Dear Leiden University-only students, below you can read about the open thesis positions at TDS Lab for 2026-2027. More topics on these research fields are available as well. Contact me if you are interested in one of these Master's Thesis Research Projects. Cheers, Marco
Open thesis projects @TDS Lab
[DL] Classifying physical neighbourhouds for health impact measurement from satellite and streetview data
The correlation between health and the physical urban or rural environment remains a challenge. How do we link statistical data to the physical, built environment? How can we categorise neighbourhoods? This thesis project is part of the national ECOTIP project where we focus on identifying crucial moments when shortages of green, healthy food and clean air in neighbourhoods affect health. It is particularly the less affluent population groups that often develop lifestyle-related diseases, such as obesity, diabetes, cardiovascular diseases, mental and lung problems. At the same time, these population groups often have an unfavourable physical living environment: a lack of nature, an unhealthy food supply, air pollution and noise pollution in their neighbourhood. All these factors can affect people's healthy lifestyle. ECOTIP aims to reduce these health differences in the Netherlands.
Your task is to employ the wealth of publicly available data on the built environment, such as Google Maps, Google Earth, other satellite imagery and aerial photographs, Street View, and social media, to uncover any correlations between particular types of health indicators and the physical form of neighbourhoods where these indicators apply. For example, extract and correlate variables such as street pattern (the type of network), street width, building height, continuous development (street walls) or detached buildings (towers, apartment blocks, villas), squares, green spaces, and mobility patterns, to categorise the physical appearance of neighbourhoods based on their likely health impact.
Supervisors: Marcel Haas, Hielke Muizelaar (LUMC), Marco Spruit[LLM] Synthetic clinical notes generation in EHRs
LLMs are great in generating well-formed sentences. However, this is not desirable when we want to synthetise clinical texts that actual doctors would write: They use acronyms a lot, merely write down key phrases, some spelling errors, etc. What we want is (1) a LLM-based generator for clinical texts that produces human-like texts (2) synchronised with the tabular patient summary data. (3) It should become a module in SynthyVerse: https://synthyverse.readthedocs.io/. Inspiration can be found in https://github.com/qforge-dev/torque among others.
Daily supervisors: Marco Spruit and others[ML] Finding the relevant differences in differences
In the evaluation of healthcare interventions, Difference-in-Differences is a very common quasi-experimental method. It aims to quantify health or financial benefit of an intervention by looking at the change in an outcome measure before and after the intervention for both a treatment and control group. The assumption is that, even though treatment and control group are not random selections from the same population, the outcome measure as a function of time behaves very similar in both groups (the so-called parallel-trend-assumption), such that a change in the difference between the two groups can be attributed to the intervention. In the common implementations, there are many assumptions that need to hold (parallel trends, no uncertainty on the data, and often even linear time dependence of the outcome), and the diff-in-diff to be measured is assumed to be a constant off-set due to the intervention. The real world is more complicated than that. In this project we will build Bayesian Generative Models that relax the assumptions and that can measure differences that do not necessarily manifest as a "jump" in the outcome, but can also be differences of the time derivative or other changes in the behavior of outcome variables. We will develop the method in controlled experiments, and verify the value and power of such models on real-world use-cases that previously have been reported using the traditional methodology.
Daily supervisors: Marcel Haas (LUMC), Marco Spruit
NB: A selection of former thesis topics can be found here.