Medication and Adverse Event Extraction from Noisy Text

Medication and Adverse Event Extraction from Noisy Text Xiang Dai1,2, Sarvnaz Karimi1, and Cecile Paris1 1CSIRO Data61, Marsfield, NSW, Australia 2School of Information Technologies, University of Sydney {dai.dai, sarvnaz.karimi, cecile.paris}@data61.csiro.au Abstract We investigate the problem of extracting mentions of medications and adverse drug events using sequence labelling and non- sequence labelling methods. We experi- ment with three different methods on two different datasets, one from a patient fo- rum with noisy text and one containing narrative patient records. An analysis of the output from these methods are reported to identify what types of named entities are best identified using these methods and, more specifically, how well the discon- tinuous and overlapping entities that are prevalent in our forum dataset are iden- tified. Our findings can guide studies to choose different methods based on the complexity of the named entities involved, in particular in text mining for pharma- covigilance. 1 Introduction An Adverse Drug Reaction (ADR) is an injury oc- curring after a drug (medication) is used at the rec- ommended dosage, for recommended symptoms. The practice of monitoring the ADRs of phar- maceutical products is known as pharmacovigi- lance [Alghabban, 2004]. Different from con- trolled clinical trials which are mainly conducted before drugs are licensed for use, pharmacovigi- lance is especially concerned with identifying pre- viously unreported adverse reactions. Text mining over different sources of information, such as elec- tronic health records and patient reports on health forums, can be one way of finding such potential adverse reactions. This is the area to which our work contributes. We note that when causality between an adverse reaction and a medication is not known, it is referred to as Adverse Drug Event (ADE) [Karimi et al., 2015c]. Extracting mentions of drugs and adverse events from social media is difficult for two main reasons. First, social media text contains collo- quial language and typographical mistakes. Refer- ences to the names of drugs, diseases, and ADEs are particularly prone to misspellings. Second, a medical concept can be considered both an ADE or a symptom in different contexts. For example, aches and pains is a symptom in the context of “I am only taking 75 mg a day and it is wonderful for relieving all of my aches and pains”, while it is an ADE in another post complaining of severe fatigue with aches and pains. We cast this concept extraction problem as a supervised Named Entity Recognition (NER) task, with drugs and ADEs as entity types. Named entity recognition itself has long been studied in different domains, including the biomedical domain. There are a number of chal- lenges that are associated with how named enti- ties are expressed in text. These include entities expressed as multiwords, especially if the entities are overlapping, discontinuous, or nested. Table 1 lists some examples of entity types of different complexities. Entities that consist of a discontinu- ous sequence of tokens are one of the more chal- lenging ones to recognise correctly, yet they con- stitute a large portion …

Content truncated to 500 words