Slow breathing modulates brain function and risk behavior

Some interesting observations reported in Neuron by Huang et al.:

Highlights

• Prolonged exhalation increases risky decisions by increasing reward sensitivity

 

• Prolonged exhalation increases parasympathetic but not sympathetic activity

 

•Greater parasympathetic activity predicts reward sensitivity in the vmPFC and precuneus

Summary

Successful decision-making requires that external information be interpreted in the context of the body’s state. Within the framework of body-brain interaction, deliberately modifying one’s autonomic state can shape how we evaluate the world, ultimately influencing choices. Yet, it remains unclear whether and how intentional autonomic regulation affects human decision-making. In this study, we tested instructed use of prolonged exhalation, a slow-breathing technique designed to boost parasympathetic activity during risky decision-making. Participants followed distinct breathing protocols while making risky choices, with neural and physiological activity measured using functional magnetic resonance imaging (fMRI) and multichannel monitoring. Prolonged exhalation increased risky choices by enhancing reward sensitivity and elevating cardiac parasympathetic activity. Importantly, individuals with greater parasympathetic upregulation also showed stronger reward-related responses in the ventromedial prefrontal cortex and precuneus. Our work reveals the transformative role of breathing-based interventions, demonstrating that autonomic regulation via breathing can shape value-based decision-making through neuro-cardiac pathways.

 

Analog cognition and consciousness

Miller et al.   suggest that brain synapses store representations while large-scale rhythmic electric fields dynamically select, route and combine them. Traveling alpha and beta waves could act as movable “stencils” controlling faster gamma activity, permitting parallel analog computation; unified consciousness would arise when such wave organization becomes sufficiently cortex-wide and integrated. They propose an "analog" computational layer on top of digital-style spikes. Waves would be organizing top-down control, flexibly route signals between neural populations, and let individual neurons take on different functional roles depending on context — the coordination problem that discrete spiking alone struggles to explain. I pass on their abstract and concluding comments (motivated readers can obtain a PDF of the article from me.)

Abstract:

Cognition and consciousness may arise from bidirectional interactions between neuronal spiking and rhythmic electric field activity (brain waves). Goal-directed behavior relies on top-down control to coordinate large neural populations into low-dimensional, task-oriented dynamics. Brain waves are well suited for this role, exerting mesoscale influence over neural excitability. They can also support analog computation, shaping activity patterns according to underlying computational principles. Brain waves can flexibly route and organize neural signals, enabling multifunctional neurons to assume context-dependent roles, a hallmark of cognition. In this view, goal-directed thought, action, and unified consciousness emerge from cortex-wide wave dynamics that both reflect and transform spiking into coherent brain states.

Concluding comments: 

Our theory shares with others the general idea that cognition and consciousness involve mesoscale coordination and thus top-down control across the brain. But instead of describing function mainly in terms of information exchange between discrete neurons, circuits, and regions, we emphasize brain-wide wave dynamics as an organizing principle.

In this view, rhythmic electric fields help unify and structure cortical activity, allowing analog computation to take place across space and time. These wave interactions not only bind distributed neural populations into coherent states but also carry out computations that support flexible thought and control. Consciousness, then, emerges when these dynamic wave patterns bring the cortex into an organized, globally integrated state, one that naturally links and influences widespread activity.

This theory is not only conceptually plausible but biologically feasible. Cortical circuits naturally generate oscillatory dynamics and propagate waves through recurrent connectivity and horizontal cortical connections across multiple scales. The dynamics we emphasize thus require no special machinery. These waves are energetically efficient, leveraging continuous field interactions rather than metabolically costly, all-or-none spiking at every step. In this sense, the brain exploits its own physics: Electric field dynamics offer a low-overhead substrate for organizing and coordinating information across cortical networks. Given strong evolutionary pressure to maximize computation per unit energy, it would be surprising if evolution did not exploit such a built-in analog computing substrate.