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 language||English (US)|
|Number of pages||5|
|Journal||AMIA ... Annual Symposium proceedings / AMIA Symposium. AMIA Symposium|
|State||Published - 2008|
ASJC Scopus subject areas