Predictive System for Medical Emergency and Admissions Control
G. Subhashini1, V. Neelambary2
1Ms. G. Subhashini, Assistant Professor, Department of Information Technology, St. Joseph‘s Institute of Technology, Affliated to Anna University, Chennai (Tamil Nadu), India.
2Ms. V. Neelambary, Assistant Professor, Department of Information Technology, St. Joseph‘s Institute of Technology, Affliated to Anna University, Chennai (Tamil Nadu), India.
Manuscript received on 22 November 2019 | Revised Manuscript received on 03 December 2019 | Manuscript Published on 14 December 2019 | PP: 30-33 | Volume-9 Issue-1S November 2019 | Retrieval Number: A10081191S19/2019©BEIESP | DOI: 10.35940/ijitee.A1008.1191S19
Open Access | Editorial and Publishing Policies | Cite | Mendeley | Indexing and Abstracting
© The Authors. Blue Eyes Intelligence Engineering and Sciences Publication (BEIESP). This is an open-access article under the CC-BY-NC-ND license (http://creativecommons.org/licenses/by-nc-nd/4.0/)
Abstract: An emergency department (ED), provides specialized facility in emergency medicine they are the life saving one for many people in emergency cases. Some main issues in ED’s are overcrowding, quality of care for the patients etc., here overcrowding is still a big issue in most of the hospitals. This paper implements some advanced methods to improve patient flow and prevent overcrowding. The ED overcrowding can be reduced by predicting the future of patient’s admission using Machine Learning and making the resources available beforehand. This technique help us to learn, analyze and predicting the future results. In this work we implement Predictive Gradient Boosted Machines (PGBM) which produces a prediction model in the form decision trees. The data set which we use in this paper has several factors like hospital admissions, including site of the hospital, patient’s age, mode of arrival, previous admission in past month and past year. Decision Trees creates a training model which predicts the data by understanding decision rules that are observed from training data. The accuracy of the system is achieved by implementing Deep Neural Network (DNN) which uses efficient mathematical model to process data in complex ways.
Keywords: Emergency Department, Machine Learning, Predictive Gradient Boosted Machines, Decision Trees, Deep Neural Network.
Scope of the Article: Biomedical Computing