PhD Candidate: AI-Driven, Risk-Based Cancer Follow-Up

Medical Delta Living Lab Better In Better Out; Baxter (TN); On-site; USD 41,000 - 52,000; Full time

Benefits offered by this job

Research environment

Interdisciplinary collaboration

Job summary

Erasmus University, together with TU Delft and Erasmus Medical Centre, invites applications for a PhD candidate to design and evaluate a risk-based follow-up model for cancer care. The role blends data analysis, participatory design with patients and clinicians, and the development of AI-assisted decision tools to optimize surveillance strategies.

The project aims to tail surveillance intensity to individual recurrence risk, with rigorous modelling and pathway feasibility assessments across

Qualifications

• PhD candidate to develop and evaluate a mathematical model and algorithm for risk-based follow-up after cancer treatment.
• Strong quantitative and modelling expertise and willingness to work with patients and clinicians.
• Experience with data analysis from clinical registries and applied modelling.

Responsibilities

• Develop and evaluate a mathematical model and algorithm for risk-based follow-up.
• Analyse data from clinical registries and perform evidence synthesis.
• Engage patients and clinicians in participatory research and implement AI decision-making components.
• Collaborate across European partners to transfer findings to health services.

Skills

Quantitative analysis

Modelling (POMDP)

Data analysis

Interdisciplinary collaboration

Education

PhD in a relevant field (cancer modelling/OR/CS)

Tools

POMDP modelling

Python

R

AI concepts

Job description

Erasmus University, together with TU Delft and Erasmus Medical Centre, invites applications for a PhD candidate to design and evaluate a risk-based follow-up model for cancer care. The role blends data analysis, participatory design with patients and clinicians, and the development of AI-assisted decision tools to optimize surveillance strategies.

The project aims to tail surveillance intensity to individual recurrence risk, with rigorous modelling and pathway feasibility assessments across