Comparing the Performance of Ensemble Methods in Predicting Emergency Department Admissions Using Machine Learning Techniques - Research Study

Aug 3, 2026

Healthcare information systems enable collection, storage, retrieval, and analysis of patient data across tools such as electronic health records, telemedicine platforms, clinical decision support systems, and health information exchanges. In emergency departments, machine learning supports triage and risk stratification by predicting severity and urgency, detecting subtle patterns clinicians may overlook, and enabling earlier intervention. The study addresses the limited comparative evaluation of ensemble methods for this task by examining their efficacy and performance to inform researchers and practitioners.

LanguageEnglish

CategoryResearch & Report

FormatPDF

Pages11

Reading Time28 min

AccessFree to download

Introduction

Literature Review

RESEARCH ARTICLE Comparing the Performance of Ensemble Methods in Predicting Emergency Department Admissions Using Machine Learning Techniques Murat Emre Yapıcıa,† , Abdulkadir Hızıroğlua , Ali Mert Erdoğana a Department of Management Information Systems, İzmir Bakırçay University, İzmir, Türkiye,† [m.emreyapici@gmail.com](m.emreyapici@gmail.com) , corresponding author RECEIVED OCTOBER 30 , 2023 ACCEPTED JANUARY 12, 2024 CITATION Yapıcı , M. E. , Hızıroğlu, A. , & Erdoğan. A. M. (2024) . Comparing the performance of ensemble methods in predicting emergency department admissions using machine learning techniques. Artificial Intelligence Theory and Applications, 4(1), 11-21. Abstract Healthcare data collection, storage, retrieval, and analysis are enabled by various technologies and tools in health information systems. These systems include health information exchanges, telemedicine platforms, clinical decision support systems, and electronic health records. They aim to improve patient outcomes, provider communication, and healthcare workflows. Machine learning is being used in emergency rooms to address challenges such as increasing patient volume, limited resources, and the need for quick decisions. Machine learning algorithms can assist in triage and risk stratification by identifying patients requiring urgent care and predicting the severity of their condition. By analyzing various patient data sources, machine learning can detect patterns and indicators that human clinicians may miss, enabling early intervention and potentially saving lives. However, there is a lack of comparative evaluation of ensemble methods used in analysis. Therefore, this study aims to thoroughly examine and analyze various ensemble methods to understand their efficacy and performance, contributing valuable insights to researchers and practitioners. Keywords: ensemble methods, logistic regression, prediction, emergency department 1. Introduction Emergency services are essential healthcare units that provide immediate medical assistance to patients in need. They are categorized based on the urgency and severity of the patient's condition, with red indicating life-threatening emergencies, yellow indicating conditions with a risk of permanent damage, and green indicating mild injuries or illnesses [1] . Information systems play a crucial role in emergency care by providing insights into the workload, patient information, and preliminary assessments in the emergency department. These systems enable informed decision-making for triage and resource allocation, addressing challenges such as overcrowding and improving overall emergency care [2] . Healthcare information systems encompass various technologies, processes, and tools that facilitate the collection, storage, retrieval, and analysis of healthcare data [3] . Electronic health records (EHRs) serve as digital databases of patient information, supporting comprehensive and coordinated care [4] . EHRs aid clinic allergies ending by providing immediate access to vital patient data, alerting healthcare Permission to make digital or hard copies of all or part of this work for personal or classroom use is granted without fee provided that copies are not made or distributed for profit or commercial advantage and that copies bear this notice and the full citation on the first page. Copyrights for components of this work owned by others than AITA must be honored. Abstracting with credit is permitted. To copy otherwise, or republish, to post on servers or to redistribute to lists, requires prior specific permission [and/or a fee. Request permissions from info@aitajournal.com](and/or a fee. Request permissions from info@aitajournal.com) Artificial Intelligence Theory and Applications , ISSN: 2757-9778. ISBN: 978-605-69730-2-4 © 2024 İzmir Bakırçay University professionals to potential interactions or allergies and suggesting evidence-based treatment options [5] . Clinical decision suppo

FAQs

Why are emergency departments suitable for applying machine learning?

Emergency services require immediate decisions under constraints like increasing patient volume and limited resources. Machine learning supports triage and risk stratification by predicting severity and identifying urgent cases.

What role do ensemble methods play in this study?

The study focuses on comparing ensemble methods’ efficacy and performance for predicting emergency department admissions, addressing the gap in comparative evaluations.

How does machine learning improve clinical decision-making in the emergency department?

By analyzing multiple patient data sources, machine learning can detect indicators and patterns that may be missed by human clinicians, enabling early intervention and potentially better outcomes.

Aug 3, 2026

Upload by River Wang