Data integration of structured and unstructured sources for assigning clinical codes to patient staysData integration of structured and unstructured sources for assigning clinical codes to patient stays
Faculty of Sciences. Mathematics and Computer Science
Faculty of Medicine and Health Sciences
Faculty of Arts. Linguistics and Literature
Research group
Advanced Database Research and Modeling (ADReM)
Centre for Computational Linguistics and Psycholinguistics (CLiPS)
Publication type
Philadelphia, Pa,
Computer. Automation
Source (journal)
Journal of the American Medical Informatics Association. - Philadelphia, Pa
Target language
English (eng)
Full text (Publishers DOI)
University of Antwerp
OBJECTIVE: Enormous amounts of healthcare data are becoming increasingly accessible through the large-scale adoption of electronic health records. In this work, structured and unstructured (textual) data are combined to assign clinical diagnostic and procedural codes (specifically ICD-9-CM) to patient stays. We investigate whether integrating these heterogeneous data types improves prediction strength compared to using the data types in isolation. METHODS: Two separate data integration approaches were evaluated. Early data integration combines features of several sources within a single model, and late data integration learns a separate model per data source and combines these predictions with a meta-learner. This is evaluated on data sources and clinical codes from a broad set of medical specialties. RESULTS: When compared with the best individual prediction source, late data integration leads to improvements in predictive power (eg, overall F-measure increased from 30.6% to 38.3% for International Classification of Diseases, Ninth Revision, Clinical Modification (ICD-9-CM) diagnostic codes), while early data integration is less consistent. The predictive strength strongly differs between medical specialties, both for ICD-9-CM diagnostic and procedural codes. DISCUSSION: Structured data provides complementary information to unstructured data (and vice versa) for predicting ICD-9-CM codes. This can be captured most effectively by the proposed late data integration approach. CONCLUSIONS: We demonstrated that models using multiple electronic health record data sources systematically outperform models using data sources in isolation in the task of predicting ICD-9-CM codes over a broad range of medical specialties.