Machine learning prediction of intellectual abilities from magnetic resonance neuroimaging

• Grant number: 18/11881-1
• Support type: Scholarships in Brazil - Doctorate
• Effective date (Start): April 01, 2019
• Effective date (End): June 30, 2021
• Field of knowledge: Biological Sciences - Biophysics - Biophysics of Processes and Systems
• Principal Investigator: Carlos Ernesto Garrido Salmon
• Grantee: Bruno Hebling Vieira
• Home Institution: Faculdade de Filosofia, Ciências e Letras de Ribeirão Preto (FFCLRP). Universidade de São Paulo (USP). Ribeirão Preto , SP, Brazil

Abstract

Intelligence encompasses several cognitive capabilities that allow the individual to gather information from and act on its environment. It is known that these cognitive processes are centered in the brain and, comparing the human brain to the brain of other animals less proficient at diverse cognitive processes usual to humans, it is possible to infer that neuroanatomical and neurophysiological divergences are, somehow, associated to differences in cognitive abilities. In another scale, these divergences are also noticed between human individuals, where there exists a correlation between intracranial volume and intelligence quotients, for example. Knowing that, it is possible to employ neuroimaging, more specifically anatomical and functional magnetic resonance imaging, to uncover correlates of intelligence in humans. Alternatively, it is also possible to derive models to predict, with machine learning, intelligence quotients in subjects from their neuroimaging data. In this project, we propose the use of both methodologies to uncover relationships between intelligence and brain morphometric and connectivity features in a large sample of healthy subjects. (AU)