• No results found

Clinical decision support : distance-based, and subgroup-discovery methods in intensive care - Contents

N/A
N/A
Protected

Academic year: 2021

Share "Clinical decision support : distance-based, and subgroup-discovery methods in intensive care - Contents"

Copied!
4
0
0

Bezig met laden.... (Bekijk nu de volledige tekst)

Hele tekst

(1)

UvA-DARE is a service provided by the library of the University of Amsterdam (https://dare.uva.nl)

UvA-DARE (Digital Academic Repository)

Clinical decision support : distance-based, and subgroup-discovery methods in

intensive care

Nannings, B.

Publication date

2009

Link to publication

Citation for published version (APA):

Nannings, B. (2009). Clinical decision support : distance-based, and subgroup-discovery

methods in intensive care.

General rights

It is not permitted to download or to forward/distribute the text or part of it without the consent of the author(s)

and/or copyright holder(s), other than for strictly personal, individual use, unless the work is under an open

content license (like Creative Commons).

Disclaimer/Complaints regulations

If you believe that digital publication of certain material infringes any of your rights or (privacy) interests, please

let the Library know, stating your reasons. In case of a legitimate complaint, the Library will make the material

inaccessible and/or remove it from the website. Please Ask the Library: https://uba.uva.nl/en/contact, or a letter

to: Library of the University of Amsterdam, Secretariat, Singel 425, 1012 WP Amsterdam, The Netherlands. You

will be contacted as soon as possible.

(2)

Contents

CHAPTER 1. GENERAL INTRODUCTION ... 9

1.1. PROBLEM DOMAIN AND OBJECTIVES ... 10

1.1.1 Part 1: Subgroup discovery ... 10

1.1.2 Part 2: Decision Support Telemedicine Systems ... 11

1.2. PRELIMINARIES ... 12

1.2.1 Intensive Care ... 13

1.2.2 Clinical Decision Support Systems ... 15

1.2.3 Telemedicine ... 17

1.2.4 Telemedicine and decision support ... 17

1.3. REFERENCES ... 18

CHAPTER 2. APPLYING PRIM (PATIENT RULE INDUCTION METHOD) AND LOGISTIC REGRESSION FOR SELECTING HIGH-RISK SUBGROUPS IN VERY ELDERLY ICU PATIENTS. ... 19 2.1. ABSTRACT... 20 2.1.1 Purpose... 20 2.1.2 Methods ... 20 2.1.3 Results ... 20 2.1.4 Conclusions ... 20 2.2. INTRODUCTION ... 21 2.2.1 Subgroup discovery ... 22

2.2.2 Patient Rule Induction Method (PRIM) ... 22

2.2.3 Related work ... 24

2.2.4 Logistic regression models in Intensive Care ... 24

2.3. MATERIALS AND METHODS ... 25

2.3.1 Statistics... 28 2.4. RESULTS ... 28 2.5. DISCUSSION ... 31 2.6. CONCLUSION ... 32 2.7. ACKNOWLEDGEMENTS ... 32 2.8. REFERENCES ... 33

CHAPTER 3. A SUBGROUP DISCOVERY APPROACH FOR SCRUTINIZING BLOOD GLUCOSE MANAGEMENT GUIDELINES BY THE IDENTIFICATION OF HYPERGLYCEMIA DETERMINANTS IN ICU PATIENTS ... 35

3.1. ABSTRACT... 36 3.1.1 Objective ... 36 3.1.2 Methods ... 36 3.1.3 Results ... 36 3.1.4 Conclusions ... 36 3.2. INTRODUCTION ... 37 3.3. OBJECTIVES ... 37 3.4. METHODS ... 38 3.4.1 Data ... 38

(3)

3.4.2 Subgroup discovery ... 41 3.4.3 Validation ... 43 3.5. RESULTS ... 44 3.6. DISCUSSION ... 46 3.7. CONCLUSIONS ... 50 3.8. ACKNOWLEDGEMENTS ... 50 3.9. REFERENCES ... 51

