Building a semantically annotated corpus for chronic disease complications using two document types

Narrative information in electronic health records (EHRs) contains a wealth of information related to patient health conditions. In addition, people use Twitter to express their experiences regarding personal health issues, such as medical complaints, symptoms, treatments, lifestyle, and other factors. Both genres of text include different types of health-related information concerning disease complications and risk factors. Knowing detailed information about controlling disease risk factors has a great impact on modifying these risks and subsequently preventing disease complications. Text-mining tools provide efficient solutions to extract and integrate vital information related to disease complications hidden in the large volume of the narrative text. However, the development of text-mining tools depends on the availability of an annotated corpus. In response, we have developed the PrevComp corpus, which is annotated with information relevant to the identification of disease complications, underlying risk factors, and prevention measures, in the context of the interaction between hypertension and diabetes. The corpus is unique and novel in terms of the very specific topic in the biomedical domain and as an integration of information from both EHRs and tweets collected from Twitter. The annotation scheme was designed with guidance by a domain expert, and two further domain experts performed the annotation, resulting in a high-quality annotation, with agreement rate F-scores as high as 0.60 and 0.75 for EHRs and tweets, respectively.