Population ageing is one of the main factors responsible for the global increase in the prevalence of dementia. Recent evidence suggests that modifiable risk factors, such as cardiovascular disease and lifestyle, may increase the risk of developing dementia and contribute to its progression. Furthermore, the use of non-invasive plasma biomarkers enables the identification of individuals with neurodegenerative diseases, even in the prodromal stage. However, the relationship between the cumulative burden of risk factors and plasma biomarkers is still poorly understood.

The main objective of this study is to identify and estimate the risk associated with modifiable and non-modifiable predictors (risk factors) linked to the development of Alzheimer's disease (AD) and non-AD dementia, as well as biological alterations consistent with AD or non-AD, through the development of a predictive tool based on Artificial Intelligence algorithms (Machine Learning model). The study also aims to provide a range of technological tools (an app for active patient monitoring and a web platform for clinicians) that could improve risk stratification and the personalisation of care pathways.

The study is divided into two different phases. Firstly, a retrospective phase is conducted in order to construct a predictive model for the risk of dementia and biological alterations consistent with AD. Secondly, a prospective phase is performed for the validation of the predictive model.