Predicting vascular complications in diabetes

  • Research type

    Research Study

  • Full title

    Use of artificial intelligence to predict vascular complications in diabetes

  • IRAS ID

    275254

  • Contact name

    Charles Gutteridge

  • Contact email

    charlesgutteridge@nhs.net

  • Sponsor organisation

    Joint Research Management Office

  • Duration of Study in the UK

    0 years, 7 months, 30 days

  • Research summary

    The east London population is characterised by a very high prevalence of diabetes, complex comorbidities and aggressively progressive diabetes complications. Diabetic foot disease is associated with particularly poor outcomes in terms of limb loss and, although symptoms and pain can be surgically treated, are associated with increased mortality. This also leads to poor quality of life for the patient and socio-economic loss for wider society.

    Some problems, such as nerve damage, artery blockages and kidney disease, are known to be associated with foot disease. It is likely that there are multiple causes of these poor outcomes: analyses utilising the information-rich clinical notes available for this high risk population treated at Barts Health to identify factors associated with, as well as to predict, these adverse outcomes is an essential prerequisite to improving prognosis. Further, evidence for the best management of these patients is lacking due to comparison in a group of patients who typically undergo multiple medical and surgical interventions simultaneously for several organ dysfunctions.

    We aim to use information-rich patient electronic health records (EHRs) to develop predictive tools for clinical risk assessment and decision support in diabetes care, allowing intervention at an earlier stage than currently possible and for stratified treatment plans. This data is particularly suited for monitoring progression of long-term health conditions such as diabetes and its complications.

  • REC name

    London - City & East Research Ethics Committee

  • REC reference

    20/LO/0510

  • Date of REC Opinion

    13 Apr 2020

  • REC opinion

    Favourable Opinion