PSD - Dr Eftychia Solea

Causal Machine Learning Methods for Complex Imaging Data

Supervisor: Dr Eftychia Solea and Dr Nicolás Hernández

Project description:

In recent years, advances in technology have enabled the collection of complex, ultra-high-dimensional imaging data in healthcare and biomedical research. Such data offer valuable opportunities to enhance clinical care through improved diagnosis and prognosis. However, there remains a critical need for statistical methods capable of uncovering causal effects. For instance, identifying the causal impact of treatments on imaging outcomes-such as changes in brain activity patterns-is essential for developing more effective and personalised therapies. 

This PhD project will develop a new class of causal machine learning methods for inferring causality from large and complex biomedical imaging data. Specifically, it will: (1) develop a nonparametric doubly robust method for estimating average treatment effects in imaging data; (2) extend this framework using machine learning techniques to address heterogeneity; and (3) leverage the capabilities of neural networks to design causal mediation analysis models for estimating indirect effects when the outcome and/or mediator are images. 

Under the supervision of Drs Solea and Hernandez, the student will develop novel statistical methods and corresponding open-source software, evaluate the proposed approaches through extensive simulation studies, and apply them to publicly available neuroimaging datasets, such as those from the Alzheimer’s Disease Neuroimaging Initiative (ADNI). The goal is to investigate the causal effects of medication use and amyloid beta on the progression of Alzheimer’s disease. The proposed methodological advances will directly support biomedical research by providing innovative statistical tools for uncovering robust causal relationships, ultimately contributing to improved treatment strategies for Alzheimer’s disease and related neurological disorders. 

The PhD project will be based within an excellent research environment at Queen Mary University of London (QMUL). The student will be jointly supervised by Dr. Eftychia Solea, Lecturer in Statistics and Dr. Nicolás Hernández, Lecturer in Statistics. 

The applicant should have a strong background in statistics, machine learning, or a closely related quantitative field. Strong programming skills (e.g., in R or Python) are highly desirable. The ideal candidate will have a keen interest in neural networks, causal inference, and their applications in medical imaging.  

References:

• J. O. Ramsay and B. W. Silverman. Functional data analysis. Springer, New York, 2005. 
• Chernozhukov, V., Chetverikov, D., Demirer, M., Duflo, E., Hansen, C., & Newey, W. (2017). Double/debiased/neyman machine learning of treatment effects. American Economic Review, 107(5), 261-265. 
• Farrell, M. H., Liang, T., & Misra, S. (2021). Deep neural networks for estimation and inference. Econometrica, 89(1), 181-213. 
• Wang, S., & Huang, Y. (2024). DP2LM: leveraging deep learning approach for estimation and hypothesis testing on mediation effects with high-dimensional mediators and complex confounders. Biostatistics, 25(3), 818-832.  
• Zhu, H., Li, T., & Zhao, B. (2023). Statistical learning methods for neuroimaging data analysis with applications. Annual review of biomedical data science, 6(1), 73-104. 

Funding Notes:

Further information: 
How to apply 
Entry requirements 
Fees and funding

PhD Information Session 2026:
On Wednesday 14 January, we will be holding a short information session about PhD studies in Mathematics at QMUL. For full details about the event, please visit: https://www.qmul.ac.uk/maths/postgraduate/postgraduate-research/phd-information-session-2026/

As one of the UK’s most diverse universities, QMUL fosters an inclusive and supportive academic community.

The School of Mathematical Sciences is committed to the equality of opportunities and to advancing women’s careers. As holders of a Bronze Athena SWAN award, we offer family-friendly benefits and support part-time study.