We describe a text mining system for classifying radiologists’ reports of CT and MRI brain scans, assigning labels indicating occurrence and type of stroke, as well as other observations. Our system, the Edinburgh Information Extraction for Radiology reports (EdIE-R) system, was developed and tested on a collection of 1,168 reports from the Edinburgh Stroke Study (ESS), a hospital-based register of stroke and transient ischaemic attack patients. Automated reading of reports such as these opens up avenues for population health monitoring and audit, and can provide a resource for epidemiological studies. Here we describe the EdIE-R system and report on its development and evaluation on annotated data from ESS. We aim to make the development and testing annotations for the ESS collection available for research.
|Publication status||Published - Apr 2018|
|Event||UK Healthcare Text Analytics Conference (HealTAC-2018): Unlocking Evidence Contained in Healthcare Free-text - Manchester, United Kingdom|
Duration: 18 Apr 2018 → 19 Apr 2018
|Conference||UK Healthcare Text Analytics Conference (HealTAC-2018)|
|Period||18/04/18 → 19/04/18|