A Computational Model Based on Human Performance for Fluid Management in Critical Care

December 2016

A Computational Model Based on Human Performance for Fluid Management in Critical Care

Authors:

Anqi Li, Michael Lewis, Christian Lebiere, Katia Sycara, Shehzaman Salim Khatib, Yuqing Tang, Matthew Siedsma, and Don Morrison

Abstract:

Computational simulation is one of the most important ways of reproducing the dynamic responses of a Cyber Physical System using a model of the system. The simulation discovers areas of differential system performance and allows linking such performance back to system characteristics. In the medical domain, patient simulators are used to train physicians in patient management. One critical question is how to verify these systems under realistic human (physician) input. This requires the creation of realistic human models that would be able to capture human cognitive and decision abilities and limitations. Verification of such an overall physician-patient model would result in two advantages: (a) since physicians realistically would not give all possible inputs to the system, verification could be more efficient and (b) the verification may uncover areas of poor human performance. In this paper, we describe our methodology and results in creating a computational model of human fluid management in critical care, based on human experiments.
@conference{Li-2016-5625,
author = {Anqi Li And Michael Lewis And Christian Lebiere And Katia Sycara And Shehzaman Salim Khatib And Yuqing Tang And Matthew Siedsma And Don Morrison},
title = {A Computational Model Based on Human Performance for Fluid Management in Critical Care},
booktitle = {Proceedings of IEEE Symposium Series on Computational Intelligence (SSCI '16)},
year = {2016},
month = {December},
}
Copyright notice: This material is presented to ensure timely dissemination of scholarly and technical work. Copyright and all rights therein are retained by authors or by other copyright holders. All persons copying this information are expected to adhere to the terms and constraints invoked by each author's copyright. These works may not be reposted without the explicit permission of the copyright holder.