Multimodal Virtual Patients for In-Silico Decision Making

The central research question is: how can machine-learning models generate coherent multimodal virtual patients from incomplete observations while representing uncertainty about unobserved patient characteristics? The project will develop probabilistic multimodal generative models that learn patient representations from heterogeneous and partially observed data. It will address three connected challenges: preserving clinically meaningful dependencies across modalities; generating distributions of plausible patient states when information is missing; and quantifying how uncertainty in these generated states affects downstream simulation and decision making.

A key methodological contribution will be to connect generative quality with decision validity. Conventional synthetic-data evaluation typically asks whether generated samples resemble observed data. For in-silico trials, this is not sufficient. The project will assess whether virtual populations preserve realistic marginal distributions and clinically meaningful cross-modal relationships, and whether conclusions from downstream simulations remain robust to uncertainty in the generated population. The aim is therefore not simply to generate realistic synthetic patients, but to establish when a generated population is sufficiently coherent and reliable to support decision making.

Initial work will focus on a tractable combination of cardiac imaging-derived phenotypes or representations, ECG information, biomarkers and structured clinical variables, rather than attempting to generate all raw medical modalities. UK Biobank provides a suitable multimodal cardiovascular setting, subject to data access [1]. Existing physiological and virtual-patient simulation workflows at Manchester will be used for downstream evaluation, allowing the PhD to focus on the core machine-learning questions rather than developing simulation infrastructure from scratch.

Desirable Student Background:

The project would suit a candidate with a strong background in machine learning, mathematics, statistics, computer vision or a closely related discipline, ideally with experience in generative modelling, probabilistic modelling, representation learning, geometric/deep learning or medical image analysis. Mathematical maturity will be particularly valuable because the project will require reasoning about probability distributions over structured spatiotemporal objects, latent-variable identifiability, uncertainty, conditional generation and statistical validation.

How to apply:

Please apply under the University of Manchester application portal and select 'PhD in Artificial Intelligence'.

When applying, you’ll need to specify the full name of this project, the name of your supervisor, if you already having funding or if you wish to be considered for available funding through the university, details of your previous study, and names and contact details of two referees.

Your application will not be processed without all of the required documents submitted at the time of application, and we cannot accept responsibility for late or missed deadlines. Incomplete applications will not be considered.

You will be asked to upload the following supporting documents:

• Final Transcript and certificates of all awarded university level qualifications
• Interim Transcript of any university level qualifications in progress
• CV
• Supporting statement: A one or two page statement outlining your motivation to pursue postgraduate research and why you want to undertake postgraduate research at Manchester, any relevant research or work experience, the key findings of your previous research experience, and techniques and skills you’ve developed. (This is mandatory for all applicants and the application will be put on hold without it).
• Contact details for two referees (Please ensure referee email addresses are official university or workplace accounts, as we may need to verify the references.)
• English Language Certificate (if applicable)

We actively encourage applicants from diverse career paths and backgrounds and from all sections of the community, regardless of age, disability, ethnicity, gender, gender expression, sexual orientation and transgender status.

We also support applications from those returning from a career break or other roles. We are dedicated to supporting work-life balance and offer flexible working arrangements to accommodate individual needs. Our selection process is free from bias, and we are committed to ensuring fair and equal opportunities for all applicants.

We are dedicated to supporting work-life balance and offer flexible working arrangements to accommodate individual needs, including a part-time study option.

Join us and help grow the UK’s national capability in artificial intelligence, part of the UK’s modern industrial strategy. Everyone is welcome if you are passionate about uncertainty quantification, decision making with humans in the loop and decision making for machine learning systems and their applications in Science and Engineering, and looking to develop your research and innovation skills at the doctoral level to further your career in the AI sector.

Equality, diversity and inclusion is fundamental to the success of The University of Manchester, and is at the heart of all of our activities. We know that diversity strengthens our research community, leading to enhanced research creativity, productivity and quality, and societal and economic impact. (Equality, diversity and inclusion | The University of Manchester)

We actively encourage applicants from diverse career paths and backgrounds and from all sections of the community, regardless of age, disability, ethnicity, gender, gender expression, sexual orientation and transgender status.

Funding Notes

Fully funded AI UKRI CDT 4 year program; The Project will be based in University of Manchester.

The UKRI AI CDT in Decision Making for Complex Systems is part of the TechFirst offering stipends of £30,000 for students eligible for home fee status. The start date is September 2027.

References

1. Multimodal Cardio-Neuro Modelling: Integrating EGG, Imaging and Structured Data with AI to Predict Major Outcomes. https://www.ukbiobank.ac.uk/projects/multimodal-cardio-neuro-modelling-integrating-ecg-imaging-and-structured-data-with-ai-to-predict-major-outcomes/
2. Mbacke, S. D. & Rivasplata, O. A Note on the Convergence of Denoising Diffusion Probabilistic Models. TMLR, 2024. https://openreview.net/forum?id=wLe1bG93yc
3. Casado-Telletxea, I & Rivasplata, O. Error Bounds for a Diffusion Model-Based Drift Estimator. Under review. https://arxiv.org/abs/2606.02115
4. Niu, S. et al. EHR-KnowGen: Knowledge-enhanced multimodal learning for disease diagnosis generation. Information Fusion, 2024.
5. Yu, J. et al. Robust Polyp Detection and Diagnosis Through Compositional Prompt-Guided Diffusion Models. IEEE TMI, 2025.