Optimising Cancer follow-up using mathematical models and AI

Erasmus University Rotterdam (EUR); Netherlands; Hybrid; EUR 36,000 - 45,000; Full time

Benefits offered by this job

CAO-NU conditions

Structured training programme

International working environment

Flexible and partly home-based working

Job summary

Erasmus University Rotterdam (EUR) is seeking a PhD candidate to develop and evaluate a mathematical model and algorithm for risk-based follow-up after cancer treatment. The project is a collaboration with Erasmus MC and TU Delft to tailor surveillance to recurrence risk and to translate findings into clinical practice.

You will combine data analysis of cancer registries, participatory design with patients and clinicians, and AI decision-making methods within CAO-NU.

Qualifications

• Demonstrable modelling and algorithmic experience building and running models (e.g., discrete-event or POMDPs).
• Ability to engage credibly with clinicians and patients in research settings.
• Completed (or nearly completed) Master’s degree in relevant field (e.g., econometrics, mathematics, computer/biomedical sciences, AI, OR, data science).
• Solid programming skills in Python and experience analysing patient-level or registry data.
• Affinity with qualitative/participatory methods or willingness to acquire them.
• Excellent command of English; Dutch preferred for focus groups.
• Independence and persistence for four years of doctoral research.

Responsibilities

• Develop and evaluate a mathematical model and algorithm for risk-based follow-up after cancer treatment.
• Use clinical registries data, evidence synthesis and participatory design with patients and clinicians.
• Build AI decision-making components and extrapolate findings to health systems contexts.
• Collaborate with multidisciplinary teams across EUR, TU Delft and Erasmus MC.

Skills

Modelling experience

Python programming

POMDP modelling

Data analysis

Interdisciplinary collaboration

Education

Master’s degree in econometrics/maths/CS/AI/OR

Tools

Python

R

POMDP toolkits

Job description

Organisation/Company Erasmus University Rotterdam (EUR) Research Field Engineering » Biomedical engineering Mathematics » Algorithms Mathematics » Applied mathematics Medical sciences » Medicine Researcher Profile First Stage Researcher (R1) Application Deadline 30 Sep 2026 - 21:59 (UTC) Country Netherlands Type of Contract Temporary Job Status Not Applicable Hours Per Week 38.0 Is the job funded through the EU Research Framework Programme? Not funded by a EU programme Is the Job related to staff position within a Research Infrastructure? No

Offer Description

Erasmus University, TU Delft and Erasmus Medical Centre have established a partnership through interdisciplinary research and education. As part of the work in the alliance, we are looking for a PhD candidate to develop and evaluate a mathematical model and algorithm to better tailor (risk-based) follow-up after cancer treatment. The role is highly impactful for ensuring sustainable cancer care in the future, and we are looking for an exceptional candidate with strong quantitative, and modelling (e.g., POMDP) expertise combined with the interest to work with patients and clinicians on improving cancer care. In the role you will combine data analysis using clinical registries, evidence synthesis, participatory research with patients and clinicians, applied modelling, and development of AI decision-making algorithms to answer a question that health services across Europe are struggling with: how much surveillance is enough, for whom, and delivered by whom?

Background

Follow-up after primary cancer treatment is, in several tumour streams, more intensive than the evidence currently supports. Where the aim is recurrence detection, frequent and intensive surveillance shows limited benefit for clinical outcomes while imposing psychological burden and out-of-pocket costs on patients and consuming scarce professional capacity.

Aim and objectives

The project aims to use modelling to propose risk-based follow-up strategies that match surveillance intensity to individual recurrence risk. It pursues three objectives.

• Optimising follow-up. Determining when, for how long and in what form patients should be seen, and identifying the factors — age, tumour stage, molecular profile, treatment received — on which stratification can be based. Given clinical and molecular characteristics of many tumours, a Partially Observable Markov Decision Process (POMDP) is a preferred approach.
• Defining successful implementation. Engaging patients to understand their concerns and preferences, and assessing the clinical feasibility of alternative follow-up arrangements, including nurse-led, physician-led and online delivery, with attention to professional roles, responsibilities and workload.
• Data and model requirements. Identifying suitable data sources such as the cancer registry, specifying the model along clinical, operational and organisational dimensions through participatory design, and building an extrapolation framework that transfers findings from large datasets to low-volume tumour streams.

