Predictive modelling of hospital readmission: Evaluation of different preprocessing techniques on machine learning classifiers

Document Type

Article

Publication Date

1-1-2021

Abstract

Hospital readmission is a major cost for healthcare systems worldwide. If patients with a higher potential of readmission could be identified at the start, existing resources could be used more efficiently, and appropriate plans could be implemented to reduce the risk of readmission. Therefore, it is important to predict the right target patients. Medical data is usually noisy, incomplete, and inconsistent. Hence, before developing a prediction model, it is crucial to efficiently set up the predictive model so that improved predictive performance is achieved. The current study aims to analyse the impact of different preprocessing methods on the performance of different machine learning classifiers. The preprocessing applied by previous hospital readmission studies were compared, and the most common approaches highlighted such as missing value imputation, feature selection, data balancing, and feature scaling. The hyperparameters were selected using Bayesian optimisation. The different preprocessing pipelines were assessed using various performance metrics and computational costs. The results indicated that the preprocessing approaches helped improve the model's prediction of hospital readmission.

Keywords

Hospital readmission, Machine learning, Predictive modelling, Preprocessing

Divisions

ai,psychological

Funders

Universiti Malaya (IIRG004B-19HWB),Universiti Kebangsaan Malaysia,Ministry of Education, Malaysia

Publication Title

Intelligent Data Analysis

Volume

25

Issue

5

Publisher

IOS Press

Publisher Location

NIEUWE HEMWEG 6B, 1013 BG AMSTERDAM, NETHERLANDS

This document is currently not available here.

Share

COinS