Using Perceptual Cycle Model and Text Mining to Investigate Ambulance Traffic Crashes

Abstract

Ambulance crashes constitute a matter of utmost concern within public health, posing potential risks to both patients and emergency responders. Despite this critical importance, investigating the underlying causes of these collisions is difficult because of the scarcity of comprehensive and relevant datasets. To bridge this research gap and gain valuable insights, the present study embarked on a mission to shed light on the causative factors behind ambulance-related crashes. To achieve this objective, this study adopted a meticulous approach, collecting narrative descriptions from ten special investigation reports published by the National Highway Traffic Safety Administration. These reports were selected as they offered in-depth accounts of real-life ambulance crashes, rendering them an invaluable resource for analyzing the multifaceted aspects leading to such incidents. Central to this investigation was the utilization of the Perceptual Cycle Model (PCM), a well-established and comprehensive framework that facilitates a systematic examination of the various stages leading to a crash. The study examined the key influential factors associated with ambulance crashes by employing PCM and text mining. The results reveal diverse factors contributing to ambulance crashes, including varied causes, driver actions, and post-crash scenarios, providing a holistic understanding of road safety. The outcomes of this study will bolster the safety of ambulance operations, safeguard patients and personnel, and ensure the efficient delivery of life-saving emergency services to those in need.