Machine Learning for Patient-Specific, Predictive Healthcare Technologies via Intelligent Electronic Health Records

Healthcare systems world-wide are struggling to cope with the demands of ever-increasing populations in the 21st-century, where the effects of increased life expectancy and the demands of modern lifestyles have created an unsustainable social and financial burden. However, healthcare is also entering a new, exciting phase that promises the change required to meet these challenges: ever-increasing quantities of complex data concerning all aspects of healthcare are being stored, throughout the life of a patient. These include electronic health records (EHRs) now active in many hospitals, and large volumes of data being collected by patient-worn sensors.

The resulting rapid growth in the amount of data that is stored far outpaces the capability of clinical experts to cope. There is huge potential for using advances in computer science to use these huge datasets. This promises to improve healthcare outcomes significantly by allowing the development of new technologies for healthcare using the data - this is an area that promises to develop into a major new field in medicine. Making sense of the complex data is one of the key challenges for exploiting these massive datasets.

This programme aims to establish a new centre focussed on developing the next generation of predictive healthcare technologies, exploiting the EHR using new methods in computer science. We describe a number of healthcare themes which demonstrate the potential to improve patient outcomes. This will be achieved in collaboration with a consortium of leading clinicians and healthcare companies. The primary aim is to develop the "Intelligent EHR", which will have applications in creating "early warning systems" to predict patient problems (such as heart failure), and to help doctors know which drug or treatment would best be used for each individual patient - by interpreting the vast quantities of data available in the EHR.

The proposed programme has the potential for very significant impact for patients in the hospital or in the home, by optimising patient management and improving outcomes. Patients who are deteriorating will be identified early, which will allow preventative action to be taken, avoiding serious escalation (such as unplanned admission to an ICU), and which will reduce the incidence of preventable morbidity, cardiac arrests, and death. Those hospital patients recovering faster than expected, and who are deemed to be sufficiently stable, can be discharged home earlier. Patient-specific treatments will be enabled in both themes of the proposed work, improving patient outcomes by improving the efficacy of care provided. The translation of such systems into the home environment will provide benefit to patients with long-term conditions, such as chronic obstructive pulmonary disease (COPD) and heart failure - this will be achieved via predictive systems that allow clinicians to track patient condition without the false-alarm rate associated with existing systems, and which prevents existing systems providing benefit to existing patients.

The NHS as an organisation will benefit from the research because improved patient outcomes are associated with lower healthcare costs, as a result of shorter stays in hospital and fewer unplanned admission to (expensive) higher levels of care. Additionally, patients will be stratified according to risk of severity / deterioration, allowing improved use of clinical staffing resources. Clinicians will benefit by being able to interpret, for the first time, the very large and heterogeneous datasets that are available for their patients - enabled by robust, probabilistic tools created during the programme.

Companies in the commercial private sector will benefit from the research, where existing links with SMEs (university spin-outs) and large IT companies (Microsoft and Philips) will allow rapid implementation of the techniques developed during the programme. Such companies have an interest in "intelligent healthcare" algorithms that can be integrated into existing healthcare IT products, which will add significant value and market differentiation. Additionally, the rapidly-growing market for wearable devices is currently focused only on consumers - the proposed centre will extend this market to healthcare technologies, by exploiting the opportunities for large-scale innovation and clinical validation that exist in the programme. The UK economy will benefit by the likely creation of new spin-out activity based around the activity of the proposed centre.

The scientific community, and the UK research base in particular, will benefit from developing capacity in an emerging field of global importance, and where the proposed centre will train the next generation of researchers in computational health informatics - the use of machine learning for healthcare technologies. The methodology developed within the proposed programme will be of translational benefit to other scientific disciplines, including other computational and mathematical sciences. Results from the proposed work will feed into the Alan Turing Institute, where researchers involved across the UK will benefit from the development of large-scale methodologies for data science.

The public will benefit via public-engagement activities run in collaboration with the Institution for Engineering & Technology (the world's largest multidisciplinary engineering professional institution), the George Institute for Global Health (which holds public-engagement conferences at its bases in Oxford, Sydney, Beijing, and New Delhi), the Royal Academy of Engineering (which supports Clifton's work via a Research Fellowship), and the NIHR Oxford Biomedical Research Centre (which holds regular public outreach events).