Optimizing Hospital-wide Patient Scheduling

Early Classification of Diagnosis-related Groups Through Machine Learning

verfasst von: Daniel Gartner

Verlag: Springer International Publishing

Buchreihe : Lecture Notes in Economics and Mathematical Systems

Enthalten in: Springer Professional "Wirtschaft+Technik" , Springer Professional "Technik" , Springer Professional "Wirtschaft"

Einloggen, um Zugang zu erhalten

Über dieses Buch

Diagnosis-related groups (DRGs) are used in hospitals for the reimbursement of inpatient services. The assignment of a patient to a DRG can be distinguished into billing- and operations-driven DRG classification. The topic of this monograph is operations-driven DRG classification, in which DRGs of inpatients are employed to improve contribution margin-based patient scheduling decisions. In the first part, attribute selection and classification techniques are evaluated in order to increase early DRG classification accuracy. Employing mathematical programming, the hospital-wide flow of elective patients is modelled taking into account DRGs, clinical pathways and scarce hospital resources. The results of the early DRG classification part reveal that a small set of attributes is sufficient in order to substantially improve DRG classification accuracy as compared to the current approach of many hospitals. Moreover, the results of the patient scheduling part reveal that the contribution margin can be increased as compared to current practice.

Inhaltsverzeichnis

Frontmatter

Chapter 1. Introduction

Abstract

The introductory chapter consists of five sections. Section 1.1 highlights different aspects of the economic situation in hospitals. In particular, it describes the reimbursement system wherein hospitals are financed by insurances for inpatient care, based on diagnosis-related groups (DRGs). Section 1.2 explains the necessity of planning the inpatient flow in a holistic way. It outlines the need for providing health care efficiently for a variety of inpatients, each having individual characteristics and requirements for multiple types of scarce resources.

Daniel Gartner

Chapter 2. Machine Learning for Early DRG Classification

Abstract

In this chapter, a literature review of machine learning methods is provided with a special focus on attribute selection and classification methods successfully employed in health care. Similarities and differences between the machine learning methods addressed in this dissertation and the approaches available from the literature are highlighted. Afterwards, techniques for selecting relevant and non-redundant attributes for early DRG classification are presented. Finally, different classification techniques are described in detail.

Daniel Gartner

Chapter 3. Scheduling the Hospital-Wide Flow of Elective Patients

Abstract

The structure of this chapter is as follows: Firstly, a literature review on patient scheduling and capacity allocation problems in health care is provided. Similarities and differences between the scheduling problems addressed in this dissertation and the approaches available from the literature are highlighted. Secondly, the patient flow problem with fixed admission dates is presented. Thirdly, the patient flow problem with variable admission dates is described, followed by an example for both the fixed and variable admission date problem.

Daniel Gartner

Chapter 4. Experimental Analyses

Abstract

The structure of this chapter is as follows: In the first section, a thorough analysis of the presented machine learning methods for early DRG classification and its comparison with a DRG grouper is provided. In the second section, a computational and economic analysis of scheduling the hospital-wide patient flow of elective patients is given.

Daniel Gartner

Chapter 5. Conclusion

Abstract

The final chapter summarizes the dissertation and highlights the main research contributions. Areas that deserve further research are also presented.

Daniel Gartner

Backmatter

Titel: Optimizing Hospital-wide Patient Scheduling
verfasst von: Daniel Gartner
Verlag: Springer International Publishing
Electronic ISBN: 978-3-319-04066-0
Print ISBN: 978-3-319-04065-3
DOI: https://doi.org/10.1007/978-3-319-04066-0