Using electronic patient records to discover disease correlations and stratify patient cohorts
Research output: Contribution to journal › Journal article › Research › peer-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 language | English |
---|---|
Journal | P L o S Computational Biology |
Volume | 7 |
Issue number | 8 |
Pages (from-to) | e1002141 |
Number of pages | 10 |
ISSN | 1553-734X |
DOIs | |
Publication status | Published - 2011 |
- Cluster Analysis, Cohort Studies, Comorbidity, Computational Biology, Data Collection, Data Mining, Electronic Health Records, Humans, International Classification of Diseases, Reproducibility of Results
Research areas
ID: 40167432