Academic Awards 2024 booklet

23 Combining Biclustering with Probabilistic Predictive Models to Develop Personalised Sets for the Famous Faces Test With the ageing of the world population, addressing the challenges of healthy ageing becomes increasingly important. Dementia is a major cause of disability and dependency among the elderly population but despite its prevalence, it is often detected too late due to its complex nature and variations in progression. Personalised approaches in medicine, facilitated by data science, offer potential solutions to this problem. In this project, I focused on the application of biclustering and probabilistic models to investigate individual factors that influence performance on the Famous Faces Test (FFT) – a tool useful for early dementia detection. First, I confirmed that personal characteristics impact FFT scores, both overall and at the level of individual FFT items. Following this, I developed and compared models predicting the probability of a correct response, thereby enabling the creation of personalised tests. The findings of this research highlight the potential of creating adapted versions of the FFT. Such tailored tests could aid early detection and support the diagnostic process of dementia in general practice.