Digital Health covers a wide range of research at the Institute of Biomedical Engineering. It focuses mostly on “AI in healthcare”, sometimes known as Clinical AI, at the interface between machine learning and health informatics, but also on the use of wearables and video cameras to acquire vital-sign data.
The Computational Health Informatics (CHI) Lab shares a common interest in deep learning, Bayesian inference, and related methods. It has access to some of the world’s largest, curated, anonymised healthcare datasets, and includes work with wearables and hospital data, across scales from the massively multivariate (including anonymised genomics) to the high-rate data acquired from medical devices. The systems developed are routinely used in the care of patients within the UK National Health Service, and for improving access to healthcare in low- and middle-income countries (LMICs).
The AI for Digital Health (AI4DH) lab develops novel machine learning methods to advance personalised healthcare and clinical decision-making. The lab specialises in representation learning, foundation and generative models for complex medical time-series, spanning longitudinal electronic health records and wearable biosignals. Its research integrates causal inference, probabilistic modelling and reinforcement learning to understand disease progression, discover patient subtypes, estimate individualised treatment effects and optimise dynamic treatment strategies. A particular emphasis is placed on addressing real-world challenges, including multimorbidity, irregular and incomplete clinical data, and data scarcity in rare conditions through transfer learning and domain adaptation. By advancing explainable, robust and uncertainty-aware AI, the lab aims to develop trustworthy models that support clinical decision-making and improve healthcare accessibility across diverse populations and resource-constrained settings.
The Biomedical Signal Processing & Machine Learning (BSP-ML) research group aims to deliver patient care agnostic to patient location, through state-of-the art monitoring technology and algorithms, together with alerting systems appropriate to the patient environment, in collaboration with the Critical Care Research Group led by Professor Peter Watkinson. The group’s recent focus has been on adapting the technology, apps and machine learning algorithms developed in the last decade for the fight against COVID-19, through remote patient monitoring, better patient stratification and improved diagnostics.
Clinical collaboration is at the heart of all projects in the Digital Health research area, with biomedical engineers working alongside clinical colleagues, which ensures that each project feeds directly into the care of patients in hospitals or at home.
