Komenti: A semantic text mining framework

Slater, Luke T; Bradlow, William; Hoehndorf, Robert; Motti, Dino FA; Ball, Simon; Gkoutos, Georgios V

Summary Komenti is a reasoner-enabled semantic query and information extraction framework. It is the only text mining tool that enables querying inferred knowledge from biomedical ontologies. It also contains multiple novel components for vocabulary construction and context disambiguation, which can improve the power of text mining and ontology-based analysis tasks, with a view towards making full use of the semantic provision of biomedical ontologies for text characterisation and analysis. Here, we describe Komenti and its features, and present a use case wherein we automate a clinical audit, extracting medications for hypertrophic cardiomyopathy patients from text, revealing a high precision, and identifying a sub-cohort of patients with atrial fibrillation who are not anti-coagulated, and are therefore at a higher risk of stroke. Availability and Implementation Komenti is freely available under an open source licence at http://github.com/reality/komenti. More information concerning the use-case is available in supplementary data.