Salvato in:
Dettagli Bibliografici
Autori principali: Sun, Sophia, Chen, Wenyuan, Zhou, Zihao, Fereidooni, Sonia, Jortberg, Elise, Yu, Rose
Natura: Preprint
Pubblicazione: 2024
Soggetti:
Accesso online:https://arxiv.org/abs/2405.18536
Tags: Aggiungi Tag
Nessun Tag, puoi essere il primo ad aggiungerne!!
_version_ 1866911891803078656
author Sun, Sophia
Chen, Wenyuan
Zhou, Zihao
Fereidooni, Sonia
Jortberg, Elise
Yu, Rose
author_facet Sun, Sophia
Chen, Wenyuan
Zhou, Zihao
Fereidooni, Sonia
Jortberg, Elise
Yu, Rose
contents 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.
format Preprint
id arxiv_https___arxiv_org_abs_2405_18536
institution arXiv
publishDate 2024
record_format arxiv
spellingShingle Data-Driven Simulator for Mechanical Circulatory Support with Domain Adversarial Neural Process
Sun, Sophia
Chen, Wenyuan
Zhou, Zihao
Fereidooni, Sonia
Jortberg, Elise
Yu, Rose
Machine Learning
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.
title Data-Driven Simulator for Mechanical Circulatory Support with Domain Adversarial Neural Process
topic Machine Learning
url https://arxiv.org/abs/2405.18536