Classification of phenotypic types and subtypes is important for both clinical care and research into underlying disease mechanisms. Detecting phenotypic subgroups of patients suffering from complex diseases for example Parkinson’s disease and Chronic obstructive pulmonary disease could provide support for early detection of deteriorating patients, determination of individualised and customised treatment, and prevention strategies for different phenotypic groups, which ultimately results in enhanced treatment outcome.

Scientists at the University of Oxford have developed an end-to-end pipeline composed of data collection, pre-processing and data modelling which can identify patients with complex diseases into subgroups with differing disease progression and risk of disease complications.

The sub-stratification of diseases enables screening of risk factors (genetic and/or environmental), tailor and target early treatment for patients in a way towards precision medicine with more efficient healthcare delivery and further improved patient outcome.

The technology allows for an integrated platform for precision medicine, more specifically using the architecture of deep clustering to subtype a disease patient cohort with phenotypic information that has genetic associations with clusters.

The technology has application in a variety of precision medicine settings including drug discovery and wearable health monitoring.