Announcing NeuroGut Tracker v1!

We have been developing a deep-learning-based self-adaptable model for processing patients/subjects' data, and we'll be testing it on our new project: a gut-brain computer interface (GBCI)

A gut–brain computer interface (GBCI) is a system that senses, interprets, and sometimes responds to physiological signals traveling along the gut–brain axis, turning them into digital data that can be analyzed or used to guide interventions. In practice, a GBCI might combine sensors that record signals like gut electrical activity, pressure, motility, microbiome-related metabolites, or autonomic nerve activity with algorithms that decode how these patterns relate to brain states such as mood, cognition, or pain. The “computer interface” part refers to using computational models—often machine learning—to map these gut signals onto meaningful outputs (for example, early warnings of neurological flare-ups or side-effects), and potentially feed information back in the form of stimulation (e.g., vagus nerve or gut stimulation) or personalized treatment guidance. In short, a GBCI is like a two-way translator between the digestive system and the brain, designed to monitor and eventually modulate their communication for diagnosis, prediction, or therapy.

In our case, the gut–brain computer interface will record gastric slow-wave activity (electrogastrography, EGG) andautonomic nervous system activity related to the vagus nerve from the same wearable or patch-based setup, letting us capture both “sides” of gut–brain communication in one synchronized stream. The EGG channels will track patterns of gastric rhythm, dysrhythmias, and motility, while additional sensors (for example, heart rate variability–based indices and other autonomic markers) will approximate vagal tone and broader autonomic balance. Instead of a fixed, one-size-fits-all algorithm, we’ll train a self-adaptable deep learning model that starts from a general baseline but then continuously fine-tunes to each individual user, learning their personal coupling patterns between gut signals and autonomic/vagal activity. Over time, this allows the system to build a patient-specific model of gut–brain dynamics, improving prediction of flares, side-effects, or unsafe states and making the GBCI more robust across different ages, environments, and clinical backgrounds.