Sorry! De informatie die je zoekt, is enkel beschikbaar in het Engels.
This programme is saved in My Study Choice.
Something went wrong with processing the request.
Something went wrong with processing the request.

Dynamic standardisation of experience-based knowledge and values in guidelines

How can AI-based methods innovate the inclusion of citizens’, patients’ and health professionals’ experiences and value judgements in vaccination guideline development?

The inclusion of more diverse knowledge can lead to more suitable, helpful and robust clinical practice guidelines. This holds the potential to improve health care practice as more practical and usable recommendations can be made that meet the needs and experiences of patients and professionals.

Originally, the evidence-based medicine (EBM) model envisaged drawing on evidence from 1) the best available clinical research, 2) individual clinical expertise, and 3) patient values and preferences. In practice, however, evidence from the former, mainly from systematic reviews and randomised control trials (RCT) has been established over time as the predominant source of knowledge – as the “gold standard”. If other knowledge about, for example, patient values is available – usually based on a limited number of interviews or observations – it is often difficult to integrate with the quantitative evidence from (meta-reviews of) RCTs. Despite the great and undeniable importance of incorporating the knowledge and values of patients and professionals, this remains a major challenge for guideline development, especially for vaccination guidelines.

The objective of this project is to improve and accelerate the integration of citizens', patient’s and health professionals' experience-based knowledge and value considerations into infectious disease prevention guidelines by applying automated text analytics to rich but untapped data sources.

New computational methods and the availability of large amounts of data open up new opportunities for the endeavour of this project. For the first time, experiential knowledge and value judgements could be extracted and analysed on a large scale, systematically and potentially in an automated way, alongside the process of guideline development and appraisal of new information. AI-based methods together with interactive research methods may thus enable a more adaptive approach to incorporate experience and value judgements into guideline development.

We mobilise AI-methods particularly from the field of natural language processing (NLP) to extract and analyse existing but unexplored sets of textual records where societal and professional knowledge and concerns are expressed, such as databases from the National Institute for Public Health and the Environment (RIVM) as well as various social media platforms.

Subsequently, the gathered knowledge will be integrated into the development of vaccination guidelines through close cooperation with the guideline development group. In particular, our analysis will feed into the development of the COVID-19 vaccination guideline in the Netherlands. Moreover, we explore the value and applicability of this method in two other guideline revision cases: the revision of the Scabies guideline and the one for Transgender care.

Athena’s role
This is a joint project between the Athena Institute and the Social AI department of the Vrije Universiteit Amsterdam (VU) and the National Coordination Centre for Communicable Disease Control (LCI) of the RIVM (National Institute for Public Health and the Environment).

Athena team members Lea Lösch, Aura Timen and Teun Zuiderent-Jerak discuss ways to integrate the voice of citizens into vaccination guidelines in a Dutch blog published by ZonMw. By Marieke Stegenga from ZonMw (2022) Ervaringskennis en waarden van burgers en professionals integreren in vaccinatierichtlijnen.

The methodology used in the Evidence in Action project and how to implement it in practice is explained step-by-step in A practical guide – Incorporating Stakeholders' Experiences in Guideline Development Through Natural Language Processing (NLP) Analysis. By Lea Lösch et. al (2024). 


Project details