Digital Health

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 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.

Our on-going projects in acute care, in collaboration with world-leading intensive care clinicians at Oxford University Hospitals, aim to produce predictive AI-based systems using the huge quantities of data now routinely collected for each patient.
Acute and Critical Care

Major CHI Lab projects focus on the development of AI-based systems to exploit rich clinical datasets, with the goal of improving the understand and treatment of complex diseases. The Oxford University Hospitals and wider collaborations provide very great opportunities to develop new AI methods for diseases that often include both genomic and clinical data.
Complex Disease

We use machine learning to greatly improve our ability to identify and fight outbreaks of infectious disease - including the COVID-19 pandemic of 2020 - using AI-based systems. This theme of research collaborates closely with Public Health England (the UK's Centre for Disease Control or CDC), experts in microbiology from Oxford University Hospitals, and a global network of CDCs from some of the world's largest countries.
Infectious Disease

This theme includes a number of initiatives that seek to improve access to healthcare in low- and middle-income countries (LMICs). Using AI-based algorithms within smartphones and wearables, we are able to use inexpensive sensors that are appropriate for use at scale in LMICs. The delivery of healthcare in such settings is often performed by healthcare workers without high levels of clinical training, and so there is therefore a need for the decision-support capabilities of such algorithms.
Low and Middle-Income Settings

The BSP-ML group is a world leader for non-contact physiological monitoring in healthcare settings using video cameras, both in the visible and infra-red. In response to the COVID-19 pandemic, we implemented real-time versions of our algorithms for estimation of pulse rate and breathing rate using the webcams in smartphones, for both iPhones and Android phones.
Non-Contact Vital Sign Monitoring

The Screening for Hypertension in the INpatient Environment (SHINE) system has been developed to detect those individuals at risk of undiagnosed hypertension whilst they are in hospital (around 14% of patients), with the aim of enabling its management to be undertaken in the patient’s home after discharge from the hospital.
Remote Monitoring in the Home

In collaboration with the Nuffield Department of Women's & Reproductive Health (Dr Lucy Mackillop), we have developed a gestational diabetes self-management smartphone app (GDm-Health™) linked to a Bluetooth-enabled blood glucose meter. The patient tags the blood glucose readings (fasting, pre-prandial and post-prandial) and enters her insulin dose (if appropriate). Feedback is provided in the form of summaries of blood glucose data, as well as prompts and reminders as appropriate.
Self-Management using Smartphone Apps

The BSP-ML research group receives substantial funding from the National Institute of Health Research (NIHR) through the Oxford Biomedical Research Centre (BRC) for projects translating research from its lab in the IBME to the clinic or the home. Our vision is 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.
Translational Studies

The overwhelming majority of ambulatory patients in modern healthcare systems are monitored only manually, by members of the clinical staff. There is an urgent need for mobile ("m-health") systems, comprising unobstrusive patient-worn sensors and lightweight processing (such as via smartphones) that are sufficiently robust for use in clinical practice.
Wearables for Digital Health