Neurology Symptom Detection

This project focuses on developing NLP models that analyze radiology reports on Head Computed Tomography (CT) scans to detect and assess neurological symptoms such as the Severity of Study, presence of Acute Blood, Mass Effect, Acute Stroke, and Hydrocephalus.

• Funded by the Foundation of the American Society of Neuroradiology (ASNR)
• Duration: 01/2015 ~ 12/2016

Directors

• PI: Falgun Chokshi - Assistant Professor of Radiology, Emory University
• Co-PI: Jinho Choi - Assistant Professor of Computer Science, Emory University

Publications

• Natural Language Processing for Classification of Acute, Communicable Findings on Unstructured Head CT Reports: Comparison of Neural Network and Non-Neural Machine Learning Techniques. Chokshi, F.; Shin, B.; Lee, T.; Lemmon, A.; Necessary, S.; and Choi, J. D. bioRxiv, 173310, 2017.
• Classification of Radiology Reports Using Neural Attention Models. Shin, B.; Chokshi, F. H.; Lee, T.; and Choi, J. D. Proceedings of the International Joint Conference on Neural Networks (IJCNN), 2017.