Approach

The work combines several strands. A systematic review with LLM-assisted extraction of policy documents updates the international consensus on follow-up and risk stratification. Second, secondary data sources (e.g., cancer registry) will be used to map variation in current practice, estimate (yearly) recurrence incidence, and define the risk factors on which cancer follow-up can be stratified. Focus groups with patients establish what implementation would require of them and focus groups with professionals address feasibility and their own role. These feed a model whose outputs cover capacity and resource use alongside clinical outcomes, with risk factors and organisational constraints — hub-and-spoke versus centralised care, nurse-led delivery — entering as explicit variables.

Colorectal, lung and bladder cancer are the primary candidate tumour streams, with prostate and breast under consideration. Ideally, the project approach and results should be generalisable to other tumour streams.

This project asks two things of you in equal measure: the technical ability to build and run models, and the interpersonal ability to work closely with the patients and clinicians whose care those models describe. Candidates who are strong on only one side will find the project difficult and may not be considered eligible. Specifically, you have:

• demonstrable modelling and algorithmic experience. You have built, programmed and run models yourself — for example discrete-event or capacity models, but specifically POMDPs — and can read and adapt someone else’s model code. You are interested in addressing challenges of scalability, robustness and interpretability in AI decision making. The emphasis in this project is on applying established methods rigorously to a clinical and organisational problem, not on developing new mathematical theory;
• the ability to engage credibly with clinicians and patients. This is the skill we weigh heavily. You can sit in an oncology outpatient clinic and earn the confidence of the professionals working there; you can facilitate a focus group with people living after cancer treatment, with the sensitivity that subject demands; and you can translate technical findings into terms that clinicians, patients and hospital managers can act on. Prior experience in a clinical, patient-facing or participatory research setting is a clear advantage;
• a completed (or nearly completed) Master’s degree in econometrics, mathematics, computer or biomedical sciences, artificial intelligence, operations research, data science, or a related field;
• solid programming skills in Python or a comparable environment, and experience analysing patient-level or registry data;
• affinity with qualitative and participatory methods, or a clear willingness to acquire them: focus groups and participatory design are a substantive part of the project, not an afterthought;
• excellent command of English, written and spoken. Command of Dutch is preferred because we expect focus groups with Dutch patients and professionals form part of the project. Should Dutch not be the preferred language, you are expected to jointly work with Dutch health professionals or students who can moderate these focus groups;
• the independence and persistence that four years of doctoral research require, alongside a genuinely collaborative disposition.

Additional Information

• We offer you an internationally oriented and varied job in an enthusiastic team, with excellent working conditions in accordance with the Collective Labour Agreement for Dutch Universities (CAO-NU).
• A structured training programme through the Erasmus Graduate School of Social Sciences and the Humanities, plus a personal budget for courses, conferences and career development. International candidates are supported in learning Dutch through the university’s language courses.
• Embedding in the EMPOWER strategic alliance (ErasmusMC) on a sustainable healthcare workforce, giving you an interdisciplinary network across research and practice.
• Flexible and partly home-based working arrangements, and an international working environment on the Woudestein campus in Rotterdam.

Everything else we offer you, you can find below!

• Everything you need for a good work-life balance : the option to work from home in consultation with your manager, 41 days of paid leave with a 40 hour contract, 8% holiday pay and an 8.3% end-of-year bonus, and a significant discount on a subscription for our on-campus sports centre !
• Moving to the Netherlands for your job with EUR? Then you may be eligible for the 30%-ruling if you meet the requirements of the Belastingdienst (Dutch tax agency), and with our Dual Career Programme we will also help your partner find the right job for them.

Selection process

Interviews are expected to take place in October 2026. For questions about the position, please contact Professor Maarten IJzerman ([e-mail] ) for general inquiries (ESHPM). For specific questions please contact Dirk Grunhagen ([e-mail] - Oncologic Surgeon) about the clinical component, Matthijs Spaan ([e-mail] -TUDelft EEMCS, Intelligent Systems department) about mathematical modelling, or Yiannis Kyratsis ([e-mail] - ESHPM) about organisational, workforce and participatory research. You can find more information about the EUR on our website www.eur.nl .

We look forward to receiving your application.

Persons of all gender identities or expressions, sexual orientations, religions, ethnicities, ages, neurodiversities, functional impairments, citizenships, or any other aspect are welcome to apply and join the EUR community.

Additional comments

The (preferred) start date of this position is 1 December 2026 and you will be based at Campus Woudestein in Erasmus School of Health Policy & Management (ESHPM). This position is for 1 fte. The salary ranges from a minimum of € 3.204 to a maximum of € 4.051 gross per month Scale PhD on a fulltime basis (38 hours), in accordance with the CAO-NU. The initial contract runs for 18 months and is extended for the remaining period following a positive evaluation.