Pratik J. Parikh, Ph.D. (Advisor); Subhashini Ganapathy, Ph.D. (Committee Member); Corrine Mowrey, Ph.D. (Committee Member)
Master of Science in Industrial and Human Factors Engineering (MSIHE)
Emergency Medical Service (EMS) providers are the first responders for an injured patient on the field. Their assessment of patient injuries and determination of an appropriate hospital play a critical role in patient outcomes. A majority of states in the US have established a state-level governing body (e.g., EMS Division) that is responsible for developing and maintaining a robust EMS system throughout the state. Such divisions develop standards, accredit EMS agencies, oversee the trauma system, and support new initiatives through grants and training. But to do so, these divisions require data to enable them to first understand the similarities between existing EMS agencies in the state in terms of their resources and activities. Benchmarking them against similar peer groups could then reveal best practices among top performers in terms of patient outcomes. While limited qualitative data exists in the literature based on surveys of EMS personnel related to their working environment, training, and stress, what is lacking is a quantitative approach that can help compare and contrast EMS agencies across a comprehensive set of factors and enable benchmarking. Our study fills this gap by proposing a data-driven approach to cluster EMS agencies (by county level) and subsequently benchmark them against their peers using two patient safety performance measures, under-triage (UT) and over-triage (OT). The study was conducted in three phases: data collection, clustering, and benchmarking. We first obtained data related to the trauma-specific capabilities, volume, and Performance Improvement activities. This data was collected by our collaborating team of health services researchers through a survey of over 300 EMS agencies in the state of OH. To estimate UT and OT, we used 6,002 de-identified patient records from 2012 made available by the state of Ohio’s EMS Division. All the data was aggregated at county level. We then used several clustering methods to group counties using three different methods: K-means, K-medoids and CLARANS. For the former two, we identified key features using the Random Forest classification technique; the latter automatically identifies such features internally. Finally, we benchmarked each county against its peer within the same cluster using guidelines from the American College of Surgeons (ACS). Our results based on the state of OH data indicated that a small number of clusters may be sufficient to group counties by their EMS capabilities, volume, and Performance Improvement (PI) activities. EMS agencies appear to cluster around county type (rural vs urban), number of trauma runs, number of paid vs. voluntary employees, and additional resources provided by EMS agencies to help with well-being and coping mechanisms for EMS providers. Benchmarking based on ACS guidelines revealed a large variation in UT and OT rates among counties in the same cluster. Up to 3-4 times higher rates were observed in several counties compared to the best performing county in that cluster, even though some of these counties had better capabilities. Such comparison among peer counties in the same cluster can unravel new insights that could be used to target cluster-specific interventions that can achieve improved outcomes. While our proposed approach was tested with state of Ohio's data and highlighted specific findings for Ohio’s EMS Division, this approach is generic enough to be used by any other regional or state EMS agency in the US.
Department or Program
Department of Biomedical, Industrial and Human Factors Engineering
Year Degree Awarded
Copyright 2020, all rights reserved. My ETD will be available under the "Fair Use" terms of copyright law.