You are here:Home>Healthcare, Optimization>Saving Children’s Lives During a Severe Pandemic

Saving Children’s Lives During a Severe Pandemic

During a severe pandemic, Saving Children’s Lives requires making difficult decisions. Rather than accepting patients on a first in, first serve basis, the patients should be triaged and allowed access to critical beds and resources based on defined criteria. But, what are the criteria? There are proposed strategies but no one has been able to show the value of implementing the strategies…until now. Alexander Kolker recently published a peer review article in Critical Care Medicine magazine that demonstrates how to increase survival by almost 25% in a severe pandemic by using a specific triage algorithm.

Saving children's lives during a severe pandemic by using process simulation.

Flowchart showing the decision structure for used save children’s lives during a severe pandemic.

Triage is defined as the assignment of degrees of urgency to wounds or illnesses. Triage is used to decide the order of treatment of a large number of patients or casualties. Boiled down, it means some will be given access to resources and some will be sent away — to assure the largest number of children will live. It means using specific criteria that give doctors a clear path to optimal outcome. During a severe pandemic, the system quickly becomes overloaded and every patient admission limits other admissions. If these decisions are not planned ahead of time, the hospitals will treat patients that would have become a casualty and not treat those they could have saved.

The Center for Disease Control (CDC) has endorsed the idea of triage allocation. But, the CDC won’t recommend any particular algorithm. This means every hospital is on their own. This is the first time that a specific triage scheme has been designed using simulation to find the optimal outcome for saving children’s lives.

Optimization Finds the Best Ways of Saving Children’s Lives

This study allowed manipulation of critical thresholds to optimize outcomes. An objective function was developed for the model. The model thresholds were changed automatically using, built-in, evolutionary algorithms to generate various solutions. The solutions must improve on the objective function to stay active. The best solution was selected when no further improvement could be made. This meant ProcessModel only ran a small subset of many thousand possible solutions and was able to find the optimal thresholds.
Some of the factors considered include:

  • Size of the pandemic
  • Pattern of patient arrival
  • Probability of death if treated
  • Days of ventilation needed
  • Beds available
  • Etc.

This study analyzed close to 1 million historical patient records dealing with similar respiratory conditions to derive the algorithms for the model. Numerous people from healthcare, statistics and public health participated in the study. The results of the study are striking and difficult to ignore, offing as much as a 25% improvement saving children’s lives during a severe pandemic.

Alex Kolker has published many other ground breaking articles, including: Predictive Analytics for Patient Length of Stay; Optimal Staffing Modeling with Variable Patent Demand; and Interdependency of Hospital Departments and Hospital-Wide Patient Flow , to name a few. ProcessModel, Inc. is particularly indebted to Alex Kolker for his tireless work in creating many improvements in Healthcare and in particular for Maximizing Survival Rate to Save Children’s Lives during a severe pandemic.

Leave a Reply