Classification of Maternity Emergency Referrals Using Gaussian Naive Bayes in the Triage Process in the Emergency Department

Document Type : Articles

Authors

1 Gadjah Mada University

2 Department of Electrical Engineering and Information Technology, Faculty of Engineering of Gadjah Mada University

3 Department of Obstetrics and Gynecology Faculty of Medicine, Public Health, and Nursing of Gadjah Mada University

10.30476/jhmi.2024.100872.1192

Abstract

Triage is needed for patient classification in the Emergency Department However,not all conditions have large amounts of data. The focus of this research is using Gaussian Naive Bayes as final model with different treatment according to data. This research was conducted at Wates Regional Hospital, Yogyakarta Special Region Province, Indonesia in 2021. This study are using 90 data train and 10 data test which are divided into two between categorical data types as much as 9 data and 6 continuous data types. There are two treatments in this study, first using the independence assumption on all parameters and second using Categorical Naive Bayes for categorical data types and Gaussian Naive Bayes for continuous data types. These two types of data will be combined using Gaussian Naive Bayes as the final model. The results of the first treatment has an accuracy of 91%, recall 97%, precision 64%, and F1-score 73%. and the second treatment has an accuracy of 96%, recall 88%, precision 86% and F1 - score 86%. This means that using combine Gaussian Naive Bayes as the final model according to the data type has better results than using Gaussian Naive Bayes without treatment. Diversity data condition helps medical personnel in classifying triage patients. Various types of medical data has challenges for solving patient classification using machine learning. Applying Gaussian Naive Bayes to non-large amounts of data as a final model of two types of categorical and continuous data obtains better results than assuming all data as continuous data.

Keywords

Main Subjects

Health Management & Information Science

Articles in Press, Accepted Manuscript
Available Online from 02 April 2024

Files

Share

How to cite

Statistics