Variational Autoencoder-Based Model Predictive Control for Automated Fluid Resuscitation
Keywords: Fluid resuscitation, robust nonlinear state-space modeling, autoencoder learning, variational autoencoder, model predictive control.
TL;DR: This work presents a pioneering approach to fluid resuscitation by developing a novel machine learning-based model for hemodynamic identification and a model predictive control (MPC) algorithm for fluid dosage adjustment.
Abstract: This paper presents a novel approach for automated fluid resuscitation by modeling hemodynamics with a machine learning method and controlling it with a model predictive control (MPC) algorithm. The modeling framework, called the robust nonlinear state-space modeling (RNSSM), uses variational autoencoders to predict hemodynamic responses from limited and noisy critical care data during hemorrhage resuscitation. The MPC controller, designed for the RNSSM models, leverages its predictive capabilities for precise control of fluid dosages in resuscitation. Simulation results demonstrate the potential of this approach in improving the safety and efficacy of fluid resuscitation in critical care settings.
Track: 4. AI-based clinical decision support systems
Registration Id: PGNSFTL4HVP
Submission Number: 386
Loading