal model performance. The integration of AD-related expertise into GNNs presents a significant challenge. Current methodologies reliant on manual design often demand substantial expertise from external domain specialists to guide the development of novel models, thereby consuming considerable time and resources. To mitigate the need for manual curation, this paper introduces a novel self-guided knowledge-infused multimodal GNN to autonomously integrate domain knowledge into the model development process. We propose to conceptualize existing domain knowledge as natural language, and devise a specialized multimodal GNN framework tailored to leverage this uncurated knowledge to direct the learning of the GNN submodule, thereby enhancing its efficacy and improving prediction interpretability. To assess the effectiveness of our framework, we compile a comprehensive literature dataset comprising recent peer-reviewed publications on AD. By integrating this literature dataset with several real-world AD datasets, our experimental results illustrate the effectiveness of the proposed method in extracting curated knowledge and offering explanations on graphs for domain-specific applications. Furthermore, our approach successfully utilizes the extracted information to enhance the performance of the GNN. 

The MRI-derived brain network serves as a pivotal instrument in elucidating both the structural and functional aspects of the brain, encompassing the ramifications of diseases and developmental processes. However, prevailing methodologies, often focusing on synchronous BOLD signals from functional MRI (fMRI), may not capture directional influences among brain regions and rarely tackle temporal functional dynamics. In this study, we first construct the brain-effective network via the dynamic causal model. Subsequently, we introduce an interpretable graph learning framework termed Spatio-Temporal Embedding ODE (STE-ODE). This framework incorporates specifically designed directed node embedding layers, aiming at capturing the dynamic interplay between structural and effective networks via an ordinary differential equation (ODE) model, which characterizes spatial-temporal brain dynamics. Our framework is validated on several clinical phenotype prediction tasks using two independent publicly available datasets (HCP and OASIS). The experimental results clearly demonstrate the advantages of our model compared to several state-of-the-art methods. 

The long-standing one-to-many problem of gold standard responses in open-domain dialogue systems presents challenges for automatic evaluation metrics. Though prior works have demonstrated some success by applying powerful Large Language Models (LLMs), existing approaches still struggle with the one-to-many problem, and exhibit subpar performance in domain-specific scenarios. We assume the commonsense reasoning biases within LLMs may hinder their performance in domain-specific evaluations. To address both issues, we propose a novel framework SLIDE (Small and Large Integrated for Dialogue Evaluation), that leverages both a small, specialized model (SLM), and LLMs for the evaluation of open-domain dialogues. Our approach introduces several techniques: (1) Contrastive learning to differentiate between robust and non-robust response embeddings; (2) A novel metric for semantic sensitivity that combines embedding cosine distances with similarity learned through neural networks, and (3) A strategy for incorporating the evaluation results from both the SLM and LLMs. Our empirical results demonstrate that our approach achieves state-of-the-art performance in both the classification and evaluation tasks, and additionally, the SLIDE evaluator exhibits a better correlation with human judgments.