Prediction of Type 2 Diabetes in Hyperuricemic Patients Using Explainable Machine Learning

Summary

Motivation

Gout and type 2 diabetes mellitus (T2D) are both common and serious conditions in Northern Ireland and globally.

Northern Ireland has among the highest rates of gout in the UK, particularly in older, socio-economically deprived populations where multimorbidity and poor access to early metabolic care exacerbate disease progression.

Despite growing evidence linking hyperuricemia and gout with insulin resistance and incident T2D, the role of gout as a predictive modifier in diabetes risk has received little attention in the development of clinical tools or population risk stratification.

This project aims to address that gap by using explainable machine learning to develop a predictive model for T2D in patients with gout or hyperuricemia. Our hypothesis is that gout-related features, such as serum urate levels, flare frequency, and urate-lowering therapy, provide independent and clinically valuable predictive information about future diabetes risk.

These features are rarely included in conventional diabetes risk tools, meaning high-risk patients may be overlooked in both research and practice.

Objective & Methods

Our objective is to create an interpretable model that integrates both metabolic and gout-specific variables, trained on a longitudinal dataset from our partner institution, Quanzhou First Hospital in Fujian, China.

This collaboration, already active through ongoing work in metabolic disease prediction, provides access to large-scale, structured clinical data and shared clinical expertise.

The model will be developed using gradient-boosted decision trees (XGBoost), and we will apply SHAP (SHapley Additive exPlanations) to ensure interpretability, allowing clinicians to see which features contribute most to each individual’s predicted risk.

We will externally validate the model using retrospective Northern Ireland health data. This step is crucial to assess generalizability across health systems and to demonstrate potential for clinical adoption in NI.

Given the high prevalence of gout, and the regional prioritization of diabetes prevention, health inequality reduction, and AI-enabled early detection, this project aligns with key public health needs in NI.

Outputs

The project will deliver:

1. A novel, interpretable ML model for T2D risk prediction in hyperuricemic patients;
2. A clinically relevant demonstration of gout as a modifiable risk signal for T2D;
3. A validated tool with potential future translation into decision support systems in NI and beyond.

By linking international clinical datasets with Northern Ireland-focused validation, and combining AI methods with real-world health priorities, this project represents a rare opportunity to deliver methodological innovation, international collaboration, and direct local impact.

AccessNI clearance required

Please note, the successful candidate will be required to obtain AccessNI clearance prior to registration due to the nature of the project.

Essential criteria

Applicants should hold, or expect to obtain, a First or Upper Second Class Honours Degree in a subject relevant to the proposed area of study.

We may also consider applications from those who hold equivalent qualifications, for example, a Lower Second Class Honours Degree plus a Master’s Degree with Distinction.

In exceptional circumstances, the University may consider a portfolio of evidence from applicants who have appropriate professional experience which is equivalent to the learning outcomes of an Honours degree in lieu of academic qualifications.

• Sound understanding of subject area as evidenced by a comprehensive research proposal
• A comprehensive and articulate personal statement

Desirable Criteria

If the University receives a large number of applicants for the project, the following desirable criteria may be applied to shortlist applicants for interview.

• First Class Honours (1st) Degree
• Completion of Masters at a level equivalent to commendation or distinction at Ulster
• Practice-based research experience and/or dissemination
• Experience using research methods or other approaches relevant to the subject domain
• Work experience relevant to the proposed project
• Publications record appropriate to career stage
• Experience of presentation of research findings

Equal Opportunities

The University is an equal opportunities employer and welcomes applicants from all sections of the community, particularly from those with disabilities.

Appointment will be made on merit.

Funding and eligibility

NOTE - This is a self funded research project and applicants will be required to provide evidence of funds to support their tuition fees and living expenses.

Applicants should hold, or expect to obtain, a First or Upper Second Class Honours Degree in a subject relevant to the proposed area of study.