1. Latest articles

The latest scientific publications of our department with a short summary.

Implementing Findable, Accessible, Interoperable, Reusable (FAIR) Principles in Child and Adolescent Mental Health Research: Mixed Methods Approach

This study identified barriers to implementing the FAIR (Findable, Accessible, Interoperable, Reusable) principles in child and adolescent mental health research.

A total of 45 barriers were identified, including those related to organizational policies and software. Key recommendations include adding a FAIR data steward to the research team, providing accessible guides, and ensuring sustainable funding to overcome these barriers, ultimately enhancing data reusability.

 Rowdy de Groot, et el DOI: 10.2196/59113

Unmasking the chameleons: A benchmark for out-of-distribution detection in medical tabular data

Machine learning models often struggle to generalize to data distributions that differ from their training dataset, known as "out-of-distribution" (OOD) data. It is important to detect OOD because prediction on such data can be unreliable.

While OOD detection methods have been explored in various fields, their effectiveness for medical data remains unclear. This study aims to evaluate and compare different OOD detection methods in the context of medical tabular data.

 The visual summary and interview with Giovanni Cina explains OOD.

 Mohammad Azizmalayeri, et al DOI:10.1016/j,ijmedinf.2024.105762

ATC-to-RxNorm mappings - A comparison between OHDSI Standardized Vocabularies and UMLS Metathesaurus

This study evaluates the completeness of mappings from 5th-level (most fine-grained level, the chemical substance) Anatomical Therapeutic Chemical (ATC) classification classes to RxNorm ingredient concepts in two vocabulary repositories, OHDSI Standardized Vocabularies (OSV) and Unified Medical Language System (UMLS) Metathesaurus. The results show that OSV provides more mappings and is therefore recommended over UMLS, though UMLS may perform better in concrete applications.

 Rowdy de Groot, et el DOI: 10.1016/j.ijmedinf.2024.105777

Linking theory and practice to advance sustainable healthcare: the development of maturity model version 1.0

Sustainability is playing an increasingly important role in healthcare organizations, but improving the environmental impact in healthcare remains a challenge. The aim of this research is to develop a model that allows healthcare professionals to assess and improve the sustainability performance of their organization or department. Do you want to learn more? Click here for more information.

Marieke Sijm et al

    Comparing causal random forest and linear regression to estimate the independent association of organisational factors with ICU efficiency

    This study looked at two different methods to measure the effect of organizational factors on ICU performance in Brazil and Uruguay. The used methods were causal random forest and linear regression modelling. Both methods found that the number of nurses per ten beds improved ICU efficiency. Causal random forest was able to spot areas where overall results might not seem significant. This approach could help hospital managers to improve ICU efficiency.

    Ferishta Raiez, et el. DOI: 10.1016/j.ijmedinf.2024.105568


    2. PhD theses

    The latest PhD theses of our department.


    3. Research in the spotlight

    Researchers of our department in the spotlight! With a visual summary and a short interview. Curious? Click on the figures to find out more.

    Digital tools in cancer screening

    Interview with Corine Oldhoff-Nuijsink, researcher on Human Factors Engineering.

    Federated learning in the healthcare setting

    Interview with Sebastian van der Voort, researcher on Quality of care (IT systems), Methods in Medical Informatics and Reusable Health Data

    Detecting unreliable predictions of ML models

    Interview with Giovanni Cinà, researcher on Methods in Medical Informatics

    Making medical terms patient-friendly

    Interview with Hugo van Mens, researcher on Reusable Health Data


    4. Broodje MedInfo (Sandwich MedInfo)

    🍞 Are you interested in or working on a data-driven (research) project in healthcare? And would you like to know more about best practices for your project? Then broodje MedInfo is for you!

    This online event includes research results, tips for your own data project and time for questions. Below, you can find the recordings of previous editions on FAIR, LLMs, Audit & Feedback and Usability.

    Usable computer systems

    In this edition, Linda Dusseljee-Peute spoke about usable computer systems (e.g. apps, decision support systems, and electronic health records), human-computer interaction, design and the currently available evidence.

    Slides: Broodje MedInfo Usable computer systems

    Quality registrations and Audit & Feedback

    Nicolette de Keizer and Ferishta Bakhshi-Raiez presented, in Dutch, results of continuous improvement using a quality registration in specialist medical care and the implications of a new Dutch law.

    Slides: Broodje MedInfo Quality registrations


    LLMs

    Iacer Coimbra Alves Cavalcanti Calixto presented, in English, the opportunities and challenges of Large Language Models in healthcare. Including patient privacy, model interpretability, and reducing administrative burden.

    Slides: Broodje MedInfo LLMs

    FAIR

    Ronald Cornet presented in the first edition, in Dutch, the importance of the FAIR (Findable, Accessible, Interoperable, Reusable) Principles and how you can apply them in projects. Look here for the tips from the Q&A.

    Slides: Broodje MedInfo FAIR


    5. Podcast Health Informatics (in Dutch)

    All podcasts


    6. Technical reports

    Check here for all our technical reports!