Current brain surface-based prediction models often overlook the variability of regional attributes at the cortical feature level. While graph neural networks (GNNs) excel at capturing regional differences, they encounter challenges when dealing with complex, high-density graph structures. In this work, we consider the cortical surface mesh as a sparse graph and propose an interpretable prediction model-Surface Graph Neural Network (SurfGNN). SurfGNN employs topology-sampling learning (TSL) and region-specific learning (RSL) structures to manage individual cortical features at both lower and higher scales of the surface mesh, effectively tackling the challenges posed by the overly abundant mesh nodes and addressing the issue of heterogeneity in cortical regions. Building on this, a novel score-weighted fusion (SWF) method is implemented to merge nodal representations associated with each cortical feature for prediction. We apply our model to a neonatal brain age prediction task using a dataset of harmonized MR images from 481 subjects (503 scans). SurfGNN outperforms all existing state-of-the-art methods, demonstrating an improvement of at least 9.0% and achieving a mean absolute error (MAE) of 0.827+0.056 in postmenstrual weeks. Furthermore, it generates feature-level activation maps, indicating its capability to identify robust regional variations in different morphometric contributions for prediction.

Emotional contagion refers to the sharing of emotional states between individuals, and it has been observed in both animal and human models that the infectivity of negative emotions is much greater than that of positive emotions [1]. Negative emotional contagion has a powerful effect on our relationships - family, friends, teams, etc. - and can lead, for example, to depressive behavior in healthy people who live with depressed individuals. It is urgent to understand the mechanism of emotional contagion, especially negative emotional contagion. Emotional contagion has long been regarded as reflecting a mimicry-based process, for which mimicry of emotional expressions and its consequent feedback function are assumed and can be evoked by higher-order social processes or by a simple emotion-to-action response as well as the primary mimicry-based process [2]. At present, the emotional contagion models mostly adopt behavioral analysis and questionnaires, which are often affected by subjects' subjective factors. They have mainly focused on behavioral experiment such as analysing people's posts containing emotional information to extract affective evidence [3], using the Positive And Negative Affective Schedule (PANAS) scale to measure positive and negative emotions as a quantitive research [4] and the mathematical simulation model of emotional contagion in crowd evacuation [5]. Although behavioral analysis and questionaires can provide valuable insights into emotional contagion, they have limitations in terms of capturing the neural mechanisms, timing, and subtleties of this phenomenon.