Predicting Readmission Following Hospital Treatment for Patients with Alcohol Related Diagnoses in an Australian Regional Health District

Jingxiang Zhang; Siyu Qian; Guoxin Su; Chao Deng; Ping Yu

doi:10.3233/SHTI220273

Predicting Readmission Following Hospital Treatment for Patients with Alcohol Related Diagnoses in an Australian Regional Health District

Stud Health Technol Inform. 2022 Jun 6:290:1072-1073. doi: 10.3233/SHTI220273.

Authors

Jingxiang Zhang¹, Siyu Qian^{1

2}, Guoxin Su³, Chao Deng^{4

5}, Ping Yu^{1

5}

Affiliations

¹ Centre for Digital Transformation, School of Computing and Information Technology, Faculty of Engineering and Information Sciences, University of Wollongong, Australia.
² Drug and Alcohol Service, Illawarra Shoalhaven Local Health District, Australia.
³ School of Computing and Information Technology, Faculty of Engineering and Information Sciences, University of Wollongong, Australia.
⁴ School of Medicine and Molecular Horizons, University of Wollongong, Wollongong, Australia.
⁵ Illawarra Health and Medical Research Institute, Wollongong, Australia.

PMID: 35673211
DOI: 10.3233/SHTI220273

Abstract

This study aims to investigate the prediction of hospital readmission of alcohol use disorder patients within 28 days of discharge and compare the performance of six machine learning methods i.e., random forest (RF), logistics regression, linear support vector machine (SVM), polynomial SVM, radial SVM, and sigmoid SVM.

Keywords: Alcohol use disorder; Hospital readmission; Machine learning.

MeSH terms

Australia / epidemiology
Hospitals
Humans
Machine Learning*
Patient Readmission*
Support Vector Machine