CHAPTER 4. PRIM VERSUS CART IN SUBGROUP DISCOVERY: WHEN PATIENCE IS HARMFUL ... 53 4.1. ABSTRACT... 54 4.1.1 Context... 54 4.1.2 Objective ... 54 4.1.3 Methods ... 54 4.1.4 Results ... 54 4.1.5 Conclusions ... 54 4.2. INTRODUCTION ... 56

4.3. MATERIALS AND METHODS ... 57

4.3.1 PRIM and CART ... 57

4.3.2 Patient Rule Induction Method ... 57

4.3.3 Differences between PRIM and tree induction with CART ... 59

4.3.4 Case study ... 62 4.3.5 Comparison design ... 63 4.3.6 Operational aspects ... 65 4.4. RESULTS ... 68 4.5. DISCUSSION ... 74 4.6. ACKNOWLEDGEMENTS ... 78 4.7. REFERENCES ... 79

CHAPTER 5. CHARACTERIZING DECISION SUPPORT TELEMEDICINE SYSTEMS ... 81

5.1. ABSTRACT... 82 5.1.1 Objectives ... 82 5.1.2 Methods ... 82 5.1.3 Results ... 82 5.1.4 Conclusions ... 82 5.2. INTRODUCTION ... 83 5.3. METHODS ... 84 5.4. RESULTS ... 85 5.4.1 Definition ... 85

5.4.2 The Characterizing Property Set ... 85

5.5. EXAMPLES:PUTTING THE CPS INTO USE ... 87

5.6. DISCUSSION AND CONCLUSION... 89

5.6.1 Future research ... 90

5.7. ACKNOWLEDGEMENTS ... 90

(4)

CHAPTER 6. DECISION SUPPORT TELEMEDICINE SYSTEMS:A CONCEPTUAL MODEL AND

REUSABLE TEMPLATES ... 93

6.1. ABSTRACT... 94

6.1.1 Objective ... 94

6.1.2 Materials and methods ... 94

6.1.3 Results ... 94

6.1.4 Conclusion ... 94

6.2. INTRODUCTION ... 95

6.3. MATERIALS AND METHODS ... 95

6.3.1 Literature search ... 95

6.3.2 Developing a conceptual model and modeling templates ... 96

6.4. RESULTS ... 97

6.4.1 Definitions ... 97

6.4.2 General model ... 98

6.4.3 Templates ... 100

6.4.4 External validation of templates ... 103

6.5. DISCUSSION ... 104

6.6. ACKNOWLEDGEMENTS ... 105

6.7. REFERENCES ... 106

CHAPTER 7. CONCLUSION AND DISCUSSION ... 109

7.1. PRINCIPAL FINDINGS ... 110

7.2. STRENGTHS AND WEAKNESSES OF OUR APPROACH ... 112

7.3. IMPLICATIONS ... 114

7.4. RELATED RESEARCH ... 115

7.5. RECOMMENDATIONS FOR FUTURE RESEARCH ... 117

7.6. CONCLUDING REMARKS ... 117

7.7. REFERENCES ... 118

SUMMARY ... 119

Referenties

GERELATEERDE DOCUMENTEN

“Migration, Remittances, Poverty, and Human Capital: Conceptual and Empirical Challenges.” World Bank Policy Research Working Paper 4272,Washington DC .The

We also show that at Ketambe, orangutan diet composition as measured through time spent feeding on different types of food (fruit, leaves, bark and insects) is not

If you believe that digital publication of certain material infringes any of your rights or (privacy) interests, please let the Library know, stating your reasons.. In case of

It is not permitted to download or to forward/distribute the text or part of it without the consent of the author(s) and/or copyright holder(s), other than for strictly

I perform experiments to understand how orangutans (Pongo pygmaeus, P. abelii, and their interspecific hybrids) react towards novel food, and how their reaction is influenced

We present vegetation data in order to describe the type and intensity of logging in the region, and present and compare data on activity budgets (feeding, moving or resting),

Fruit availability did not influence the percentage of time spent feeding on identical species for either fruits or figs, but a negative relation was found between fig

My main argument is that patrimonial capitalism is not only a result of the top-down activity of the state sovereign, its corrupt agents or cronies in