Creating Explainable AI for Health with Confidence University of Southampton in United Kingdom

This PhD project, supervised by Professor Gabriela Czanner, aims to develop advanced machine learning methods to transform heterogeneous, routinely collected medical data into explainable, uncertainty-aware insights for healthcare decision-making. The research will combine multimodal data, longitudinal modelling, and personalised uncertainty quantification to address critical challenges in digital health, such as improving disease prediction, monitoring, and communicating confidence in clinical decisions.

Medical data are often recorded irregularly and in various formats, including numerical measurements and medical images. The project will tackle issues of data quality, heterogeneity, and personalisation, proposing methods at the intersection of deep neural networks and longitudinal predictive modelling. The goal is to create automated monitoring systems that are explainable, robust, and capable of expressing their own confidence, thus supporting more accurate and user-centred health decision-making.

Research directions include multimodal machine learning, image processing, information-theoretic approaches to uncertainty quantification, communication of uncertainty to users, explainable AI, and active learning. The project offers opportunities to collaborate with a multidisciplinary team in digital healthcare, biomedical engineering, and the Faculty of Medicine at the University of Southampton. Candidates will contribute to high-impact journals and conferences and have access to high-performance computing resources.

The School of Electronics and Computer Science at the University of Southampton is ranked 1st in the UK for Electrical and Electronic Engineering and is among the top 1% of universities worldwide. The university is committed to equality, diversity, and sustainability, offering generous maternity policies, onsite childcare, and a range of benefits to support well-being and work-life balance.

Entry requirements include a UK 2:1 honours degree or its international equivalent in computer science, data science, or a closely related discipline. Applicants must have strong programming skills in Python and machine learning, and a keen interest in the intersection of machine learning, dataset simulation, and mathematical statistics. Applications should include a research proposal, CV, two reference letters, degree transcripts/certificates, and proof of English language qualification if applicable.

Funding is available for both UK and international students, including bursaries and scholarships. Funding will be awarded on a rolling basis, so early application is encouraged. The application deadline is August 31, 2026, but positions may be filled earlier as suitable candidates are identified.

To apply, visit the University of Southampton postgraduate application portal, select 'PhD Computer Science (Full time)' under the Faculty of Engineering and Physical Sciences, and include the supervisor's name in Section 2 of the application form. For further information, contact [email protected].