Data-Driven Simulator for Mechanical Circulatory Support with Domain Adversarial Neural Process

TL;DR

This paper introduces a neural process-based simulator for Mechanical Circulatory Support devices that incorporates domain adversarial training to better model patient-specific behavior and improve prediction accuracy.

Contribution

It presents a novel Domain Adversarial Neural Process model that combines simulation data with real-world observations for more realistic MCS device modeling.

Findings

19% improvement in non-stationary trend prediction

Effective integration of simulation and real-world data

Enhanced understanding of patient-specific MCS behavior

Abstract

Mechanical Circulatory Support (MCS) devices, implemented as a probabilistic deep sequence model. Existing mechanical simulators for MCS rely on oversimplifying assumptions and are insensitive to patient-specific behavior, limiting their applicability to real-world treatment scenarios. To address these shortcomings, our model Domain Adversarial Neural Process (DANP) employs a neural process architecture, allowing it to capture the probabilistic relationship between MCS pump levels and aortic pressure measurements with uncertainty. We use domain adversarial training to combine simulation data with real-world observations, resulting in a more realistic and diverse representation of potential outcomes. Empirical results with an improvement of 19% in non-stationary trend prediction establish DANP as an effective tool for clinicians to understand and make informed decisions regarding MCS patient treatment.