Programmes Deep Medicine
This programme will use some of the largest and most complex biomedical datasets that have ever been collected to generate insights into complex disease patterns, risk trajectories and treatment effects. Through an interdisciplinary approach, established and novel techniques in data mining, machine learning and deep learning will be applied to complex biomedical datasets.
Advances in medicine over the past few decades have led to an unprecedented increase in life expectancy and reduction in major disabilities. More people can expect to live into their 60s and beyond than die prematurely before the age of 60. But this longevity brings with it new problems: a rise in chronic conditions such as diabetes, dementia and heart failure, with many patients suffering from multiple conditions at the same time (multimorbidity), which are poorly understood.
Our limited understanding of complex disease patterns and risks is further compounded by current methods of research, which tend to oversimplify complexity and often underrepresent patients with complicated disease history or concurrent treatments. Elevated blood pressure, for example, is the leading risk factor for death and disability worldwide, but despite substantial research still little is known about the effects of blood pressure lowering in elderly people with multimorbidity, who may have relatively normal blood pressure levels.
The advent of ‘Big Data’ can offer unprecedented opportunities for extending our knowledge and understanding of complex disease patterns and risk, but harnessing its full potential will require new and innovative methods of analysis.
Substantial investments in healthcare informatics have allowed the collection of large quantities of electronic healthcare records and research datasets. They have further provided the infrastructure for interrogating vast amounts of data.
Combining expertise in healthcare, biomedical data and advanced machine learning, our team will investigate whether applying data mining, machine learning and deep learning techniques to large biomedical datasets can lead to better understanding and management of chronic diseases and multimorbidity.
Our initial sources of data will include:
- UK Biobank – an unprecedented wealth of multimodal data from 500,000 participants, with work underway data to collect further imaging data
- Clinical Practice Research Datalink (CPRD) – the world’s largest database of linked primary and secondary care records, covering 700 UK GP practices, with data from 10 million patients
- Blood Pressure Lowering Treatment Trialists’ Collaboration (BPLTTC) – the largest randomised database involving data from over 40 trials and more than 270,000 randomised patients
We will further access other national and international datasets to contrast and expand research findings.
We will develop scalable methods for analysis of datasets, prepare and transform data in order to apply new and existing algorithms, and advance our assessment of treatment effects by including patient features such as multimorbidity in analysis of trial data.
We aim to generate insights into complex disease patterns, risk trajectories and treatment effects, and provide empirical evidence for the value of applying data mining, modelling and machine learning techniques to biomedical data.