SYRIAC: The systematic review information automated collection system a data warehouse for facilitating automated biomedical text classification.

Jianji J. Yang, Aaron Cohen, Marian McDonagh

Research output: Contribution to journalArticle

10 Citations (Scopus)

Abstract

Automatic document classification can be valuable in increasing the efficiency in updating systematic reviews (SR). In order for the machine learning process to work well, it is critical to create and maintain high-quality training datasets consisting of expert SR inclusion/exclusion decisions. This task can be laborious, especially when the number of topics is large and source data format is inconsistent.To approach this problem, we build an automated system to streamline the required steps, from initial notification of update in source annotation files to loading the data warehouse, along with a web interface to monitor the status of each topic. In our current collection of 26 SR topics, we were able to standardize almost all of the relevance judgments and recovered PMIDs for over 80% of all articles. Of those PMIDs, over 99% were correct in a manual random sample study. Our system performs an essential function in creating training and evaluation data sets for SR text mining research.

Original languageEnglish (US)
Pages (from-to)825-829
Number of pages5
JournalAMIA ... Annual Symposium proceedings / AMIA Symposium. AMIA Symposium
StatePublished - 2008

Fingerprint

Information Systems
Data Mining
Information Storage and Retrieval
Research
Datasets
Machine Learning

ASJC Scopus subject areas

  • Medicine(all)

Cite this

@article{1f8f25b68e3f4210ac29bf40a6d1bc95,
title = "SYRIAC: The systematic review information automated collection system a data warehouse for facilitating automated biomedical text classification.",
abstract = "Automatic document classification can be valuable in increasing the efficiency in updating systematic reviews (SR). In order for the machine learning process to work well, it is critical to create and maintain high-quality training datasets consisting of expert SR inclusion/exclusion decisions. This task can be laborious, especially when the number of topics is large and source data format is inconsistent.To approach this problem, we build an automated system to streamline the required steps, from initial notification of update in source annotation files to loading the data warehouse, along with a web interface to monitor the status of each topic. In our current collection of 26 SR topics, we were able to standardize almost all of the relevance judgments and recovered PMIDs for over 80{\%} of all articles. Of those PMIDs, over 99{\%} were correct in a manual random sample study. Our system performs an essential function in creating training and evaluation data sets for SR text mining research.",
author = "Yang, {Jianji J.} and Aaron Cohen and Marian McDonagh",
year = "2008",
language = "English (US)",
pages = "825--829",
journal = "AMIA ... Annual Symposium proceedings / AMIA Symposium. AMIA Symposium",
issn = "1559-4076",
publisher = "American Medical Informatics Association",

}

TY - JOUR

T1 - SYRIAC

T2 - The systematic review information automated collection system a data warehouse for facilitating automated biomedical text classification.

AU - Yang, Jianji J.

AU - Cohen, Aaron

AU - McDonagh, Marian

PY - 2008

Y1 - 2008

N2 - Automatic document classification can be valuable in increasing the efficiency in updating systematic reviews (SR). In order for the machine learning process to work well, it is critical to create and maintain high-quality training datasets consisting of expert SR inclusion/exclusion decisions. This task can be laborious, especially when the number of topics is large and source data format is inconsistent.To approach this problem, we build an automated system to streamline the required steps, from initial notification of update in source annotation files to loading the data warehouse, along with a web interface to monitor the status of each topic. In our current collection of 26 SR topics, we were able to standardize almost all of the relevance judgments and recovered PMIDs for over 80% of all articles. Of those PMIDs, over 99% were correct in a manual random sample study. Our system performs an essential function in creating training and evaluation data sets for SR text mining research.

AB - Automatic document classification can be valuable in increasing the efficiency in updating systematic reviews (SR). In order for the machine learning process to work well, it is critical to create and maintain high-quality training datasets consisting of expert SR inclusion/exclusion decisions. This task can be laborious, especially when the number of topics is large and source data format is inconsistent.To approach this problem, we build an automated system to streamline the required steps, from initial notification of update in source annotation files to loading the data warehouse, along with a web interface to monitor the status of each topic. In our current collection of 26 SR topics, we were able to standardize almost all of the relevance judgments and recovered PMIDs for over 80% of all articles. Of those PMIDs, over 99% were correct in a manual random sample study. Our system performs an essential function in creating training and evaluation data sets for SR text mining research.

UR - http://www.scopus.com/inward/record.url?scp=69549138794&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=69549138794&partnerID=8YFLogxK

M3 - Article

C2 - 18999194

AN - SCOPUS:69549138794

SP - 825

EP - 829

JO - AMIA ... Annual Symposium proceedings / AMIA Symposium. AMIA Symposium

JF - AMIA ... Annual Symposium proceedings / AMIA Symposium. AMIA Symposium

SN - 1559-4076

ER -