P-38 Automatic summarization of clinical abstracts for evidence-based medicine
Presenter Status
Department of Engineering and Computer Science
Second Presenter Status
Department of Computer Science
Third Presenter Status
MS Student in Computer Science
Fourth Presenter Status
MS Student in Computer Science
Fifth Presenter Status
Department of Pediatrics
Sixth Presenter Status
Department of Pediatrics and Department of Medical Education
Location
Buller Hallway
Start Date
1-11-2013 1:30 PM
End Date
1-11-2013 3:00 PM
Presentation Abstract
A central concern in Evidence Based Medicine (EBM) is how to convey research results effectively to practitioners. One important idea is to summarize results by key summary statistics that describe the effectiveness (or lack thereof) of a given intervention, specifically the absolute risk reduction (ARR) and number needed to treat (NNT). Manual summarization is slow and expensive, thus, with the exponential growth of the biomedical research literature, automated solutions are needed. We have developed a novel machine learning-based software system that generates EBM-oriented summaries from research abstracts of randomized controlled trials. The system has learned to identify descriptions of the treatment groups and outcomes, as well as various associated quantities. It distills these elements into summaries that include summary statistics calculated from the reported outcome values found in the text.
P-38 Automatic summarization of clinical abstracts for evidence-based medicine
Buller Hallway
A central concern in Evidence Based Medicine (EBM) is how to convey research results effectively to practitioners. One important idea is to summarize results by key summary statistics that describe the effectiveness (or lack thereof) of a given intervention, specifically the absolute risk reduction (ARR) and number needed to treat (NNT). Manual summarization is slow and expensive, thus, with the exponential growth of the biomedical research literature, automated solutions are needed. We have developed a novel machine learning-based software system that generates EBM-oriented summaries from research abstracts of randomized controlled trials. The system has learned to identify descriptions of the treatment groups and outcomes, as well as various associated quantities. It distills these elements into summaries that include summary statistics calculated from the reported outcome values found in the text.