Improving Risk Prediction for Type 2 Diabetes

Individual risk prediction is a principal goal of precision medicine. Accurately estimating the probability of a specific event or the development of a disease in a given individual over a specified time period can enable earlier and more effective intervention. Type 2 Diabetes (T2D) serves as an exemplary outcome for predictive models because its progression can be significantly altered, or even reversed, with early identification and intervention. However, predicting such an outcome is not straightforward. Like all complex phenotypes, T2D arises from the intricate interplay between genetic and environmental factors, which are challenging to distinguish and quantify. The proliferation of proteomic data offers a rich source of potential predictors for diabetes and other complex phenotypes. Including proteomic data in predictive models may improve their performance and provide mechanistic insights into the biological pathways underlying diabetes. Understanding these pathways can help identify new therapeutic targets and tailor treatments to individual patients' molecular profiles. It is likely that proteomic data capture both genetic and environmental contributions to T2D. The limited existing evidence suggests that protein-based scores improve the performance of predictive models and can outperform PRS for T2D. Including proteins as predictors may encapsulate both genetic and environmental factors conferring risk to T2D, which could explain their improved performance as predictors over PRS. This work aims to further our understanding of how best to predict risk for T2D in different ancestral populations, how environmental factors and -omics may jointly contribute to T2D, and how we can use emerging -omic data to elucidate the complexity of T2D and its subtypes.

This proposal will use observational and genetic data in both the China Kadoorie and UK Biobank and emerging proteomic data in the CKB (~10,000 proteins in 4000 participants) and the UKB (~3000 proteins in 50,000 participants). The project will utilise both conventional and machine learning approaches to address the aims

Aims

1) To build a risk prediction model for T2D using observational data for traditional risk factors; 2) To investigate the performance of a novel method of PRS development with an existing published PRS for T2D in the two cohorts;
3) Compare the performance of the novel PRS and exiting PRS for T2D related phenotypes;
4) Develop methods to extend the risk prediction models of T2D by incorporating proteomic data in addition to conventional risk factors, and PRS scores for T2D;
5) To internally and potentially externally validate the different risk prediction models;
6) Develop tools in order to communicate T2D risk to patients and health professionals.

This project falls within the EPSRC research area of Healthcare Technologies.

In the same way that bioinformatics has transformed genomic research and clinical practice, health data science will have a dramatic and lasting impact upon the broader fields of medical research, population health, and healthcare delivery. The beneficiaries of the proposed training programme, and of the research that it delivers and enables, will include academia, industry, healthcare, and the broader UK economy.

Academia: Graduates of the training programme will be well placed to start their post-doctoral careers in leading academic institutions, engaging in high-impact multi-disciplinary research, helping to build training and research capacity, sharing their experience within the wider academic community.

Industry: Partner organisations will benefit from close collaboration with leading researchers, from the joint exploration of research priorities, and from the commercialisation of arising intellectual property. Other organisations will benefit from the availability of highly-qualified graduates with skills in big health data analytics.

Healthcare: Healthcare organisations and patients will benefit from the results of enabled and accelerated health research, leading to new treatments and technologies, and an improved ability to identify and evaluate potential improvements in practice through the analysis of real-world health data.

Economy: The life sciences sector is a key component of the UK economy. The programme will provide partner companies with direct access to leading-edge research. Graduates of the programme will be well-qualified to contribute to economic growth - supporting health research and the development of new products and services - and will be able to inform policy and decision making at organisational, regional, and national levels.