A Chronic Illness System Using Biomedical Knowledge Sources and Relevance Feedback

CISS+ is a new surveillance system designed to aid clinicians seeking to help patients make healthy decisions about their lifestyle and health. It takes clinical records as queries anduses these records to find articles in the scientific literature that describe risk factors relevant to the patients' history and medical state. CISS+ is a revision of the earlier CISS system, which useda simple n-gram text retrieval strategy. CISS+ enhances CISS byusing higher-relevance terms and concepts taken from the UMLS and MetaMap systems and by using automated techniques related to relevance feedback to refine queries. CISS+ was evaluated viaa small set of experimental queries that were sent to other widely available biomedical research search systems. CISS+ returned asmall number of results that had better relevance to the goal of identifying risks factors.

[1]  Falk Scholer,et al.  Quantifying the impact of concept recognition on biomedical information retrieval , 2012, Inf. Process. Manag..

[2]  D. Barker.  Fetal and infant origins of adult disease , 2001, Monatsschrift Kinderheilkunde.

[3]  James Bailey,et al.  Improving MeSH classification of biomedical articles using citation contexts , 2011, J. Biomed. Informatics.

[4]  Luo Si,et al.  Combining Multiple Resources, Evidences and Criteria for Genomic Information Retrieval , 2006, TREC.

[5]  Alan R. Aronson,et al.  An overview of MetaMap: historical perspective and recent advances , 2010, J. Am. Medical Informatics Assoc..

[6]  Marcelo Fiszman,et al.  Interpreting comparative constructions in biomedical text , 2007, BioNLP@ACL.

[7]  Rong Chen,et al.  Ontology-driven indexing of public datasets for translational bioinformatics , 2009, BMC Bioinformatics.

[8]  J. J. Rocchio,et al.  Relevance feedback in information retrieval , 1971 .

[9]  Alan R. Aronson,et al.  Effective mapping of biomedical text to the UMLS Metathesaurus: the MetaMap program , 2001, AMIA.

[10]  Marcelo Fiszman,et al.  The interaction of domain knowledge and linguistic structure in natural language processing: interpreting hypernymic propositions in biomedical text , 2003, J. Biomed. Informatics.

[11]  Sooyoung Yoo,et al.  Semantic concept-enriched dependence model for medical information retrieval , 2014, J. Biomed. Informatics.

[12]  William R. Hersh,et al.  Information Retrieval: A Health and Biomedical Perspective , 2002 .

[13]  Juliana Tarossi Pollettini,et al.  Surveillance for the prevention of chronic diseases through information association , 2014, BMC Medical Genomics.

[14]  Nikola K. Kasabov,et al.  Ontology Based Personalized Modeling for Chronic Disease Risk Analysis: An Integrated Approach , 2008, Aust. J. Intell. Inf. Process. Syst..

[15]  Zhoujun Li,et al.  Promoting Ranking Diversity for Biomedical Information Retrieval Using Wikipedia , 2010, ECIR.