Text Mining Brain Imaging Reports

Claire Grover; Richard Tobin; Beatrice Alex; Catherine Sudlow; Grant Mair; William Whiteley

Text Mining Brain Imaging Reports

Claire Grover, Richard Tobin, Beatrice Alex, Catherine Sudlow, Grant Mair, William Whiteley

Research output: Contribution to conference › Paper › peer-review

Abstract / Description of output

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.

Original language	English
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 http://healtex.org/healtac-2018/

Conference

Conference	UK Healthcare Text Analytics Conference (HealTAC-2018)
Abbreviated title	HealTAC-2018
Country/Territory	United Kingdom
City	Manchester
Period	18/04/18 → 19/04/18
Internet address	http://healtex.org/healtac-2018/

Cite this

@conference{252f1fd829804ea9a54de75758eb1589,

title = "Text Mining Brain Imaging Reports",

abstract = "We describe a text mining system for classifying radiologists{\textquoteright} 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.",

author = "Claire Grover and Richard Tobin and Beatrice Alex and Catherine Sudlow and Grant Mair and William Whiteley",

year = "2018",

month = apr,

language = "English",

note = "UK Healthcare Text Analytics Conference (HealTAC-2018) : Unlocking Evidence Contained in Healthcare Free-text, HealTAC-2018 ; Conference date: 18-04-2018 Through 19-04-2018",

url = "http://healtex.org/healtac-2018/",

}

TY - CONF

T1 - Text Mining Brain Imaging Reports

AU - Grover, Claire

AU - Tobin, Richard

AU - Alex, Beatrice

AU - Sudlow, Catherine

AU - Mair, Grant

AU - Whiteley, William

PY - 2018/4

Y1 - 2018/4

N2 - 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.

AB - 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.

M3 - Paper

T2 - UK Healthcare Text Analytics Conference (HealTAC-2018)

Y2 - 18 April 2018 through 19 April 2018

ER -

Text Mining Brain Imaging Reports

Abstract / Description of output

Conference

Fingerprint

Cite this