Spatial Clustering of Ambulance Dispatches for Cardiovascular Problems During Heat and Non-Heat Days: Preliminary Study for Milan, Italy

Ambulance transportation plays a critical role in Emergency Medical Services (EMS), directly impacting patient outcomes through timely response. However, during heatwaves, the emergency transportation system often faces overload, highlighting the need for optimized strategies. Despite this, studies investigating variations in emergency call patterns between heat and non-heat days are lacking. This study addresses this gap by conducting density-based clustering of ambulance dispatches separately for heat and non-heat days, analysing spatial distribution and patient characteristics. Heat days were defined as those with apparent temperature exceeding the 95<sup xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink">th</sup> percentile of its annual distribution. Ambulance dispatches for cardiovascular problems that happened in Milan, Italy in the period May-September 2017–2022 were clustered using the Hierarchical Density-Based Spatial Clustering of Applications with Noise (HDBSCAN) algorithm separately for heat and non-heat days. In the central-northern part of the city, three zones of increased spatial coverage during heat compared to non-heat days were identified. Moreover, in one cluster, a shift in spatial distribution in heat was observed. Notably, four clusters were identified during non-heat, but not during heat days. This framework offers insights for efficient emergency transportation management in extreme meteorological conditions, crucial in the context of ongoing climate change.