What is it about?
When ambulances are busy, response time for concurrent medical emergencies may be affected differently in different places. With data on incidents in the Central Norway region over a ten year period, we estimated a probability of busy ambulance being 35% in urban and 22% in rural areas. Still, busy ambulances had a smaller impact in urban areas, accounting for about an average of 1-minute delay per incident compared to 1 minute 45 seconds in rural areas. This highlights that availability of ambulances may have larger impact in places where resources are fewer and further between.
Featured Image
Photo by Eugene Chystiakov on Unsplash
Why is it important?
Knowledge on how busy ambulances affect response times is important for planning and organizing ambulance services.
Perspectives
As a foundation for this work, we developed a new approach for assessing effects from real life observational data, using machine learning to estimate the probability of busy ambulances. We analysed the data as a natural experiment, comparing only between incidents in the same geographical area at similar times. The method shows promise as a way to evaluate various effects of response time, which may support decision makers in organizing ambulance services.
Lars E. Næss
Norges teknisk-naturvitenskapelige universitet
Read the Original
This page is a summary of: Using machine learning to assess the extent of busy ambulances and its impact on ambulance response times: A retrospective observational study, PLoS ONE, January 2024, PLOS,
DOI: 10.1371/journal.pone.0296308.
You can read the full text:
Contributors
The following have contributed to this page
