An attempt to predict Emergent Large Vessel Occlusion(ELVO) using Machine Learning Techniques

This research is an effort to improve the performance of the ELVO checker using machine learning techniques. Seven points were implemented to improve the sensitivity and false negative rate. Random Forest with class weighting, adding number of cases for ELVO by up sampling, and data preprocessing for age were effective. We have obtained the learning model that achieves a sensitivity of 93.1% and a false negative rate of 6.9%.