Predicting the risk of Diabetic Retinopathy in people with type 2 diabetes

Details

Recent figures from Diabetes UK show that 4.3 million people in the UK are diagnosed with diabetes of whom approximately 90% have type 2 diabetes mellitus (T2DM) and another 2.4 million are at high risk of developing the T2DM. The prevalence of T2DM has been increasing worldwide with an estimated 537 million in 2021 with a projection of 600 million by 2040. Diabetes without optimal treatment management may progress to the risk of diabetic retinopathy (DR) and other adverse outcomes. Due to the complex and dynamic progression of conditions in patients with type 2 diabetes mellitus (T2DM), the care of patients involves continuous monitoring and critical decision-making processes assessing a vast amount of diverse clinical, laboratory and medication data.

Although early worsening of the condition and specific drug exposure along with the possible pathophysiological mechanism is reported, limited information is available to evaluate the variations of drug classes and their doses and other clinical conditions on the progression of DR. We earlier conducted a systematic review and network meta-analysis of published DR prediction models having drug exposure as a predictor and observed that exposure to insulin is associated with a higher risk of DR (Bantounou et al., 2024). However, the practicality and generalisability of published DR prediction models are limited. These models did not consider information about drug exposure and medication-related features consistently. Additionally, these models lack a rigorous approach to account for time-varying risk factors, dynamic progression of risk and external validation. Therefore, the longitudinal and multiple features of drug exposure data require advanced statistical and other methodological strategies to model day-to-day medication and clinical profiles of patients in the prognostic modelling framework.

Utilising the existing platform and resources and our long-standing expertise and experience in the cutting-edge area of data science and working at the frontline with patients, the proposed PhD project will take a holistic approach to understand the DR progression in people with T2DM: the project aims to develop prognostic analytical tools focussing on the drug exposure history, clinical profiles of patients and retinal images thereby predicting the DR risk of people with T2DM. The project will employ advanced statistical methodologies, alongside state-of-the-art machine learning and deep learning techniques, to develop models designed to enhance personalised risk assessment of individual patients.

Informal enquiries are encouraged, please contact Dr Mintu Nath (mintu.nath@abdn.ac.uk) for further information.

Candidate Background:

Applicants to this project should hold a minimum of a 2:1 UK Honours degree (or international equivalent) in a relevant subject.

The student should have a good background in statistics, data sciences or computing and some familiarity in handling large-scale datasets.

We actively encourage applications from diverse career paths and backgrounds and across all sections of the community, regardless of age, disability, ethnicity, gender, gender expression, sexual orientation and transgender status, amongst other protected characteristics.

We also invite applications from those returning from a career break, industry or other roles. We typically require a minimum of a 2:1 UK Honours degree (or equivalent), but exceptions can be made where applicants can demonstrate excellence in alternative ways, including, but not limited to, performance in masters courses, professional placements, internships or employment.

APPLICATION PROCEDURE:

• Please note: This is a self-funded opportunity only.
• Formal applications can be completed online: https://www.abdn.ac.uk/pgap/login.php
• You should apply for Applied Health Sciences (PhD) to ensure your application is passed to the correct team.
• Please clearly note the name of the supervisor and the project title on the application form.
• Your application must include: a personal statement, an up-to-date copy of your academic CV, and clear copies of your educational certificates and transcripts.
• If you are still undertaking your undergraduate degree, it is helpful to the selection panel if you could provide documentation showing your grades to date (this can be a screenshot from an online portal).
• Please note: Project supervisors will not respond to requests for funding assistance.
• If you require any additional assistance in submitting your application or have any queries about the application process, please don’t hesitate to contact us at pgrs-admissions@abdn.ac.uk