Limits...
Mining Electronic Health Records using Linked Data.

Odgers DJ, Dumontier M - AMIA Jt Summits Transl Sci Proc (2015)

Bottom Line: In order to realize the potential of using these data for translational research, clinical data warehouses must be interoperable with standardized health terminologies, biomedical ontologies, and growing networks of Linked Open Data such as Bio2RDF.We demonstrate the utility of this system though basic cohort selection, phenotypic profiling, and identification of disease genes.This work is significant in that it demonstrates the feasibility of using semantic web technologies to directly exploit existing biomedical ontologies and Linked Open Data.

View Article: PubMed Central - PubMed

Affiliation: Stanford Center for Biomedical Informatics Research, Stanford University, Stanford, CA.

ABSTRACT
Meaningful Use guidelines have pushed the United States Healthcare System to adopt electronic health record systems (EHRs) at an unprecedented rate. Hospitals and medical centers are providing access to clinical data via clinical data warehouses such as i2b2, or Stanford's STRIDE database. In order to realize the potential of using these data for translational research, clinical data warehouses must be interoperable with standardized health terminologies, biomedical ontologies, and growing networks of Linked Open Data such as Bio2RDF. Applying the principles of Linked Data, we transformed a de-identified version of the STRIDE into a semantic clinical data warehouse containing visits, labs, diagnoses, prescriptions, and annotated clinical notes. We demonstrate the utility of this system though basic cohort selection, phenotypic profiling, and identification of disease genes. This work is significant in that it demonstrates the feasibility of using semantic web technologies to directly exploit existing biomedical ontologies and Linked Open Data.

No MeSH data available.


Related in: MedlinePlus

STRIDE2RDF Architecture.
© Copyright Policy
Related In: Results  -  Collection


getmorefigures.php?uid=PMC4525267&req=5

f2-2091678: STRIDE2RDF Architecture.

Mentions: We evaluated our system with a set of 10 questions, of which 3 are presented below. Our queries were executed from an end user console, behind a firewall, as depicted figure 2. These exemplar queries demonstrate that we can build patient cohorts using selected attributes - coded diagnoses and clinical note annotations - and connect into selected biomedical terminologies and Linked Datasets - OMIM 22, SIDER 23. The questions relate to Mucopolysaccharidosis, a group of rare metabolic disorders caused by dysfunction in lysosomal storage enzymes. The first question uses diagnoses associated with patient visits to identify other diseases that are experienced by the patient throughout their lifetime. The second question uses Bio2RDF’s version of OMIM to identify disease genes that are associated with the co-morbid diseases. The third question uses ICD9, RxNorm, and SIDER to identify known drug side effects that are experienced by Mucopolysaccharidosis patients taking Trometamine for metabolic acidosis.


Mining Electronic Health Records using Linked Data.

Odgers DJ, Dumontier M - AMIA Jt Summits Transl Sci Proc (2015)

STRIDE2RDF Architecture.
© Copyright Policy
Related In: Results  -  Collection

Show All Figures
getmorefigures.php?uid=PMC4525267&req=5

f2-2091678: STRIDE2RDF Architecture.
Mentions: We evaluated our system with a set of 10 questions, of which 3 are presented below. Our queries were executed from an end user console, behind a firewall, as depicted figure 2. These exemplar queries demonstrate that we can build patient cohorts using selected attributes - coded diagnoses and clinical note annotations - and connect into selected biomedical terminologies and Linked Datasets - OMIM 22, SIDER 23. The questions relate to Mucopolysaccharidosis, a group of rare metabolic disorders caused by dysfunction in lysosomal storage enzymes. The first question uses diagnoses associated with patient visits to identify other diseases that are experienced by the patient throughout their lifetime. The second question uses Bio2RDF’s version of OMIM to identify disease genes that are associated with the co-morbid diseases. The third question uses ICD9, RxNorm, and SIDER to identify known drug side effects that are experienced by Mucopolysaccharidosis patients taking Trometamine for metabolic acidosis.

Bottom Line: In order to realize the potential of using these data for translational research, clinical data warehouses must be interoperable with standardized health terminologies, biomedical ontologies, and growing networks of Linked Open Data such as Bio2RDF.We demonstrate the utility of this system though basic cohort selection, phenotypic profiling, and identification of disease genes.This work is significant in that it demonstrates the feasibility of using semantic web technologies to directly exploit existing biomedical ontologies and Linked Open Data.

View Article: PubMed Central - PubMed

Affiliation: Stanford Center for Biomedical Informatics Research, Stanford University, Stanford, CA.

ABSTRACT
Meaningful Use guidelines have pushed the United States Healthcare System to adopt electronic health record systems (EHRs) at an unprecedented rate. Hospitals and medical centers are providing access to clinical data via clinical data warehouses such as i2b2, or Stanford's STRIDE database. In order to realize the potential of using these data for translational research, clinical data warehouses must be interoperable with standardized health terminologies, biomedical ontologies, and growing networks of Linked Open Data such as Bio2RDF. Applying the principles of Linked Data, we transformed a de-identified version of the STRIDE into a semantic clinical data warehouse containing visits, labs, diagnoses, prescriptions, and annotated clinical notes. We demonstrate the utility of this system though basic cohort selection, phenotypic profiling, and identification of disease genes. This work is significant in that it demonstrates the feasibility of using semantic web technologies to directly exploit existing biomedical ontologies and Linked Open Data.

No MeSH data available.


Related in: MedlinePlus