Machine learning for prediction of Alzheimer's Disease using brain diffusion tensor imaging

• Grant number: 21/09205-0
• Support Opportunities: Scholarships in Brazil - Scientific Initiation
• Effective date (Start): November 01, 2021
• Effective date (End): November 30, 2022
• Field of knowledge: Health Sciences - Medicine
• Principal Investigator: Liara Rizzi
• Grantee: Thais Maria Santos Bezerra
• Host Institution: Faculdade de Ciências Médicas (FCM). Universidade Estadual de Campinas (UNICAMP). Campinas , SP, Brazil

Abstract

Alzheimer's disease is the main cause of age-related dementia. One of its main current challenges consists in expanding diagnostic capacities in order to early identify the disease, preferably by using non-invasive methods. Parameters extracted by novel neuroimaging techniques including diffusion tensor imaging show promising results in the discrimination of AD's characteristics. In view of that, the current project aims to understand the diagnostic capacity of diffusion tensor imaging utilizing machine learning techniques to distinguish, among patients with mild cognitive impairment, which are more likely to progress to AD dementia. The neuroimaging parameters were collected from patients followed at Neuropsychology and Dementia's Ambulatory of Hospital de Clínicas da UNICAMP and machine learning analyses will be performed using Python 3.0. (AU)