Key result
Embedding a circular manifold into recurrent neural networks accurately models nonlinear blood pressure dynamics.
Why the study?
During blood pressure transitions, neurons in the spinal intermediolateral nucleus show heterogeneous firing responses, a diversity that is intrinsic to homeostatic control but hampers accurate decoding of internal state dynamics.
Does a manifold-based recurrent neural network model mapping spinal intermediolateral nucleus population activity accurately reproduce nonlinear blood pressure dynamics and neural variability?
Does a manifold-based recurrent neural network model mapping spinal intermediolateral nucleus population activity accurately reproduce nonlinear blood pressure dynamics and neural variability?
Embedding a low-dimensional circular manifold derived from spinal intermediolateral nucleus population dynamics into a recurrent neural network reproduces both trial-by-trial neural variability and nonlinear blood pressure transitions.
Manifold modeling may aid decoding of blood pressure dynamics from heterogeneous IML neurons; leaves open clinical translation.
Physiological signals underlying homeostasis, such as blood pressure, are dynamic and nonlinear, shaped by interactions among diverse neurons. During blood pressure transitions, neurons in the spinal intermediolateral nucleus (IML), a sympathetic hub, show heterogeneous monotonic increases or decreases in firing. Such diversity is intrinsic to homeostatic control but hampers accurate decoding of internal state dynamics. Here, we introduce a manifold-based model that addresses this challenge by directly mapping IML population activity onto physiological state transitions. Individual neurons responded independently with increases or decreases in firing, but these patterns alone did not align with the nonlinear trajectory of blood pressure. Focusing instead on recurrent population dynamics, we derived a low-dimensional circular manifold that captured the cyclical temporal evolution of state transitions. Embedding this manifold as a dynamic reservoir in a recurrent neural network reproduced both trial-by-trial variability in neural population activity and nonlinear blood pressure dynamics, establishing a circuit-level framework for autonomic state decoding.
No takes yet. Share an insight, caveat, or question.
Choo et al. (2026) studied Autonomic state transitions and blood pressure dynamics. Manifold-based recurrent neural network model vs. Individual neuron firing patterns was evaluated on Reproduction of trial-by-trial variability in spinal intermediolateral nucleus population activity and nonlinear blood pressure dynamics. Embedding a low-dimensional circular manifold into a recurrent neural network reproduced both spinal neural population variability and nonlinear blood pressure dynamics.
Synapse has enriched 5 closely related papers on similar clinical questions. Consider them for comparative context: