Models for Solving Emergency Room Crisis
Jomon Aliyas Paul
Kennesaw State University
Research Scientist, CUBRC
Emergency department issues like ambulance diversion, overcrowding etc are due to reduced throughput problems (increased length of stay) in the Emergency department. These problems are primarily due to diagnostic errors and incorrect disposition of patients. We propose to address these issues with the help of Bayesian models developed using patient data.
Emergency rooms across United States are distraught with issues like overcrowding, ambulance diversion, medical errors, patient left without being seen etc. An effective strategy in solving such a crisis is one that understands the interrelatedness of these issues and addresses them single handedly. A primary cause for all such unrest is long patient waiting times and length of stay due to inaccurate diagnosis and disposition of the patients. Thereby a tool that supports decision making with regard to these critical steps in emergency care forms the focus of this research endeavor. In this regard, we propose Bayesian networks that uses past patient data to accurately classify new incoming patients into different severity types based on their chief complaints and at the same time assist doctors in subsequent diagnosis and disposition of patients. Information fed into the Bayesian net is obtained at the triage station. Further to increase the reliability of the proposed tools, we apply techniques like kappa statistics to improve the agreement between the doctors and Bayesian tools developed in this research. We demonstrate applications of our models via case studies on chest pain and dyspnea two of the most common chief complaints in hospital emergency departments.