Using electronic patient records to discover disease correlations and stratify patient cohorts

Research output: Contribution to journalJournal articlepeer-review

Electronic patient records remain a rather unexplored, but potentially rich data source for discovering correlations between diseases. We describe a general approach for gathering phenotypic descriptions of patients from medical records in a systematic and non-cohort dependent manner. By extracting phenotype information from the free-text in such records we demonstrate that we can extend the information contained in the structured record data, and use it for producing fine-grained patient stratification and disease co-occurrence statistics. The approach uses a dictionary based on the International Classification of Disease ontology and is therefore in principle language independent. As a use case we show how records from a Danish psychiatric hospital lead to the identification of disease correlations, which subsequently can be mapped to systems biology frameworks.
Original languageEnglish
JournalP L o S Computational Biology
Volume7
Issue number8
Pages (from-to)e1002141
Number of pages10
ISSN1553-734X
DOIs
Publication statusPublished - 2011

    Research areas

  • Cluster Analysis, Cohort Studies, Comorbidity, Computational Biology, Data Collection, Data Mining, Electronic Health Records, Humans, International Classification of Diseases, Reproducibility of Results

ID: 40167432