Biomedical & Health Informatics

The Biomedical & Health Informatics theme has broad application from molecular to population level, focusing on signal processing and statistical machine learning applied in healthcare. There is scope within this theme both for methodological development (e.g. new data analytics and information processing methods e.g. time-series analysis and signal processing, to developing novel machine learning methods which can be generic/validated in clinical datasets), and also applied work focusing on mining (large-scale) clinical datasets.

Translation of the developed approaches into real-world use requires explainable models that can deal with mixed type variables (continuous, ordinal, categorical) present in clinical data, and we would encourage ultimately the development of tools (e.g. embedding models into apps or websites) that can be readily used. PhD students will be uniquely positioned to leverage on accessing large-scale clinical datasets for research via trusted research environments (known as safe havens in Scotland). UoE is uniquely placed to explore translating research outputs and embedding them into clinical practice with NHS/clinical colleagues co-located with academic researchers facilitating inter-disciplinary working in a rich collaborative environment. Example research areas include mining different types of physiological signals such as electrocardiogram, electroencephalogram etc.; mining data from ubiquitous devices such as smartphones and (wearable) sensors for healthcare applications; tracking disease-specific and multi-morbidity trajectories from large scale electronic health records; facilitating diagnosis via designing clinical decision support tools mining multimodal data including self-reports, health records, and assay results; disease risk prediction modeling; and synthetic data generation.

Projects in this theme will address these challenges by developing and applying methods which are directly motivated by the complex medical datasets available within each specific application.