All studies
Study 02 · BMC Medical Informatics and Decision Making
Peer reviewedBreathing emergencies and nonlinear risk
How response time, age and sex interact with high-risk time-sensitive triage among 132,395 breathing-problem missions.
Age was the most important model feature. Patients older than 60 showed complex rising HRTS probability at prolonged response times beyond two hours; discrimination was modest (AUC 0.66).
- Research question
- How response time, age and sex interact with high-risk time-sensitive triage among 132,395 breathing-problem missions.
- Study population
- 132,395 EMS missions · 2017–2022 · Stockholm, Sweden
- Method
- Retrospective observational analysis of 132,395 breathing-problem missions in Stockholm, 2017–2022. Multiple models were explored, with PD and ICE plots used to examine nonlinear relationships.
- Key findings
- Age was the most important model feature. Patients older than 60 showed complex rising HRTS probability at prolonged response times beyond two hours; discrimination was modest (AUC 0.66).
- Operational relevance
- Extended waits may justify systematic reassessment, especially when demographic and clinical vulnerability could be underestimated at the first call.
The exploratory model is not validated for patient-level prediction or dispatch automation and was based on limited variables from one region.
Open publication ↗Why might the same wait matter differently?
Explore this research questionOriginal publication title
Uncovering nonlinear patterns in time-sensitive prehospital breathing emergencies: an exploratory machine learning study
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 response time, age and sex interact with high-risk time-sensitive triage among 132,395 breathing-problem missions.
- Study population
- 132,395 EMS missions
- Setting
- Stockholm, Sweden
- Study period
- 2017–2022
- Method
- Retrospective observational analysis of 132,395 breathing-problem missions in Stockholm, 2017–2022. Multiple models were explored, with PD and ICE plots used to examine nonlinear relationships.
- Interpretation boundaries
- The exploratory model is not validated for patient-level prediction or dispatch automation and was based on limited variables from one region.
- Cite this research
- Hill P, Jonsson D, Lederman J, Bolin P, et al. Uncovering nonlinear patterns in time-sensitive prehospital breathing emergencies: an exploratory machine learning study. BMC Med Inform Decis Mak. 2025;25:205. doi:10.1186/s12911-025-03046-z