Abstract: Models have been developed to predict stroke outcomes (e.g., mortality) in attempt to provide better guidance for stroke treatment. However, there is little work in developing classification models for the problem of unknown time-since-stroke (TSS), which determines a patient’s treatment eligibility based on a clinical defined cutoff time point (i.e., <4.5hrs). In this paper, we construct and compare machine learning methods to classify TSS<4.5hrs using magnetic resonance (MR) imaging features. We also propose a deep learning model to extract hidden representations from the MR perfusion-weighted images and demonstrate classification improvement by incorporating these additional imaging features. Finally, we discuss a strategy to visualize the learned features from the proposed deep learning model. The cross-validation results show that our best classifier achieved an area under the curve of 0.68, which improves significantly over current clinical methods (0.58), demonstrating the potential benefit of using advanced machine learning methods in TSS classification
Learning Objective 1: To formulate an machine learning apporach to classify acute ishemic stroke patient unknown time since stroke (TSS).
Learning Objective 2: To learn the use of a deep learning appraoch (i.e., autoencoder) to learn representative and predictive features from perfusion-weighted images to classify acute ishemic stroke patient unknown time since stroke (TSS).
King Chung Ho (Presenter)
William Speier, UCLA
Suzie El-Saden, UCLA
Corey Arnold, UCLA