PT  - JOURNAL ARTICLE
AU  - Garies, Stephanie
AU  - Taylor, Matt
AU  - Soos, Boglarka
AU  - Lindeman, Cliff
AU  - Drummond, Neil
AU  - Pham, Anh
AU  - Aponte-Hao, Zhi
AU  - Williamson, Tyler
TI  - Using machine learning to standardize medication records in a pan-Canadian electronic medical record database: a data-driven algorithm study focused on antibiotics prescribed in primary care
AID  - 10.9778/cmajo.20220235
DP  - 2023 Sep 01
TA  - CMAJ Open
PG  - E1020--E1024
VI  - 11
IP  - 5
4099  - http://www.cmajopen.ca/content/11/5/E1020.short
4100  - http://www.cmajopen.ca/content/11/5/E1020.full
SO  - CMAJ2023 Sep 01; 11
AB  - Background: Most antibiotics dispensed by community pharmacies in Canada are prescribed by family physicians, but using the prescribing information contained within primary care electronic medical records (EMRs) for secondary purposes can be challenging owing to variable data quality. We used antibiotic medications as an exemplar to validate a machine-learning approach for cleaning and coding medication data in a pan-Canadian primary care EMR database.Methods: The Canadian Primary Care Sentinel Surveillance Network database contained an estimated 42 million medication records, which we mapped to an Anatomic Therapeutic Chemical (ATC) code by applying a semisupervised classification model developed using reference standard labels derived from the Health Canada Drug Product Database. We validated the resulting ATC codes in a subset of antibiotic records (16 119 unique strings) to determine whether the algorithm correctly classified the medication according to manual review of the original medication record.Results: In the antibiotic subset, the algorithm showed high validity (sensitivity 99.5%, specificity 92.4%, positive predictive value 98.6%, negative predictive value 97.0%) in classifying whether the medication was an antibiotic.Interpretation: Our machine-learning algorithm classified unstructured antibiotic medication data from primary care with a high degree of accuracy. Access to cleaned EMR data can support important secondary uses, including community-based antibiotic prescribing surveillance and practice improvement.