English

Input-Output Non-Linear Dynamical Systems applied to Physiological Condition Monitoring

Machine Learning 2016-10-11 v2

Abstract

We present a non-linear dynamical system for modelling the effect of drug infusions on the vital signs of patients admitted in Intensive Care Units (ICUs). More specifically we are interested in modelling the effect of a widely used anaesthetic drug (Propofol) on a patient's monitored depth of anaesthesia and haemodynamics. We compare our approach with one from the Pharmacokinetics/Pharmacodynamics (PK/PD) literature and show that we can provide significant improvements in performance without requiring the incorporation of expert physiological knowledge in our system.

Keywords

Cite

@article{arxiv.1608.00242,
  title  = {Input-Output Non-Linear Dynamical Systems applied to Physiological Condition Monitoring},
  author = {Konstantinos Georgatzis and Christopher K. I. Williams and Christopher Hawthorne},
  journal= {arXiv preprint arXiv:1608.00242},
  year   = {2016}
}

Comments

15 pages, 4 figures, Presented at 2016 Machine Learning and Healthcare Conference (MLHC 2016), Los Angeles, CA, camera ready version