Hybrid Spiking Neural Networks for Anomaly Detection of Brain, Heart and Pancreas

Abstract

To understand the information processing mechanism of the brain, it is important to decode the bidirectional communication between the brain and organs. For this purpose, computational models were proposed to simulate brain–organ interfaces at different levels of abstraction. Conventional computational models can be modified to understand the bidirectional interactions for further clarification and treatment of morbidity. In this work, a unified model of excitable cells (brain, heart, and pancreatic cells) is proposed that can predict the electrical response with adrenergic features. This enables us to activate the sparsely coupled cardio-neural network to estimate the heart rate variability, one of the key features to identify a healthy heart. The recent advancements in nano- and bioelectronics will make it possible to build and deploy the brain–heart interface as a nanochip in the body to monitor and control the electrophysiological abnormality of the brain and heart by integrating nano-regulators with ion channels for stimulation.