Neuroscience have been the field with most significant contributions to the study of the human brain. The development of new techniques for image acquisition has made possible the improvement of extracting quality information of brain activity. Utilizing functional MRIs, is possible to measure brain activity based on changes of the oxygen level in the blood at certain period of time. This imaging data is transformed into numerical values using a software that maps all the information into a data object. Taking advantage of the availability of functional connectivity information of the human brain, the present study shows a widespread process to build a predictive model with built-in Cross-Validation. The investigation shows three powerful statistical methods (Logistic Regression, Linear Discriminant Analysis and Random Forest) to predict subjects traits based on the relationships between brain regions. The final model will be able to use any brain connectivity data, which make this process a generalized approach that others researchers could use to assess other features of the human brain.
Applied Statistics (MS)
Nibbs, Guenadie, "Predictive Models in Brain Connectivity Analysis" (2018). Thesis. Rochester Institute of Technology. Accessed from
RIT – Main Campus