Fine-tuned Circuit Representation of Human Vessels through Reinforcement Learning: A Novel Digital Twin Approach for Hemodynamics

NANOCOM '23: Proceedings of the 10th ACM International Conference on Nanoscale Computing and Communication(2023)

Cited 0|Views7
No score
The modeling of human vessel hemodynamics targets various benefits in health care applications. Subject-specific models of vessels allow the accurate prediction of pressure and flow, thus, enabling the study of individuals' responses to medical treatment. Instead of developing a model for a standard person, this paper features a design for the human circulatory system (HCS) accounting for the specific physiological parameters of an individual. We report using a reinforcement learning (RL) model for customary vessel parameters when training with subject-specific pressure and flow waveforms. We use an equivalent electric-circuit model for the human arteries and adjust the values of resistors, inductors, and capacitors in combination with reinforcement learning (RL). The conceived model stems as a digital twin replicating specific subjects. The reinforcement learning (RL) method predicts the vessel length and radius with an error of less than 10 % and fits pressure waveforms with a similarity higher than 94 %.
Translated text
AI Read Science
Must-Reading Tree
Generate MRT to find the research sequence of this paper
Chat Paper
Summary is being generated by the instructions you defined