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

• Published in: PLoS computational biology Vol. 7; no. 8; p. e1002141
• Main Authors: Roque, Francisco S, Jensen, Peter B, Schmock, Henriette, Dalgaard, Marlene, Andreatta, Massimo, Hansen, Thomas, Søeby, Karen, Bredkjær, Søren, Juul, Anders, Werge, Thomas, Jensen, Lars J, Brunak, Søren
• Format: Journal Article
• Language: English
• Published: United States Public Library of Science 01.08.2011; Public Library of Science (PLoS)
• Subjects: Bias; Biology; Classification; Cluster Analysis; Codes; Cohort Studies; Comorbidity; Computational Biology - methods; Computer Science; Data Collection - methods; Data mining; Data Mining - methods; Disease; Electronic Health Records; Humans; International Classification of Diseases; Medical research; Medicine; Ontology; Patients; Reproducibility of Results; Studies; International Classification of Diseases; Reproducibility of Results; Comorbidity; Humans; Computational Biology; Data Mining; Data Collection; Electronic Health Records; Cluster Analysis; Cohort Studies
• ISSN: 1553-7358; 1553-734X; 1553-7358
• DOI: 10.1371/journal.pcbi.1002141

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.