Objective: To tackle the extraction of adverse drug reaction events in electronic health records. The challenge stands in inferring a robust prediction model from highly unbalanced data. According to our manually annotated corpus, only 6% of the drug-disease entity pairs trigger a positive adverse drug reaction event and this low ratio makes machine learning tough.

Method: We present a hybrid system utilising a self-developed morpho-syntactic and semantic analyser for medical texts in Spanish. It performs named entity recognition of drugs and diseases and adverse drug reaction event extraction. The event extraction stage operates using rule-based and machine learning techniques.

Results: We assess both the base classifiers, namely a knowledge-based model and an inferred classifier, and also the resulting hybrid system. Moreover, for the machine learning approach, an analysis of each particular bio-cause triggering the adverse drug reaction is carried out.

Conclusions: One of the contributions of the machine learning based system is its ability to deal with both intra-sentence and inter-sentence events in a highly skewed classification environment. Moreover, the knowledge-based and the inferred model are complementary in terms of precision and recall. While the former provides high precision and low recall, the latter is the other way around. As a result, an appropriate hybrid approach seems to be able to benefit from both approaches and also improve them. This is the underlying motivation for selecting the hybrid approach. In addition, this is the first system dealing with real electronic health records in Spanish.