Effective use of diagnostics - application of machine learning solutions in clinical practice

Aug 2, 2026

This PhD thesis investigates how diagnostic stewardship can be strengthened in clinical practice by applying machine learning solutions. The research focuses on reducing inappropriate laboratory and culture testing through implementation of minimum retest intervals, validation and prospective evaluation of prediction tools, and de-implementation strategies. It also evaluates barriers and facilitators for adopting artificial intelligence in healthcare, covering studies from hospital settings to emergency departments and proposing approaches for optimizing blood and urine culture use, including study protocols for controlled trials.

LanguageEnglish

CategoryResearch & Report

FormatPDF

Pages224

Reading Time9 h 24 min

AccessFree to download

General introduction and outline of the thesis

The usefulness of implementing minimum retest intervals in reducing inappropriate laboratory test requests in a Dutch hospital

The long-term sustainability of a successful de-implementation strategy reducing inappropriate laboratory testing: a retrospective multicenter mixed-method study

Using machine learning to predict blood culture outcomes in the emergency department: a single-centre, retrospective, observational study

Diagnostic stewardship for blood cultures in the emergency department: a multicenter validation and prospective evaluation of a machine learning prediction tool

Implementing artificial intelligence in clinical practice: a mixed-method study of barriers and facilitators

Appropriate use of blood cultures in the emergency department through machine learning (ABC): study protocol for a randomised controlled non-inferiority trial

Predicting urine culture outcomes in adult patients using machine learning with the aim of reducing unnecessary urine cultures

Summary and general discussion

Appendices

PhD portfolio

List of publications

Dankwoord

About the author

VU Research Portal Effective use of diagnostics Boerman, Anneroos Willemijn 2025 DOI (link to publisher) 10.5463/thesis.1108 document version Publisher's PDF, also known as Version of record Link to publication in VU Research Portal citation for published version (APA) Boerman, A. W. (2025) . Effective use of diagnostics: application of machine learning solutions in clinical practice. [PhD-Thesis-Research and graduation internal, Vrije Universiteit Amsterdam] . [https://doi.org/10.5463/thesis.1108](https://doi.org/10.5463/thesis.1108) General rights Copyright and moral rights for the publications made accessible in the public portal are retained by the authors and/or other copyright owners and it is a condition of accessing publications that users recognise and abide by the legal requirements associated with these rights. • Users may download and print one copy of any publication from the public portal for the purpose of private study or research. • You may not further distribute the material or use it for any profit-making activity or commercial gain • You may freely distribute the URL identifying the publication in the public portal Take down policy If you believe that this document breaches copyright please contact us providing details, and we will remove access to the work immediately and investigate your claim. E-mail address: [vuresearchportal.ub@vu.nl](vuresearchportal.ub@vu.nl) [Download date: 30](Download date: 30) . Sep. 2025 (΍HFWLYH XVH RI GLDJQRVWLFV Application of machine learning solutions in clinical practice A.W. (Roos) Boerman &RORIRQ Copyright 2025 © A.W. Boerman All rights reserved. No parts of this thesis may be reproduced, stored, or transmitted, in any form or by any means, without prior permission of the author, or when applicable, RI WKH SXEOLVKHUV RI WKH VFLHQWLȴF SDSHUV􀀑 Provided by thesis specialist Ridderprint, [ridderprint.nl](ridderprint.nl)[ ](ridderprint.nl)Printing: Ridderprint Cover Design: Nicoline Frederique, Atelier Ink Amsterdam, [www.ink-amsterdam.nl](www.ink-amsterdam.nl)[ ](www.ink-amsterdam.nl)[Layout: Robin Weijland](Layout: Robin Weijland), persoonlijkproefschrift.nl ISBN: 978-94-6522-147-2 VRIJE UNIVERSITEIT ())(&7Ζ9( 86( 2) 'Ζ$*1267Ζ&6 Application of machine learning solutions in clinical practice ACADEMISCH PROEFSCHRIFT ter verkrijging van de graad Doctor aande Vrije Universiteit Amsterdam, RS JH]DJ YDQ GH UHFWRU PDJQLȴFXV prof.dr. J.J.G. Geurts, volgens besluit van de decaan van de Faculteit der Geneeskundein het openbaar te verdedigen op vrijdag 23 mei 2025 om 13.45 uur in de universiteit door Anneroos Willemijn Boerman geboren te Utrecht promotoren: prof.dr. R. deJonge prof.dr. K. D. P.W. B. Nanayakkara promotiecommissie: prof.dr. T. H. Muller prof.dr. W.W. van Solinge prof.dr. M. van Vugt prof.dr. S. Repping prof.dr. S.C. E. Klein Nagelvoort-Schuit dr. S.A. Nurmohamed 7DEOH RI FRQWHQWV &KDSWHU 􀀔 General introduction and outline of the thesis 7 &KDSWHU 􀀕 The usefulness of implementing minimum retest intervals in 17 reducing inappropriate laboratory test requests in a Dutch hospital &KDSWHU 􀀖 The long-term sustainability of a successful de-implementation 31 strategy reducing inappropriate laboratory testing: a retrospective multicenter mixed-method study &KDSWHU 􀀗 Using machine learning to predict blood culture outcomes in 65 the emergency department: a single-centre, retrospective, observational study &KDSWHU 􀀘 Diagnostic stewardship for blood cultures in the emergency 89 department: a multicenter validation and prospective evaluation of a machine learning prediction tool &KDSWHU 􀀙 ΖPSOHPHQWLQJ DUWLȴFLDO LQWHOOLJHQFH LQ FOLQLFDO SUDFWLFH􀀝 D PL[HG􀀐 125 method study of barriers and facilitators &KDSWHU 􀀚 Appropriate use of blood cultures in the emergency department 147 through machine learning (ABC): study protocol for a randomised controlled non-inferiority trial &KDSWH

FAQs

What problem does the thesis address in diagnostic testing?

The thesis addresses inappropriate laboratory testing and focuses on strategies to reduce unnecessary diagnostic tests in clinical settings.

How does the thesis use machine learning in clinical practice?

It applies machine learning to predict outcomes for blood cultures and urine cultures and evaluates tools through validation and prospective evaluation studies.

What additional strategies are studied beyond predictive models?

The thesis also examines minimum retest intervals, de-implementation strategies, and the practical implementation of artificial intelligence by studying barriers and facilitators.

Aug 2, 2026

Upload by Clementine