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

TY - JOUR

T1 - Using electronic patient records to discover disease correlations and stratify patient cohorts

AU - Roque, Francisco S

AU - Jensen, Peter B

AU - Schmock, Henriette

AU - Dalgaard, Marlene

AU - Andreatta, Massimo

AU - Hansen, Thomas

AU - Søeby, Karen

AU - Bredkjær, Søren

AU - Juul, Anders

AU - Werge, Thomas

AU - Jensen, Lars J

AU - Brunak, Søren

PY - 2011/8

Y1 - 2011/8

N2 - 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.

AB - 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.

KW - Cluster Analysis

KW - Cohort Studies

KW - Comorbidity

KW - Computational Biology

KW - Data Collection

KW - Data Mining

KW - Electronic Health Records

KW - Humans

KW - International Classification of Diseases

KW - Reproducibility of Results

U2 - 10.1371/journal.pcbi.1002141

DO - 10.1371/journal.pcbi.1002141

M3 - Journal article

C2 - 21901084

SN - 1553-734X

VL - 7

SP - e1002141

JO - P L o S Computational Biology (Online)

JF - P L o S Computational Biology (Online)

IS - 8

ER -