Imbalanced prediction of emergency department admission using natural language processing and deep neural network.

The emergency department (ED) plays a very significant role in the hospital. Owing to the rising number of ED visits, medical service points, and ED market, overcrowding of EDs has become serious worldwide. Overcrowding has long been recognized as a vital issue that increases the risk to patients and negative emotions of medical personnel and impacts hospital cost management. For the past years, many researchers have been applying artificial intelligence to reduce crowding situations in the ED. Nevertheless, the datasets in ED hospital admission are naturally inherent with the high-class imbalance in the real world. Previous studies have not considered the imbalance of the datasets, particularly addressing the imbalance. This study purposes to develop a natural language processing model of a deep neural network with an attention mechanism to solve the imbalanced problem in ED admission. The proposed framework is used for predicting hospital admission so that the hospitals can arrange beds early and solve the problem of congestion in the ED. Furthermore, the study compares a variety of methods and obtains the best composition that has the best performance for forecasting hospitalization in ED. The study used the data from a specific hospital in Taiwan as an empirical study. The experimental result demonstrates that almost all imbalanced methods can improve the model's performance. In addition, the natural language processing model of Bi-directional Long Short-Term Memory with attention mechanism has the best results in all-natural language processing methods.

[Reducing False Alarms and Absent Treatments by Nurses During Resuscitation in the Emergency Department].

BACKGROUND & PROBLEMS: Medical management protocols prioritize the safety of patients during emergency resuscitation situations. According to a medical center in Taiwan statistics gathered in 2017, the unnecessary activation of resuscitation teams by new nurses because of their improper assessment of patient conditions was a significant cause of anxiety in patient relatives and source of complaints directed at the medical center. In June 2018, 18.7% of the emergency resuscitation calls in the emergency department (ED) were false alarms or absent treatment incidents. After investigation, lack of clearly stated resuscitation team member responsibilities and insufficient practical training for new nurses were primary factors associated with the high rate of false alarm/absent treatment incidents in the ED. PURPOSE: To decrease the rate of absent treatment by nurses during resuscitation from 18.7% to 0% in the ED. RESOLUTION: The assignments of emergency team members were revised, a new "Emergency app" was introduced, the assignment schedule of the emergency resuscitation team was distributed, SIM realistic education training was held, stronger team work was promoted, and a standard assignment review schedule was established and regularly monitored. RESULTS: After the introduction of the resolution measures, the false alarm / absent treatment incidents in the ED caused by ED nurses dropped from 18.7% to 0%. CONCLUSIONS: Resuscitation workflow is closely related to patient safety, and teamwork among colleagues critical to successful resuscitation. The project revised resuscitation teamwork assignments and organized resuscitation education training, including simulation courses, to enhance the understanding of team members. The strategy outlined in this paper may be used to raise awareness using posters and resuscitation record checklists to track and manage the team`s progress. This project was designed to enhance teamwork to decrease the rate of absent treatment and to provide safe and quality resuscitation care in order to improve resource management by the team to increase productivity.

An interprofessional training program for intrahospital transport of critically ill patients: model build-up and assessment.

Intrahospital transport of critically ill patients for diagnostic or therapeutic procedures can be compromised by patient instability, equipment problems or inexperienced teamworking. This quasi-experimental study aimed to assess the effectiveness of an in-situ interprofessional simulation-based training (IIST) model for junior member transport teams. Newly registered postgraduate physicians, nurses and respiratory therapists underwent the IIST. The technical skills (TS) of each participant and non-technical skills (NTS) of each interprofessional team were assessed using well-validated checklists. Thirty-six participants enrolled and were randomly assigned to six experimental and six control teams. Most participants achieved a significantly higher level of both TS and NTS. Both the control and experimental teams overvalued their NTS in the pretest, while the posttest self-assessment scores among the experimental groups more closely matched the expert assessments. Despite challenges in scheduling and the setting, the IIST was successfully conducted in a crowded hospital, which enabled trainees to optimize their learning in a real-life environment. In conclusion, the IIST model can facilitate the development of both TS and NTS for transport team members. Transport teams made up of newly registered staff from different disciplines may lack insight into their NTS in critical patient transfer management, but simulation training may cause improvements.