Large language models (LLMs) offer new opportunities to extract valuable information from unstructured healthcare data. At the same time, their use in healthcare raises important questions about privacy, transparency, reliability and responsible AI. In this master’s thesis, conducted in collaboration with Radboud University, you will investigate what is needed to use AI responsibly within pharmacovigilance and translate these insights into a practical framework for Lareb.

This master's thesis project is part of a larger case study (with three students) in the ELSA Lab for Decision Support in collaboration with the Netherlands Comprehensive Cancer Organisation (IKNL) and Lareb. IKNL is the national organisation that provides open access to high-quality cancer data. Lareb is the Dutch national pharmacovigilance centre and is responsible for collecting, assessing, and communicating information about the safety of medicines and vaccines. This particular thesis project is partially hosted at Lareb and focuses on the safe and responsible use of LLMs in pharmacovigilance.

For shared decision-making about personalized care, it is important to consider not only purely clinical outcomes, such as expected survival rate, but also quality-of-life (QoL) aspects, such as experienced pain, mobility, or nausea. However high-quality QoL data is not easy to obtain and often requires patients to fill in questionnaires in the last phase of their life. However, there is an abundance of information in the free-text forms of Electronic Health Records, for example, nurse reports that - combined with information about medication - can indicate a relationship between the start of a new medication regimen and increased side effects: “I feel worse today than yesterday”. This information is in natural language, uses synonyms and is often incomplete, making it difficult to use; this is where large language models (LLMs) may be useful. As healthcare is a high-risk AI application area, quality control over the procedure of constructing decision support tools and the underlying models is crucial, as are absolute guarantees about privacy and transparency regarding the source and development of the LLMs.

The Assignment

You will analyse relevant guidelines and regulations for AI in healthcare and translate these into the Lareb context. Through interviews with internal and external stakeholders, you will investigate how AI is perceived and what conditions are required for its responsible use. Based on this, you will develop a practical framework to assess and justify AI applications within Lareb. This framework will support transparency towards external stakeholders. If feasible, you will begin implementing measures tot address gaps identified using the framework. You will work at the intersection of data science, healthcare and governance. In doing so, you contribute to the responsible use of AI in drug safety.

About Info Support

Info Support specializes in custom software, data/AI solutions, management, and training and is active in the Finance, Industry, Agriculture, Food & Retail, Mobility & Public, and Healthcare sectors. We provide solid and innovative solutions for complex and critical software issues. Our headquarters are located in Veenendaal (NL) and Mechelen (BE). At present, approximately 500 employees are employed by Info Support.

Info Support's working method is characterized by a number of core values: solidity, integrity, craftsmanship, and passion. These core values are intertwined in our work and the way we interact with each other.

To ensure that all employees are always up to date with the latest developments, Info Support has an in-house IT Academy that eagerly satisfies the hunger for more or different knowledge and skills.

B2 language proficiency in Dutch is required.