Seybold Report ISSN: 1533-9211
P. Suneel Kumar
Professor, Department of Electronics and Communication Engineering, Sridevi Women’s Engineering College, Hyderabad, India, psunilkumar.ece@gmail.com
Morla Rachana
U.G. Student, Department of Electronics and Communication Engineering, Sridevi Women’s Engineering College, Hyderabad, India, rachanamorla@gmail.com
Bhagavatula Sai Malavika
U.G. Student, Department of Electronics and Communication Engineering, Sridevi Women’s Engineering College, Hyderabad, India, malubhagavatula642@gmail.com
Nittala Sai Shridula
U.G. Student, Department of Electronics and Communication Engineering, Sridevi Women’s Engineering College, Hyderabad, India, sai.shridula@gmail.com
Vol 17, No 07 ( 2022 ) | DOI: 10.5281/zenodo.6876034 | Licensing: CC 4.0 | Pg no: 54-60 | Published on: 25-07-2022
Abstract
The In-hospital length of stay (LOS) is expected to increase as disease complexity increases and the population ages. This will affect healthcare systems, especially with the current situation of decreased bed capacity and increasing costs. Therefore healthcare, accurately predicting LOS would have a positive on metrics. The length of stay (LOS) is an important indicator of the efficiency of hospital management. The purpose of this study was to determine which factors are associated with length of hospital stay, based on electronic health records, to manage the hospital, stay more efficiently our aim of the project is to predict the length of stay of the patients using the CART algorithm Classification and Regression Trees (CART) is only a modern term for what is otherwise known as Decision Trees. In this paper, we devise a two-stage classification model to classify patients into resource user groups with lower variability by using a digital record of the patient's health. It is possible to use a variety of statistical methods to divide patients into groups with lower levels of variability in their use of resources.
Keywords:
Random Forest, CART Analysis, Length of stay, KNN