Automatic generation of case-detection algorithms to identify children with asthma from large electronic health record databases
Article first published online: 17 APR 2013
Copyright © 2013 John Wiley & Sons, Ltd.
Pharmacoepidemiology and Drug Safety
Volume 22, Issue 8, pages 826–833, August 2013
How to Cite
Afzal, Z., Engelkes, M., Verhamme, K. M. C., Janssens, H. M., Sturkenboom, M. C. J. M., Kors, J. A. and Schuemie, M. J. (2013), Automatic generation of case-detection algorithms to identify children with asthma from large electronic health record databases. Pharmacoepidem. Drug Safe., 22: 826–833. doi: 10.1002/pds.3438
- Issue published online: 21 JUL 2013
- Article first published online: 17 APR 2013
- Manuscript Accepted: 25 FEB 2013
- Manuscript Revised: 21 JAN 2013
- Manuscript Received: 13 AUG 2012
- VICI. Grant Number: 91896632
- Priority Medicines voor Kinderen. Grant Number: 113201006
- case-detection algorithms;
- machine learning;
- electronic medical records;
- automated case definition;
Most electronic health record databases contain unstructured free-text narratives, which cannot be easily analyzed. Case-detection algorithms are usually created manually and often rely only on using coded information such as International Classification of Diseases version 9 codes. We applied a machine-learning approach to generate and evaluate an automated case-detection algorithm that uses both free-text and coded information to identify asthma cases.
The Integrated Primary Care Information (IPCI) database was searched for potential asthma patients aged 5–18 years using a broad query on asthma-related codes, drugs, and free text. A training set of 5032 patients was created by manually annotating the potential patients as definite, probable, or doubtful asthma cases or non-asthma cases. The rule-learning program RIPPER was then used to generate algorithms to distinguish cases from non-cases. An over-sampling method was used to balance the performance of the automated algorithm to meet our study requirements. Performance of the automated algorithm was evaluated against the manually annotated set.
The selected algorithm yielded a positive predictive value (PPV) of 0.66, sensitivity of 0.98, and specificity of 0.95 when identifying only definite asthma cases; a PPV of 0.82, sensitivity of 0.96, and specificity of 0.90 when identifying both definite and probable asthma cases; and a PPV of 0.57, sensitivity of 0.95, and specificity of 0.67 for the scenario identifying definite, probable, and doubtful asthma cases.
The automated algorithm shows good performance in detecting cases of asthma utilizing both free-text and coded data. This algorithm will facilitate large-scale studies of asthma in the IPCI database. Copyright © 2013 John Wiley & Sons, Ltd.