Replicating medication trend studies using ad hoc information extraction in a clinical data warehouse

Abstract

BackgroundMedication trend studies show the changes of medication over the years and may be replicated using a clinical Data Warehouse (CDW). Even nowadays, a lot of the patient information, like medication data, in the EHR is stored in the format of free text. As the conventional approach of information extraction (IE) demands a high developmental effort, we used ad hoc IE instead. This technique queries information and extracts it on the fly from texts contained in the CDW.MethodsWe present a generalizable approach of ad hoc IE for pharmacotherapy (medications and their daily dosage) presented in hospital discharge letters. We added import and query features to the CDW system, like error tolerant queries to deal with misspellings and proximity search for the extraction of the daily dosage. During the data integration process in the CDW, negated, historical and non-patient context data are filtered. For the replication studies, we used a drug list grouped by ATC (Anatomical Therapeutic Chemical Classification System) codes as input for queries to the CDW.ResultsWe achieve an F1 score of 0.983 (precision 0.997, recall 0.970) for extracting medication from discharge letters and an F1 score of 0.974 (precision 0.977, recall 0.972) for extracting the dosage. We replicated three published medical trend studies for hypertension, atrial fibrillation and chronic kidney disease. Overall, 93% of the main findings could be replicated, 68% of sub-findings, and 75% of all findings. One study could be completely replicated with all main and sub-findings.ConclusionA novel approach for ad hoc IE is presented. It is very suitable for basic medical texts like discharge letters and finding reports. Ad hoc IE is by definition more limited than conventional IE and does not claim to replace it, but it substantially exceeds the search capabilities of many CDWs and it is convenient to conduct replication studies fast and with high quality.

Structured, Harmonized, and Interoperable Integration of Clinical Routine Data to Compute Heart Failure Risk Scores

“…Our approach should be seen as a support for standard clinical studies. Conventional studies can, e.g., be motivated by such results or the results of conventional studies can be confirmed by research based on reused routine data [ 14 ].…”

Can antiepileptic efficacy and epilepsy variables be studied from electronic health records? A review of current approaches

“…While this review was not systematic, our comprehensive approach returned over 2000 articles by PubMed search criteria of which 128 articles were reviewed in detail. The key studies worth highlighting from this search include: 1) PEEP (phenotype extraction in epilepsy) which is highly accurate for medication dosing and extracts key information regarding epileptogenic zone, etiology, semiology and EEG patterns from EMU discharge summaries [9,10] and 2) ExECT (extraction of epilepsy clinical text) which extracts epilepsy diagnosis, epilepsy type, abnormal findings on imaging, and seizure frequency (albeit with some limitations) [28]. However, great variability in algorithm performance across variables persists.…”

“…The best pipeline for extraction of active medication ingredients and dosing achieves greater than 97 % F1s [9,10]. However, extracting the indication for each medication is more difficult, with the best group achieving F1 of 66 % [11].…”

Can antiepileptic drug efficacy be studied from electronic health records? A review of current approaches

“…[6,8] The best pipeline for extraction of active medication ingredients and dosing achieves greater than 97% F1s. [9,10] However, extracting the indication for each medication is more difficult, with the best group achieving F1 of 66%. [11] Extracting the indication is particularly important in the field of epilepsy, since many of our medications may be prescribed for alternative indications (e.g.…”