Toward Personalized Neuroscience: Evaluating Individual-Level Information in Neural Mass Models

Abstract

Macroscale brain modeling using neural mass models (NMMs) offers a framework for simulating human whole-brain dynamics. These models are pivotal for investigating the brain as a complex dynamic system, exploring phenomena like bifurcations, oscillatory patterns, and responses to stimuli. While connectome-based NMMs allow for the creation of personalized NMMs, their utility in capturing individual-specific neural characteristics remains underexplored, with current studies constrained by small sample sizes and computational inefficiencies. To address these limitations, we employed an algorithmically differentiable version of the reduced Wong Wang (RWW) model, enabling efficient optimization for large datasets. Applying this to resting-state fMRI data from 1444 samples, we optimized models with varying parameter complexities (n = 4, 658, and 23,875), which were derived from creating biologically plausible model variants. The optimized models achieved 4%, 19%, and 56% variance explanation in empirical functional connectivity (FC), respectively. Subject identification accuracy, based on simulated FC patterns, improved from < 1% (n = 4) to almost 100% (n = 23,875). Despite this precision, individual-level correlations between model parameters and attributes like age, gender, or intelligence quotient were small (effect sizes: ${\eta }_{\text{partial}}^2\le 0.03$ , standardized $\beta \le 0.234$ ). Machine learning analyses confirmed that these parameters lack the granularity to encode personal traits effectively. These findings suggest that, while current implementations of the RWW NMM can robustly replicate resting-state dynamics, the resulting parameters may lack the granularity required to map onto individual-specific behavioral metrics. This highlights a critical alignment problem: neural patterns and behavioral constructs such as intelligence may not correspond in a one-to-one fashion but instead represent higher-level abstractions. Bridging this gap will require the development of new tools capable of uncovering the underlying mapping manifolds, likely situated at the level of functional dynamics rather than isolated parameters. Future efforts should build on individual-level mechanistic modeling by exploring more expressive model classes and integrating richer sources of data, such as multimodal imaging or task-based paradigms, to better capture individual variability in both neural dynamics and behavioral traits. Such approaches may ultimately help to bridge the gap between model-based neural similarity and clinically meaningful personalization.

FIGURE 1

Schematic illustration of the whole brain, connectome‐based neural mass modeling framework. Input data comprise brain parcellations derived from T1‐weighted MRI and SC derived from diffusion‐weighted MRI, defining the connections between the model's nodes. An NMM specifies the dynamics of population‐level neural activity at each node (brain region). This integrated model enables simulation of fMRI time series, computation of a synthetic FC matrix, and comparison with an individual's empirical FC profile. Subsequent parameter optimization using the ADAM algorithm enhances alignment between simulated and empirical fMRI patterns.

FIGURE 2

Optimization results: mean explained variance (%) of empirical rs‐fMRI data using simulated rs‐fMRI from different models (localized model [LM], globalized model [GM], connectivity model [CM]), empirical DTI, mean FC for n = 1444 samples, or empirical rs‐fMRI from a second time point (2TP) for n = 491 samples.