Development of statistical methods for the joint modelling of multiple longitudinal biomarkers and time-to-event data derived from linked electronic health records, for use in patient-tailored precision medicine within cardiovascular disease

Clinicians dynamically record changing information in electronic health records, yet most prognostic models consider only a single static value of a biomarker. In cardiovascular disease little is known about how to model both trends over time, and also their association with clinical endpoints . This project will use population based electronic health records linking primary care, hospitalisation registry, heart attack and death registries (the CALIBER programme), to investigate the extent to which current values of biomarkers, such as systolic and diastolic blood pressure, and trends over time, add information beyond a single baseline value in the prediction of death, MI or stroke. This centres on precision medicine, utilising records to tailor predictions at the individual patient level, with the potential to allow targeted interventions to be applied at the optimum time-point, whilst dynamically monitoring patient characteristics as they evolve in “real time”. The project will involve development of advanced statistical techniques in the field of joint modelling of longitudinal and survival data, including development of user-friendly software. Possible topics include, 1) Systematic review of joint modelling in cardiovascular disease, 2) Modelling the visiting process: Sicker patients go to the doctor’s more often, 3) Joint modelling of multiple, repeatedly measured biomarkers and their association with survival, 4) Developing model discrimination tools to evaluate multiple predictive biomarkers. Close collaboration will be fostered with researchers at the Farr Institute at UCL. The student will have the opportunity to attend and present at national and international conferences. Application deadline 12 noon 16th May 2016.
In order to apply please select Health Sciences Research for a September 2016 intake on the application form linked below. In the Funding section of the online application, please select Studentship and then Select CMBSP in the next dropdown option. Please indicate the name of the project supervisor(s) and the project title in the space provided within the application.