Skip to content

Analysis of quantum bayesian networks under a real-world medical decision problem

Study level


Vacation research experience scheme

Faculty/Lead unit

Science and Engineering Faculty

School of Information Systems

Topic status

We're looking for students to study this topic.


Dr Catarina Pinto Moreira
Lecturer in Information Science
Division / Faculty
Science and Engineering Faculty


Probabilistic graphical models, such as Bayesian Networks, are one of the most powerful structures known by the Computer Science community for deriving inferences based on probability.

However, modern cognitive psychology has revealed that human decisions could not follow the rules of classical probability theory because humans cannot process large amounts of data in order to make judgements. Consequently, the inferences performed are based on limited data coupled with several heuristics, leading to violations of the law of total probability. This means that probabilistic graphical models based on classical probability theory are too limited to fully simulate and explain various aspects of human cognition decision-making.

Quantum cognition emerged as a research field that attempts to model human cognition and build more general decision-making models by using the mathematical concepts of quantum mechanics.

For the purposes of this project, we want to take a pioneering step forward by investigating the potential of quantum models in real world medical decision scenarios. More specifically, we want to analyse data from patients with cancer at the gynaecology department at a hospital in the Netherlands.

One main concern for doctors the speed of the right diagnosis as cancer is hard to detect in the early stages. In this work, we plan to explore the possibilities of applying quantum models and interference effects to try to reduce this search space and support doctors in their decisions.

Research activities

As part of the research project, you will be involved in:

  • processing and organising a large-scale dataset
  • modelling the business processes involved for each type of cancer
  • apply a Quantum-Like Bayesian Network and compare its performance with its classical counterpart
  • perform a statistical evaluation of both models.


At the end of the project, we expect to have achieved the following:

  • summarised the business processes involved in each type of cancer present in the dataset
  • a simplified business process that can lead to a higher speed of diagnosis or the reduction of tasks that are just time consuming and costly.
  • evaluation on the performance of the Quantum-Like Bayesian Networks vs Classical Bayesian Networks
  • a submitted journal article with these findings.

Skills and experience

To be considered for this project, you should have the following skills and/or experiences:

  • data manipulation, representation and visualisation
  • probabilistic models, such as inference in Bayesian Networks
  • linear algebra and complex numbers
  • programming skills for data manipulation (Python / Java) and for calculus (MATLAB).



Contact the supervisor for more information.