TY - JOUR

T1 - Using Electronic Patient Records to Discover Disease Correlations and Stratify Patient Cohorts

A1 - Roque,Francisco S.

A1 - Jensen,Peter B.

A1 - Schmock,Henriette

A1 - Dalgaard,Marlene

A1 - Andreatta,Massimo

A1 - Hansen,Thomas

A1 - Søeby,Karen

A1 - Bredkjaer,Søren

A1 - Juul,Anders

A1 - Werge,Thomas

A1 - Jensen,Lars J.

A1 - Brunak,Søren

AU - Roque,Francisco S.

AU - Jensen,Peter B.

AU - Schmock,Henriette

AU - Dalgaard,Marlene

AU - Andreatta,Massimo

AU - Hansen,Thomas

AU - Søeby,Karen

AU - Bredkjaer,Søren

AU - Juul,Anders

AU - Werge,Thomas

AU - Jensen,Lars J.

AU - Brunak,Søren

PB - Public Library of Science

PY - 2011

Y1 - 2011

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.

U2 - 10.1371/journal.pcbi.1002141

DO - 10.1371/journal.pcbi.1002141

JO - P L o S Computational Biology

JF - P L o S Computational Biology

SN - 1553-734X

IS - 8

VL - 7

ER -