Link to the University of Pittsburgh Homepage
Link to the University Library System Homepage Link to the Contact Us Form

Automating tissue bank annotation from pathology reports - comparison to a gold standard expert annotation set.

Liu, K and Mitchell, KJ and Chapman, WW and Crowley, RS (2005) Automating tissue bank annotation from pathology reports - comparison to a gold standard expert annotation set. AMIA ... Annual Symposium proceedings / AMIA Symposium. AMIA Symposium. 460 - 464.

[img] Plain Text (licence)
Available under License : See the attached license file.

Download (1kB)


Surgical pathology specimens are an important resource for medical research, particularly for cancer research. Although research studies would benefit from information derived from the surgical pathology reports, access to this information is limited by use of unstructured free-text in the reports. We have previously described a pipeline-based system for automated annotation of surgical pathology reports with UMLS concepts, which has been used to code over 450,000 surgical pathology reports at our institution. In addition to coding UMLS terms, it annotates values of several key variables, such as TNM stage and cancer grade. The object of this study was to evaluate the potential and limitations of automated extraction of these variables, by measuring the performance of the system against a true gold standard - manually encoded data entered by expert tissue annotators. We categorized and analyzed errors to determine the potential and limitations of information extraction from pathology reports for the purpose of automated biospecimen annotation.


Social Networking:
Share |


Item Type: Article
Status: Published
CreatorsEmailPitt UsernameORCID
Liu, K
Mitchell, KJkjm84@pitt.eduKJM84
Chapman, WW
Crowley, RS
Date: 1 January 2005
Date Type: Publication
Journal or Publication Title: AMIA ... Annual Symposium proceedings / AMIA Symposium. AMIA Symposium
Page Range: 460 - 464
Event Type: Conference
Schools and Programs: School of Medicine > Biomedical Informatics
Refereed: Yes
MeSH Headings: Abstracting and Indexing as Topic--methods; Abstracting and Indexing as Topic--standards; Algorithms; Automatic Data Processing; Clinical Laboratory Information Systems; Computer Communication Networks; Feasibility Studies; Humans; Information Storage and Retrieval; Medical Informatics Applications; Medical Records Systems, Computerized; Natural Language Processing; Pathology, Surgical; Tissue Banks; Unified Medical Language System
Other ID: NLM PMC1560700
PubMed Central ID: PMC1560700
PubMed ID: 16779082
Date Deposited: 29 Aug 2012 21:04
Last Modified: 03 Feb 2019 00:55


Monthly Views for the past 3 years

Plum Analytics

Actions (login required)

View Item View Item