Postgrad LIVE! Study Fairs


Nottingham Trent University Featured PhD Programmes
Birkbeck, University of London Featured PhD Programmes
University of Glasgow Featured PhD Programmes
FindA University Ltd Featured PhD Programmes
Birkbeck, University of London Featured PhD Programmes

Statistical Learning for Early Detection and Prevention of Diabetes

Project Description

Diabetes remains one of the largest challenges for our health service, and predictions have suggested that the NHS could be spending 17 billion pounds per year treating it by 2035.

Diabetes is a challenging disease because its consequences are many and varied and despite there being a known preventive strategy for type-2 diabetes, there is a lack of pragmatic evidence surrounding the actual impacts of lifestyle interventions in preventing individuals at a high risk of diabetes becoming clinically diabetic. The number of diabetic individuals is large, which makes public-scale campaigns difficult (costly and resource demanding) to implement and better use of existing data, targetting the most at risk individuals could make a big difference to the long-term clinical outcomes of patients.

Using historical EMIS records including predictors such as BMI, age, sex, HBAIC and other blood counts as well as the existence of co-morbidities, practice pharmacist prescribing data and socioeconomic data, this project aims to:

(1) Develop statistical models to identify which of the pragmatically-collected risk factors (EMIS / prescribing / socioeconomic) are are useful for identifying individuals at risk of pre-diabetes* and clinical diabetes

(2) To develop statistical models for HBAIC trajectories and evaluate this biomarker as a potential major component of a risk score calculator (see next)

(3) To produce statistical models of risk as a function of time and develop an risk score calculator for predicting transition to (a) pre-diabetes and (b) clinical diabetes within a given time-period.

By involving local key stakeholders, the results of this research will directly influence diabetes care in the Morecambe bay area and through publications, influence national practice.

* NB we use the term `pre-diabetic’ to describe individuals that are at a high risk of developing diabetes.

For further information about the project please contact or

Applications are made by completing an application for PhD Statistics and Epidemiology October 2019 through our online application system. Closing date: midnight 15th March 2019


- Beverley Balkau et al (2008). Predicting Diabetes: Clinical, Biological, and Genetic Approaches
Data from the Epidemiological Study on the Insulin Resistance Syndrome (DESIR). Diabetes Care 2008 Oct; 31(10): 2056-2061.

- Kedir N Turi el al (2017). Predicting Risk of Type 2 Diabetes by Using Data on Easy-to-Measure Risk Factors. Prev Chronic Dis 2017;14:160244. DOI:

- Yang et al (2018) Type 2 diabetes mellitus prediction model based on data mining.

- Alghamdi et al (2017) Predicting diabetes mellitus using SMOTE and ensemble machine learning approach: The Henry Ford ExercIse Testing (FIT) project.


How good is research at Lancaster University in Allied Health Professions, Dentistry, Nursing and Pharmacy?

FTE Category A staff submitted: 64.40

Research output data provided by the Research Excellence Framework (REF)

Click here to see the results for all UK universities

Email Now

Insert previous message below for editing? 
You haven’t included a message. Providing a specific message means universities will take your enquiry more seriously and helps them provide the information you need.
Why not add a message here
* required field
Send a copy to me for my own records.

Your enquiry has been emailed successfully

FindAPhD. Copyright 2005-2019
All rights reserved.