Shallow Medication Extraction from Hospital Patient Records

This paper presents methods for shallow Information Extraction (IE) from the free text zones of hospital Patient Records (PRs) in Bulgarian language in the Patient Safety through Intelligent Procedures in medication (PSIP) project. We extract automatically information about drug names, dosage, modes and frequency and assign the corresponding ATC code to each medication event. Using various modules for rule-based text analysis, our IE components in PSIP perform a significant amount of symbolic computations. We try to address negative statements, elliptical constructions, typical conjunctive phrases, and simple inferences concerning temporal constraints and finally aim at the assignment of the drug ACT code to the extracted medication events, which additionally complicates the extraction algorithm. The prototype of the system was used for experiments with a training corpus containing 1,300 PRs and the evaluation results are obtained using a test corpus containing 6,200 PRs. The extraction accuracy (f-score) for drug names is 98.42% and for dose 93.85%.