Muutke küpsiste eelistusi

Optimizing Hospital-wide Patient Scheduling: Early Classification of Diagnosis-related Groups Through Machine Learning 2014 ed. [Pehme köide]

  • Formaat: Paperback / softback, 119 pages, kõrgus x laius: 235x155 mm, kaal: 2175 g, 22 Illustrations, black and white; XIV, 119 p. 22 illus., 1 Paperback / softback
  • Sari: Lecture Notes in Economics and Mathematical Systems 674
  • Ilmumisaeg: 09-Jun-2015
  • Kirjastus: Springer International Publishing AG
  • ISBN-10: 3319040650
  • ISBN-13: 9783319040653
Teised raamatud teemal:
  • Pehme köide
  • Hind: 48,70 €*
  • * hind on lõplik, st. muud allahindlused enam ei rakendu
  • Tavahind: 57,29 €
  • Säästad 15%
  • Raamatu kohalejõudmiseks kirjastusest kulub orienteeruvalt 2-4 nädalat
  • Kogus:
  • Lisa ostukorvi
  • Tasuta tarne
  • Tellimisaeg 2-4 nädalat
  • Lisa soovinimekirja
Optimizing Hospital-wide Patient Scheduling: Early Classification of Diagnosis-related Groups Through Machine Learning 2014 ed.Suurem pilt
  • Formaat: Paperback / softback, 119 pages, kõrgus x laius: 235x155 mm, kaal: 2175 g, 22 Illustrations, black and white; XIV, 119 p. 22 illus., 1 Paperback / softback
  • Sari: Lecture Notes in Economics and Mathematical Systems 674
  • Ilmumisaeg: 09-Jun-2015
  • Kirjastus: Springer International Publishing AG
  • ISBN-10: 3319040650
  • ISBN-13: 9783319040653
Teised raamatud teemal:
Püsilink: https://www.kriso.ee/db/9783319040653.html
Märksõnad:
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.
1 Introduction
1(8)
1.1 DRG-Systems and the Economic Situation in Hospitals
1(3)
1.2 Necessity of a Holistic Planning Approach
4(1)
1.3 Strategic, Tactical and Operational Problems in Hospitals
5(1)
1.4 Topic of This Dissertation
6(2)
1.5 Outline
8(1)
2 Machine Learning for Early DRG Classification
9(24)
2.1 Machine Learning for Health Care: A Literature Review
9(6)
2.1.1 Selection Criteria and Search for Relevant Literature
10(1)
2.1.2 Classification of Relevant Literature
11(4)
2.2 Attribute Ranking and Selection Techniques Employed for Early DRG Classification
15(10)
2.2.1 Information Gain Attribute Ranking
15(2)
2.2.2 Relief-F Attribute Ranking
17(3)
2.2.3 Markov Blanket Attribute Selection
20(4)
2.2.4 Correlation-Based Feature Selection
24(1)
2.2.5 Wrapper Attribute Selection
24(1)
2.3 Classification Techniques Employed for Early DRG Classification
25(8)
2.3.1 Naive Bayes
26(1)
2.3.2 Bayesian Networks
26(1)
2.3.3 Classification Trees
27(3)
2.3.4 Voting-Based Combined Classification
30(1)
2.3.5 Probability Averaging to Combine the DRG Grouper with Machine Learning Approaches
31(1)
2.3.6 Decision Rule-Based Mapping of Attribute Values to DRGs
31(2)
3 Scheduling the Hospital-Wide Flow of Elective Patients
33(22)
3.1 Mathematical Programming Applied to Patient Scheduling in Hospitals
33(8)
3.1.1 Selection Criteria and Search for Relevant Literature
34(1)
3.1.2 Classification of Relevant Literature
34(7)
3.2 The Patient Flow Problem with Fixed Admission Dates
41(5)
3.3 The Patient Flow Problem with Variable Admission Dates
46(2)
3.4 An Example of the Patient Flow Problem with Fixed and Variable Admission Dates
48(3)
3.5 A Rolling Horizon Approach for Scheduling the Hospital-Wide Flow of Elective Patients
51(4)
4 Experimental Analyses
55(38)
4.1 Experimental Evaluation of the Early DRG Classification
55(29)
4.1.1 Data from Patients That Contact the Hospital Before Admission (Elective Patients)
55(2)
4.1.2 Data from All Patients Available at Admission (Elective and Non-elective Patients)
57(3)
4.1.3 Results of the Attribute Ranking and Selection
60(3)
4.1.4 Evaluation Techniques for the Classification Part
63(1)
4.1.5 Computation Times
64(4)
4.1.6 Parameter Optimization for the Classification Tree
68(2)
4.1.7 Results of the Classification Techniques
70(6)
4.1.8 Investigation on Major Diagnostic Categories
76(3)
4.1.9 Investigation on Selected DRGs
79(3)
4.1.10 Evaluation of Expected Revenue Estimates
82(2)
4.2 Computational and Economic Analysis of Scheduling the Hospital-Wide Flow of Elective Patients
84(9)
4.2.1 Data and Instance Generation
84(3)
4.2.2 Computation Time Analysis of the Static Approaches
87(1)
4.2.3 Economic Analysis of the Static Approaches
87(1)
4.2.4 Economic Analysis of the Rolling Horizon Approach
88(5)
5 Conclusion
93(4)
5.1 Summary
93(2)
5.2 Main Research Contributions
95(1)
5.3 Future Research
95(2)
A Notation and List of Abbreviations 97(4)
B Attributes Assessed and Ranking Results for the Early DRG Classification 101(8)
Bibliography 109
Daniel Gartner earned his doctoral degree in Operations Management at the TUM School of Management, Technische Universität München, Germany. His research examines optimization problems in health care and machine learning techniques to improve hospital-wide scheduling decisions. Prior to joining TUM he received his university diploma (Master's equivalent) in medical informatics from the University of Heidelberg, Germany, and a M.Sc. in Networks and Information Systems from the Université Claude Bernard Lyon, France.