All studies
Study 04 · BMC Medical Informatics and Decision Making
Peer reviewedUnderstanding EMS response times
How priority, workload, geography, weather and operational intervals shape variability and tail delays.
Priority was the strongest overall feature, but workload, call reason, geography, precipitation, temperature and operational intervals interacted. Lower priorities had markedly long-tailed response-time distributions.
- Research question
- How priority, workload, geography, weather and operational intervals shape variability and tail delays.
- Study population
- 1,144,754 EMS missions · 2017–2022 · Stockholm, Sweden
- Method
- Retrospective analysis of 1,144,754 EMS missions in Stockholm, 2017–2022, integrating operational, geographic and weather variables with regression and machine-learning analyses.
- Key findings
- Priority was the strongest overall feature, but workload, call reason, geography, precipitation, temperature and operational intervals interacted. Lower priorities had markedly long-tailed response-time distributions.
- Operational relevance
- Management should monitor distributions and extreme delays across all priorities, not only a median for the highest priority. System strain can be redistributed rather than removed.
Traffic information was unavailable, the study was conducted in one region and predictive performance does not make the models ready for real-time deployment.
Open publication ↗What can the longest response times reveal?
Explore this research questionOriginal publication title
Understanding EMS response times: a machine learning-based analysis
This page is a research summary. Consult the original English publication for the full methods, results and reuse terms.
Research provenance
- Publication status
- Peer reviewed
- Research question
- How priority, workload, geography, weather and operational intervals shape variability and tail delays.
- Study population
- 1,144,754 EMS missions
- Setting
- Stockholm, Sweden
- Study period
- 2017–2022
- Method
- Retrospective analysis of 1,144,754 EMS missions in Stockholm, 2017–2022, integrating operational, geographic and weather variables with regression and machine-learning analyses.
- Interpretation boundaries
- Traffic information was unavailable, the study was conducted in one region and predictive performance does not make the models ready for real-time deployment.
- Cite this research
- Hill P, Lederman J, Jonsson D, Bolin P, et al. Understanding EMS response times: a machine learning-based analysis. BMC Med Inform Decis Mak. 2025;25:143. doi:10.1186/s12911-025-02975-z