Paper: Earlier Identification of Epilepsy Surgery Candidates Using Natural Language Processing

ACL ID W13-1901
Title Earlier Identification of Epilepsy Surgery Candidates Using Natural Language Processing
Venue Workshop on Biomedical Natural Language Processing
Session
Year 2013
Authors

This research analyzed the clinical notes of epilepsy patients using techniques from corpus linguistics and machine learning and predicted which patients are can- didates for neurosurgery, i.e. have in- tractable epilepsy, and which are not. Information-theoretic and machine learn- ing techniques are used to determine whether and how sets of clinic notes from patients with intractable and non- intractable epilepsy are different. The re- sults show that it is possible to predict from an early stage of treatment which pa- tients will fall into one of these two cate- gories based only on text data. These re- sults have broad implications for develop- ing clinical decision support systems.