Modelling and Predicting the Progression of Chronic Kidney Disease

  • Research type

    Research Study

  • Full title

    Modelling and Predicting the Progression of Chronic Kidney Disease

  • IRAS ID

    195905

  • Contact name

    Norman Poh

  • Contact email

    n.poh@surrey.ac.uk

  • Duration of Study in the UK

    3 years, 0 months, 0 days

  • Research summary

    Chronic kidney disease (CKD) is a significant cause of morbidity and mortality across the developed world. Patients with CKD have an increased risk of end stage kidney failure, leading to dialysis and kidney transplant, and of death from cardiovascular disease. According to an NHS Kidney Care report in 2012, CKD was estimated to cost £1.45 billion in 2009-10, 1.8 million people were diagnosed with CKD in England and there were potentially 900,000 to 1.8 million people with undiagnosed CKD.

    Although CKD risk estimators such as the QKidney Score exist, they predict only progression to end stage kidney failure, whereas guidelines based prescribing promotes continuous assessment and monitoring of risks. According to the latest NICE guidelines on CKD, this risk is defined in terms of the estimated glomerular filtration rate (eGFR) and urinary albumin:creatinine ratio (ACR). Therefore, prediction of a patient’s eGFR and ACR values will enable clinicians to gauge the future risks to a patient in line with the guidelines.

    In order to enable this, we are revisiting the problem of modelling the progression of CKD using a data intensive approach. This consists of three main aims:

    1) To develop models that can predict key clinical variables (e.g. eGFR and ACR) so that clinicians can make more informed decisions.
    2) To develop a method of identifying distinct groups of CKD patients based on their health histories.
    3) To develop a risk model for predicting acute kidney injury (AKI), in order to inform clinicians about a patient’s risk of AKI.

    We anticipate that this study will enable both eGFR measurements and the risk of AKI to be incorporated into models of CKD progression, lead to better tailored predictions through the grouping of patients and help clinicians quickly and accurately gauge the risk to their patients.

  • REC name

    North East - Newcastle & North Tyneside 1 Research Ethics Committee

  • REC reference

    15/NE/0431

  • Date of REC Opinion

    28 Dec 2015

  • REC opinion

    Favourable Opinion