Hospital patients arrival prediction using Markov chain model method

The outpatient care unit is one of hospital services visited first by patients for treatment. More and more patients are coming, the data will also increase. However, the patients' data in the form of the patients' arrival historical data has not been fully utilized by the hospital to impr...

Full description

Saved in:
Bibliographic Details
Published in:2016 4th International Conference on Cyber and IT Service Management pp. 1 - 7
Main Authors: Nazir, Alwis, Anggraini, Lia, Octavia, Lola, Syafria, Fadhilah
Format: Conference Proceeding
Language:English
Published: IEEE 01-04-2016
Subjects:
Online Access:Get full text
Tags: Add Tag
No Tags, Be the first to tag this record!
Description
Summary:The outpatient care unit is one of hospital services visited first by patients for treatment. More and more patients are coming, the data will also increase. However, the patients' data in the form of the patients' arrival historical data has not been fully utilized by the hospital to improve the re-registration services that are still running conventional. This study aimed to analyze the arrival of patients by predicting their arrival. Patients' data processed by one of data mining techniques called prediction. This research is to predict the arrival of patients for a week for the next visit based on historical data of patients' arrival. Data used to build prediction models are data from XYZ Hospital. These data are the data of outpatients in 2011 amounted 17 814 records. These will be processed using Markov Chain Model· Markov Chain Model is a method of studying the movement of a variable in the future based on the movement of the variable in the present. The result obtained in the form of the greatest probability of the next patient's arrival which is the second day to the sixth based on the first arrival day of the patient to the hospital. Based on the test it was concluded that the Markov Chain Model could be a method to predict the arrival day of patients for a week.
DOI:10.1109/CITSM.2016.7577590