Study II
Time-sensitive prehospital breathing emergencies
Exploratory machine-learning study of nonlinear patterns in response time, patient characteristics, and high-risk time-sensitive conditions.
Publication
Hill P, Jonsson D, Lederman J, Bolin P, Vicente V. Uncovering nonlinear patterns in time-sensitive prehospital breathing emergencies: an exploratory machine learning study. BMC Medical Informatics and Decision Making. 2025;25:205.
Study aim
The study examined nonlinear and subgroup-specific patterns in prehospital breathing-problem missions, with particular attention to response time, age, sex, and high-risk time-sensitive conditions.
Analytical approach
The study used retrospective EMS data and an exploratory machine-learning approach to inspect associations and heterogeneity. The modelling was used to support interpretation of system patterns, not to make causal or deployment-ready claims.
Patient vulnerability
Breathing-problem missions may include clinically heterogeneous patients with different vulnerability profiles and outcome risks.
Nonlinear patterns
The study investigated patterns that may not be well captured by simple linear assumptions or average response-time summaries.
System interpretation
The findings support a more nuanced view of how response time, patient factors, and clinical urgency interact in EMS data.
