Abstract
In recent years, the safety and reliability of information technology (IT) systems in the healthcare industry are of increasing importance. In this paper, we propose an approach for monitoring and predicting reliability degradation in Health IT (HIT) using Markov chain (MC). A MC model provides an opportunity to represent highly dynamic systems, such as HIT, in a succinct manner to simulate the evolution of the system over time in discrete time steps. The model can also represent system behavior that varies over a long duration. Consequently, using electronic health records (EHR) data from systems such as the Veterans Affairs’ Corporate Data Warehouse systems, we defined clinical workflow as a Transaction Process Model (TPM). The TPM represents a set of states in the Consult workflow. It is also an ideal workflow description and has several degrees of freedom. The TPM is then converted into a MC representation and the EHR data is used to compute transition probabilities between the nodes in the MC. The original MC representation is perturbed by changing the transition probabilities to simulate alternative system workflow paths and identifying scenarios that could impact system reliability. We present scenarios that illustrate the proposed approach and discuss some of the insights from the results.
Original language | English |
---|---|
Title of host publication | IISE Annual Conference and Expo 2019 |
Publisher | Institute of Industrial and Systems Engineers, IISE |
ISBN (Electronic) | 9781713814092 |
State | Published - 2019 |
Event | 2019 Institute of Industrial and Systems Engineers Annual Conference and Expo, IISE 2019 - Orlando, United States Duration: May 18 2019 → May 21 2019 |
Publication series
Name | IISE Annual Conference and Expo 2019 |
---|
Conference
Conference | 2019 Institute of Industrial and Systems Engineers Annual Conference and Expo, IISE 2019 |
---|---|
Country/Territory | United States |
City | Orlando |
Period | 05/18/19 → 05/21/19 |
Funding
The first author thank Yunhe Feng for his assistance with some of the figures. This work is sponsored by the US Department of Veterans Affairs. This manuscript has been authored by UT-Battelle, LLC, under contract DE-AC05-00OR22725 with the US Department of Energy (DOE). The US government retains and the publisher, by accepting the
Keywords
- Markov chain
- Perturbation algorithm
- Process improvement
- Process monitoring
- System reliability