Extracting Information from Summary of Product Characteristics for Improving Drugs Prescription Safety

Abstract : Information about medications is critical in supporting decision-making during the prescription process and thus in improving the safety and quality of care. The Summary of Product Characteristics (SPC) represents the basis of information for health professionals on how to use medicines. However, this information is locked in free-text and, as such, cannot be actively accessed and elaborated by computerized applications. In this work, we propose a machine learning based system for the automatic recognition of drug-related entities (active ingredient, interaction effects, etc.) in SPCs, focusing on drug interactions. Our approach learns to classify this information in a structured prediction framework, relying on conditional random fields. The classifier is trained and evaluated using a corpus of a hundred SPCs. They have been hand-annotated with thirteen semantic labels that have been derived from a previously developed domain ontology. Our evaluations show that the model exhibits high overall performance, with an average F1-measure of about 90%.
Document type :
Conference papers
Complete list of metadatas

https://hal.archives-ouvertes.fr/hal-00637738
Contributor : Alexander A. Spengler <>
Submitted on : Wednesday, November 2, 2011 - 5:52:56 PM
Last modification on : Thursday, March 21, 2019 - 1:07:37 PM

Links full text

Identifiers

Citation

Stefania Rubrichi, Silvana Quaglini, Alexander A. Spengler, Patrick Gallinari. Extracting Information from Summary of Product Characteristics for Improving Drugs Prescription Safety. 13th Conference on Artificial Intelligence in Medicine (AIME 2011), Jul 2011, Bled, Slovenia. pp.327-337, ⟨10.1007/978-3-642-22218-4_42⟩. ⟨hal-00637738⟩

Share

Metrics

Record views

97