Wiktor Stachera

• Using AI models for the prediction of mild cognitive impairment; A systematic review
• Master of Pharmacy with Honours

Mild cognitive impairment (MCI) is an early stage of memory loss or other cognitive ability loss in individuals who maintain the ability to independently perform most activities of daily living. We conducted a systematic review to identify the optimal set of predictors for developing artificial intelligence (AI) models to predict MCI using non-invasive methods, such as daily life activities or gait. We screened 1,098 papers and identified 22 relevant studies with relevant AI models. These models exhibited high accuracy (79% on average) in identifying the subtle early signs of MCI, which can potentially slow down the progression to Alzheimer's disease. We identified nine types of predictors that can be readily obtained in clinical care settings including biological response, health assessments, demographics, gait, game performance, cognitive tasks, speech, sensory response, and daily activities. Further research into the application of AI for disease prediction and prevention has the potential to enhance healthcare outcomes and improve overall quality of life.

Funded by: Newcastle University Research Scholarship

Project Supervisor: Professor Sarah Slight