emergency department | The Journal of Critical Care Medicine

Using Machine Learning Techniques to Predict Hospital Admission at the Emergency Department

Georgios Feretzakis^1,3, George Karlis², Evangelos Loupelis¹, Dimitris Kalles³, Rea Chatzikyriakou¹, Nikolaos Trakas¹, Eugenia Karakou¹, Aikaterini Sakagianni¹, Lazaros Tzelves¹, Stavroula Petropoulou¹, Aikaterini Tika¹, Ilias Dalainas¹, Vasileios Kaldis¹

1 Sismanogleio General Hospital, Athens, Greece
2 Sotiria General Hospital of Chest Diseases of Athens, Athens, Greece
3 Hellenic Open University, Patras, Greece

DOI: 10.2478/jccm-2022-0003

Introduction: One of the most important tasks in the Emergency Department (ED) is to promptly identify the patients who will benefit from hospital admission. Machine Learning (ML) techniques show promise as diagnostic aids in healthcare.
Aim of the study: Our objective was to find an algorithm using ML techniques to assist clinical decision-making in the emergency setting.
Material and methods: We assessed the following features seeking to investigate their performance in predicting hospital admission: serum levels of Urea, Creatinine, Lactate Dehydrogenase, Creatine Kinase, C-Reactive Protein, Complete Blood Count with differential, Activated Partial Thromboplastin Time, DDimer, International Normalized Ratio, age, gender, triage disposition to ED unit and ambulance utilization. A total of 3,204 ED visits were analyzed.
Results: The proposed algorithms generated models which demonstrated acceptable performance in predicting hospital admission of ED patients. The range of F-measure and ROC Area values of all eight evaluated algorithms were [0.679-0.708] and [0.734-0.774], respectively. The main advantages of this tool include easy access, availability, yes/no result, and low cost. The clinical implications of our approach might facilitate a shift from traditional clinical decision-making to a more sophisticated model.
Conclusions: Developing robust prognostic models with the utilization of common biomarkers is a project that might shape the future of emergency medicine. Our findings warrant confirmation with implementation in pragmatic ED trials.

Improving Clinical Performance of an Interprofessional Emergency Medical Team through a One-day Crisis Resource Management Training

Teodora Sorana Truța¹, Cristian Marius Boeriu¹, Marc Lazarovici², Irina Ban³, Marius Petrișor¹, Sanda-Maria Copotoiu¹

1 University of Medicine and Pharmacy of Tîrgu Mureș, Street Gheorghe Marinescu 38, 540139 Tîrgu Mureș, Mureș, Romania
2 Institut für Notfallmedizin und Medizinmanagement – INM, Klinikum der Universität, Ludwig-Maximilians-Universität München, Schillestraße 53, 80336 München, Germany
3 Department of Medicine, University of Padova, Via V. Galluci, 13-35121, Padova, Italy

DOI: 10.2478/jccm-2018-0018

Introduction: Errors are frequent in health care and Emergency Departments are one of the riskiest areas due to frequent changes of team composition, complexity and variety of the cases and difficulties encountered in managing multiple patients. As the majority of clinical errors are the results of human factors and not technical in nature or due to the lack of knowledge, a training focused on these factors appears to be necessary. Crisis resource management (CRM), a tool that was developed initially by the aviation industry and then adopted by different medical specialties as anesthesia and emergency medicine, has been associated with decreased error rates.
The aim of the study: To assess whether a single day CRM training, combining didactic and simulation sessions, improves the clinical performance of an interprofessional emergency medical team.
Material and Methods: Seventy health professionals with different qualifications, working in an emergency department, were enrolled in the study. Twenty individual interprofessional teams were created. Each team was assessed before and after the training, through two in situ simulated exercises. The exercises were videotaped and were evaluated by two assessors who were blinded as to whether it was the initial or the final exercise. Objective measurement of clinical team performance was performed using a checklist that was designed for each scenario and included essential assessment items for the diagnosis and treatment of a critical patient, with the focus on key actions and decisions. The intervention consisted of a one-day training, combining didactic and simulation sessions, followed by instructor facilitated debriefing. All participants went through this training after the initial assessment exercises.
Results: An improvement was seen in most of the measured clinical parameters.
Conclusion: Our study supports the use of combined CRM training for improving the clinical performance of an interprofessional emergency team. Empirically this may improve the patient outcome.