From Natural Language Descriptions in Clinical Guidelines to Relationships in an Ontology

Knowledge Engineering allows to automate entity recognition and relation extraction from clinical texts, which in turn can be used to facilitate clinical practice guideline (CPG) modeling. This paper presents a method to recognize diagnosis and therapy entities, and to identify relationships between these entities from CPG free-text documents. Our approach applies a sequential combination of several basic methods classically used in knowledge engineering (natural language processing techniques, manually authored grammars, lexicons and ontologies), to gradually map sentences describing diagnostic and therapeutic procedures to an ontology. First, using a standardized vocabulary, our method automatically identifies guideline concepts. Next, for each sentence, it determines the patient conditions under which the descriptive knowledge of the sentence is valid. Then, it detects the central information units in the sentence, in order to match the sentence with a small set of predefined relationships. The approach enables automated extraction of relationships about findings that have manifestation in a disease, and procedures that diagnose or treat a disease.

[1]  Asunción Gómez-Pérez,et al.  Ontological Engineering: With Examples from the Areas of Knowledge Management, e-Commerce and the Semantic Web , 2004, Advanced Information and Knowledge Processing.

[2]  Olivier Bodenreider,et al.  Chapter 3 Lexical, terminological and ontological resources for biological text mining , 2006 .

[3]  A. Hoes,et al.  Guidelines for the diagnosis and treatment of chronic heart failure: executive summary (update 2005): The Task Force for the Diagnosis and Treatment of Chronic Heart Failure of the European Society of Cardiology. , 2005, European heart journal.

[4]  Robert Stevens,et al.  Process of Building a Vocabulary for the Infection Domain , 2008, 2008 21st IEEE International Symposium on Computer-Based Medical Systems.

[5]  Katharina Kaiser,et al.  How can information extraction ease formalizing treatment processes in clinical practice guidelines?: A method and its evaluation , 2007, Artif. Intell. Medicine.

[6]  Ling Liu,et al.  Encyclopedia of Database Systems , 2009, Encyclopedia of Database Systems.

[7]  Arie Hasman,et al.  Approaches for creating computer-interpretable guidelines that facilitate decision support , 2004, Artif. Intell. Medicine.

[8]  Wendy W. Chapman,et al.  A Simple Algorithm for Identifying Negated Findings and Diseases in Discharge Summaries , 2001, J. Biomed. Informatics.

[9]  John Fox,et al.  Application of Information Technology: The Syntax and Semantics of the PROforma Guideline Modeling Language , 2003, J. Am. Medical Informatics Assoc..

[10]  Antonio Moreno,et al.  Computer-based execution of clinical guidelines: A review , 2008, Int. J. Medical Informatics.

[11]  Frank van Harmelen,et al.  Extraction and use of linguistic patterns for modelling medical guidelines , 2007, Artif. Intell. Medicine.

[12]  Robert H. Baud,et al.  A Multilingual Analyser ofMedical Texts , 1994, ICCS.

[13]  Oren Etzioni,et al.  PRODIGY: an integrated architecture for planning and learning , 1991, SGAR.

[14]  Silvana Quaglini,et al.  Architectures and tools for innovative Health Information Systems: The Guide Project , 2005, Int. J. Medical Informatics.

[15]  Yuval Shahar,et al.  Synthesis of Research: EON: A Component-Based Approach to Automation of Protocol-Directed Therapy , 1996, J. Am. Medical Informatics Assoc..

[16]  K Denecke,et al.  Semantic Structuring of and Information Extraction from Medical Documents Using the UMLS , 2008, Methods of Information in Medicine.

[17]  Dimitra Alexopoulou,et al.  Word Sense Disambiguation in biomedical ontologies with term co-occurrence analysis and document clustering , 2008, Int. J. Data Min. Bioinform..

[18]  A. Hoes,et al.  [Guidelines for the Diagnosis and Treatment of Chronic Heart Failure: executive summary (update 2005)]. , 2005, Revista espanola de cardiologia.

[19]  Sophia Ananiadou,et al.  Text Mining for Biology And Biomedicine , 2005 .

[20]  Karl Swedberg,et al.  Prognostic relevance of atrial fibrillation in patients with chronic heart failure on long-term treatment with beta-blockers: results from COMET. , 2005, European heart journal.

[21]  Omolola Ogunyemi,et al.  GLIF3: a representation format for sharable computer-interpretable clinical practice guidelines , 2004, J. Biomed. Informatics.

[22]  W W Rosser,et al.  Promoting effective guideline use in Ontario. , 2001, CMAJ : Canadian Medical Association journal = journal de l'Association medicale canadienne.

[23]  F A Sonnenberg,et al.  Computer-Interpretable Clinical Practice Guidelines , 2006, Yearbook of Medical Informatics.

[24]  Hongfang Liu,et al.  Evaluating the UMLS as a source of lexical knowledge for medical language processing , 2001, AMIA.

[25]  Henrik Eriksson,et al.  The evolution of Protégé: an environment for knowledge-based systems development , 2003, Int. J. Hum. Comput. Stud..

[26]  Yuval Shahar,et al.  ASBRU: A TASK-SPECIFIC, INTENTION-BASED, AND TIME-ORIENTED LANGUAGE FOR REPRESENTING SKELETAL PLANS , 1999 .

[27]  Yuval Shahar,et al.  AsbruView: Capturing Complex, Time-Oriented Plans - Beyond Flow Charts , 2002, Diagrammatic Representation and Reasoning.

[28]  D. Lindberg,et al.  The Unified Medical Language System , 1993, Methods of Information in Medicine.