The research focuses on understanding underlaying factors and that impact Type II Diabetes, or weight-associated diabetes, and life-expectancy outcomes and the overlap between these factors in different populations.
This research has practical implications for identifying groups most at risk, and for the long-term tracking of progression and improvement of ageing related conditions – and for tailoring interventions to improve the time in which people remain healthy.
The work will also provide a better understanding of the associations between changes in health measures during ageing and death, which could have value for future prevention advice and public health benefits.
This work also helps to address a second problem of trustworthiness and bias in AI in healthcare & how to overcome issues. The project will use the population datasets to evaluate different models and provide transparency on how results were achieved. This helps to contribute to a future where health products give reliable results for everyone.