Document Type : Original Article

Authors

• Saba Paydar ¹
• GholamAli Reisi Ardali ²
• Hossein Raeisi ³

¹ Msc, Industrial Engineering, Department of Industrial and Systems Engineering Isfahan University of Technology, Isfahan. Iran

² Associate Professor, Industrial Engineering, Department of Industrial and Systems Engineering, Isfahan University of Technology, Isfahan, Iran

³ MSc Student, Industrial Engineering, Department of Industrial and Systems Engineering, Isfahan University of Technology, Isfahan, Iran

Abstract

Introduction: Today, hospitals face challenges such as overcrowding in the emergency ward and increased chaos and disruption in staff work, which leads to increased patient dissatisfaction. With the advancement of artificial intelligence and the expansion of data mining, predicting patient admission has become important. This study endeavors to predict patient admission in the emergency department of Imam Ali Hospital in Shahrekord.
Methods: In this study, 2180 patient records from the emergency ward of the hospital were examined. Initial patient information, including personal details, vital signs, and triage level which were recorded by nurses, were extracted. Using pairwise comparison matrix, the effective features were selected by experts. Then, using naive Bayes, decision tree, random forest, and support vector machine algorithms, the data were classified.
Results: Out of the 15 collected features, 9 features were selected by experts, and the results revealed that the random forest algorithm had the good performance in predicting patient admission in this case study, with an accuracy of 92/2%.
Conclusion: The results indicated that the accuracy of machine learning models increases with the use of expert opinions, and the random forest algorithm can predict patients' admission with high accuracy in this case study.v

Keywords

• Data mining
• Forecasting
• Patient admission
• Hospital Emergency Services

Main Subjects

• Health Information management