Predicting Cerebral Aneurysm Rupture by Machine Learning Using Medical Data and Blood Flow Simulation Data

Abstract

Stroke is the third leading cause of death and the number one cause of bedridden in Japan. Stroke occurs suddenly and is extremely difficult to predict. The purpose of this research is to predict cerebral aneurysm rupture with high accuracy by machine learning using medical data and engineering data, and to enable reasonable and optimal treatment according to the risk of rupture. In this study, we construct a classifier for predicting cerebral aneurysm rupture using clinical data and computational fluid dynamics simulation data of cerebral blood flow, and also extract dominant factors of rupture.