Ana Cristina Guirola De Newell

• Using Artificial Intelligence (AI) to predict mild cognitive impairment in cognitively unimpaired individuals; a systematic review
• Master of Pharmacy with Honours

Alzhemier’s disease (AD) is a neurodegenerative disease, marked by symptoms of dementia. These symptoms can gradually get worse over time, with a decline in cognition that is severe enough to interfere with daily life. Mild cognitive impairment (MCI) is a state intermediate between normal cognition and dementia, with essentially perserved functional abilities. Artificial Intelligence (AI) models are now employed to predict MCI risk. We conducted a systematic review to explore the optimum set of non-invasive predictors to predict the onset of MCI in healthy individuals. Four databases were used, following the (PRISMA) guidance; 1098 articles were identified, 22 of which met our inclusion criteria. Different machine learning algorithms were identified, the K-fold cross validation model being the most common. Accuracy (78.7%) indicates that these methods are promising and that the data could be useful to clinicians in the early detection of MCI.

Funded by:  Newcastle University Research Scholarship

Project Supervisors: Professor Sarah Slight and Nehal Hassan