New Papers Related to Healthcare

Predictive Analytics

1. Bravo, Fernanda and Rudin, Cynthia and Shaposhnik, Yaron and Yuan, Yuting, Simple Rules for Predicting Congestion Risk in Queueing Systems: Application to ICUs (May 7, 2019). SSRN: https://ssrn.com/abstract=3384148

We study the problem of predicting congestion risk in service systems in order to improve the overall system performance by initiating preventive measures, such as rescheduling activities or increasing short-term capacities. To this end, we define “high-risk states” as system states that are likely to lead to a congested state in the near future, and strive to formulate simple rules for determining whether a given system state is high-risk. We show that for simple queueing systems, such as the M / M / ∞ queue with multiple customer classes, such rules could be approximated by linear and quadratic functions on the state space. For more general queueing systems, we develop a computational framework for devising simple prediction rules, and demonstrate through extensive computational study its effectiveness. We also show that for several queueing models that are often used to model ICUs, linear classifiers provide very accurate prediction rules.

Keywords: Congestion; Queueing systems; Prediction; Service operation; Machine learning; Interpretability; ICU

Summary

1.

Triage Standing Order in Emergency Department

1. Saied Samiedaluie, Vera Tilson, and Armann Ingolfsson. Models of the Impact of Triage Nurse Standing Orders on Emergency Department Length of Stay.

Standing orders allow triage nurses in emergency departments (EDs) to order tests for certain medical conditions before the patient sees a physician, which could reduce the patient’s length of stay (LOS). Several medical studies have documented a decrease in average ED LOS for a target patient population, resulting from the use of standing orders. We formulate models of the operational impact of standing orders and test several policies for whether to order tests at triage for individual target patients, as a function of ED congestion. We find that a threshold policy, with a threshold whose value can be estimated easily from model primitives, performs well across a wide range of parameter values. We demonstrate potential unintended consequences of the use of standing orders, including over testing and spillover effects on non-target patients.

2. Karim Ghanes, Oualid Jouini, Mathias Wargon, Zied Jemai. Modeling and analysis of triage nurse ordering in emergency departments. Conference on Industrial Engineering and Systems Management IESM’15, Oct 2015, Seville, Spain

Emergency departments are facing a worldwide problem that affects their performance, namely Overcrowding. Triage Nurse Ordering appears to be a promising approach in addition to be cost effective. This paper proposes a process-based triage nurse ordering model and assesses its efficiency on the ED performance through simulation while considering the length of stay as the key indicator. The study examines the impact of triage nurse ability, system load and triage time extension on the benefits that might be derived from triage nurse ordering.

Keywords: emergency departments; triage nurse ordering;simulation; length of stay

3. PhD Thesis: Advanced Triage Protocols in the Emergency Department, by Lijuan Zhao, Walden University, 2017.

Approximation: mean value analysis vs. mean field analysis

What are their differences?