• N. Hema Girija
• R. Aravind
• K. Sandhya Rani

Crowding within Emergency Departments (EDs) can have serious negative effects on patients. EDs need to explore the use of novel approaches to improve patient experience and reduce overcrowding. One possible approach is the use of data mining to predict ED admissions using machine learning techniques. We use two algorithms to build the predictive models: Logistic Regression and Random Forests. Drawing on logistic Regression, we identify several factors related to hospital admissions including hospital site, age, arrival mode, care group, previous admission in the past month and previous admission in the past year. Practical implementation of the models produced in this study would provide a snapshot of predicted admissions from an emergency department at a given time, allowing for advance planning of resources, and inpatient movement to prevent bottlenecks, as well as analysis of the predicted and actual admission rates When interpretability and key consideration, EDs should consider adopting logical regression models, although GBMs will be useful for giving an accuracy amount.

Emergency Department, triage, GBM, hospital admissions.

"Classification and Prediction For Hospital Admissions Through Emergency Department", International Journal of Emerging Technologies and Innovative Research (www.jetir.org), ISSN:2349-5162, Vol.7, Issue 3, page no.700-702, March-2020, Available :http://www.jetir.org/papers/JETIR2003109.pdf

"Classification and Prediction For Hospital Admissions Through Emergency Department", International Journal of Emerging Technologies and Innovative Research (www.jetir.org | UGC and issn Approved), ISSN:2349-5162, Vol.7, Issue 3, page no. pp700-702, March-2020, Available at : http://www.jetir.org/papers/JETIR2003109.pdf