The increase in patients presenting to the emergency department (ED) for primary care poses a serious safety issue in the care that can be provided. In a care area that is overcrowded, physicians, nurses, ancillary department staff, and other care team members may have a difficult time delivering care. Poorly managed flow in the ED leads to overcrowding, and patients with life-threatening illnesses are less likely to be transitioned to designated specialized areas in a safe and efficient manner. The practice-focused question was whether processes to improve the flow of patients entering the ED decreased the number of patients leaving without being seen, decreased time from the time entering the ED to hospital admission, improved the average length of stay, and increased patient satisfaction. The plan-do-check-act methodology was used to address this quality improvement project. Results of the project demonstrated a decrease in the number of patients leaving without being seen, a decrease in the time entering the ED to hospital admission, a decrease in average length of stay, and an increase in patient satisfaction. This project provided positive social change to the patients, families, organization, and community by improving the ED processes to ensure patient needs were addressed as rapidly as possible.

In this work, we produce several prediction models for aspects of hospital emergency departments. Firstly, we demonstrate the use of a recurrent neural network to predict the rate of patient arrival at a hospital emergency department. The prediction is made on a per hour basis using date, time, calendar, and weather information. Then, we present our comparison of two prediction systems on the task of replicating the human decisions of patient admittance in a typical American emergency department. Again, a recurrent neural network (RNN) was trained to learn the task of selecting the next patient from the waiting room/queue to be admitted for treatment. Lastly, we present our attempt to produce a regression model that can predict the likelihood that a given patient will leave after waiting a specific amount of time in the emergency department’s waiting-room/queue. Such a model could be used to optimize the patient’s waiting-room/queue of an ED to minimize the likelihood of patients leaving without receiving care.

Influenza is a highly contagious respiratory virus that can cause very severe health complications in people, and can be especially dangerous for young children. The peak influenza season occurs in the winter months with February usually being the month with the highest number of reported infections. As the virus can cause serious illness, pediatric institutions during the winter months see a very large number of patients who have influenza or influenza related complications. Pediatric Emergency Departments (ED) similarly see a dramatic increase in the number of patients who visit the ED during the winter influenza season. Therefore, it is important that pediatric EDs develop ways to handle the increased patient population while still maintaining quality care to the rest of the ED. Thus, a novel influenza clinic run entirely by non-ED Nurse Practitioners (NP) was implemented into the operations of the ED as an annexed clinic in February 2013 during the winter influenza season. The clinic was beneficial in improving the average quality measures of the ED against similar days without the influenza clinic, lowering the average length of stay (LOS) by 24 minutes (13% decrease) and lowering the left without being seen rates (LWBS) by 1.35% (3 fewer patients on average). In addition, using NPs instead of higher cost physicians dramatically lowered the cost of the clinic by nearly half. While the influenza clinic was beneficial in lowering the average LOS and LWBS rates against similar days without the clinic the data did not reach statistical significance, perhaps due to the small amount of data available. The results, despite the statistical insignificance, show a promising future in addition of an NP run influenza clinic to handle the increased patient population during the winter influenza season.