Main navigation

  • About
  • Our Approach
  • News
  • Events
  • Research
  • ARC Store Resources
  • Contact

Search

Home

Search

Skip to main navigation Skip to main content
Home

Main navigation

  • About
  • Our Approach
  • News
  • Events
  • Research
  • ARC Store Resources
  • Contact

Predicting diabetes-related complications with machine learning techniques

ARC Themes
Data Sciences
Resource Stage
PhD
Status
Ongoing
Health Category
Generic Health Relevance

What we are doing?

We are taking clinical data from the NHS to develop a machine learning algorithm that can successfully and accurately predict any long-term complications for diabetic patients. Multiple algorithms will be explored such as classification and regression trees, support vector machines (SVM), k-nearest neighbour, gradient boosting machines, and supervised principal component analysis as well as the more statistical approaches such as regressions. A graphical user interface or app will be developed to allow GPs and patients to interact with and utilise the Machine Learning algorithm that will be developed. 

Why we are doing it?

Diabetes is a chronic condition that affects millions globally and often leads to severe long-term complications such as cardiovascular disease, kidney failure, and neuropathy. Early prediction of these complications can enable timely interventions, improving patient outcomes and reducing healthcare costs. Current clinical methods often lack the precision to identify high-risk individuals early enough. By leveraging machine learning, we aim to provide more accurate and individualised risk assessments, empowering clinicians and patients with actionable insights. This research bridges the gap between cutting-edge technology and clinical practice, offering a proactive approach to managing diabetes and its associated complications.

What the benefits will be and to whom?

This research will benefit diabetic patients by enabling earlier detection of potential complications, improving their quality of life through timely interventions. Healthcare providers, including general practitioners and specialists, will gain access to a powerful decision-support tool that enhances diagnostic accuracy and streamlines patient management. Policymakers and healthcare systems will also benefit from reduced treatment costs associated with late-stage complications. Furthermore, researchers in the field of machine learning and medical informatics can build upon this framework to address other chronic diseases. Ultimately, this project aims to transform diabetes care through personalised and data-driven solution.

Who we are working with?

We are collaborating with the NHS, to access high-quality clinical data from the CPRD Aurum and GOLD dataset. Our multidisciplinary team includes a GP, Data Scientist and a Bioinformatician. By combining expertise across domains, we aim to develop a robust and impactful solution for predicting diabetes-related complications.

Contact

Bismah Ghafoor, PhD Researcher, Leicester Diabetes Centre, Bg205@leicester.le.ac.uk. 
 

ARC Themes
Health Category
National Programme
Resource Stage
Status

Main navigation

  • Explore our research
  • Research Themes
    • Building Community Resilience and Enabling Independence
    • Data2Health
    • Ethnicity and Health Inequalities
    • Mental Health and Wellbeing
    • Multiple Long-term Conditions
    • Translating and Implementing Sustainable Service Improvement
  • Acknowledging ARC research
Back to top
Home

In partnership with

  • University of Nottingham
  • Nottinghamshire Healthcare NHS Trust
  • University of Leicester
  • About
    Core Team
    Contact

Follow us

  • Follow us on X
  • Follow us on LinkedIn
  • Follow us on Youtube
  • Follow us on Spotify

© 2025 by ARC East Midlands

Footer

  • Cookies
  • Disclaimer
  • Privacy Policy
  • Terms and Conditions

Site by Effusion