Search

Narrative information in Electronic Health Records (EHRs) contains a wealth of clinical information about treatments, diagnosis, medication and family history. In addition, the scientific literature represents a rich source of information that summarises the latest results and new research findings relevant to different diseases. These two textual sources often contain different types of valuable phenotypic information that may be complementary to each other. Combining details from each source thus has the potential to be useful in uncovering new disease-phenotypic associations. In turn, these associations can help to identify patients with high risk factors, and they can be useful in developing solutions to control the causes responsible for the development of different diseases. However, clinicians at the point of care have limited time to review the large volume of potentially useful information that is locked away in unstructured text format. This in turn limits the utility of this “raw” information to clinical practitioners and computerised applications. Accordingly, the provision of automated and efficient means to extract, combine and present phenotype information that may be scattered amongst a large number of different textual sources in an easily digestible format is a prerequisite to the effective use and comprehensive understanding of details contained within both the records and the literature. The development of such facilities can in turn help in deriving information about disease correlations and supporting clinical decisions. This thesis is the first comprehensive study focussing on extracting and integrating phenotypic information from two different biomedical sources using Text Mining (TM) techniques. In this research, we describe our work on (1) extracting phenotypic information from both EHRs and the biomedical literature; (2) extracting the relations between phenotypic information and distilling them from EHRs using an event-based approach; and (3) using normalisation methods to link the phenotypic information found in EHRs with associated mentions found in the literature as a first step towards the automatic integration of information from these heterogeneous sources.

Background Phenotypic information locked away in unstructured narrative text presents significant barriers to information accessibility, both for clinical practitioners and for computerised applications used for clinical research purposes. Text mining (TM) techniques have previously been applied successfully to extract different types of information from text in the biomedical domain. They have the potential to be extended to allow the extraction of information relating to phenotypes from free text. Methods To stimulate the development of TM systems that are able to extract phenotypic information from text, we have created a new corpus (PhenoCHF) that is annotated by domain experts with several types of phenotypic information relating to congestive heart failure. To ensure that systems developed using the corpus are robust to multiple text types, it integrates text from heterogeneous sources, i.e., electronic health records (EHRs) and scientific articles from the literature. We have developed several different phenotype extraction methods to demonstrate the utility of the corpus, and tested these methods on a further corpus, i.e., ShARe/CLEF 2013. Results Evaluation of our automated methods showed that PhenoCHF can facilitate the training of reliable phenotype extraction systems, which are robust to variations in text type. These results have been reinforced by evaluating our trained systems on the ShARe/CLEF corpus, which contains clinical records of various types. Like other studies within the biomedical domain, we found that solutions based on conditional random fields produced the best results, when coupled with a rich feature set. Conclusions PhenoCHF is the first annotated corpus aimed at encoding detailed phenotypic information. The unique heterogeneous composition of the corpus has been shown to be advantageous in the training of systems that can accurately extract phenotypic information from a range of different text types. Although the scope of our annotation is currently limited to a single disease, the promising results achieved can stimulate further work into the extraction of phenotypic information for other diseases. The PhenoCHF annotation guidelines and annotations are publicly available at https://code.google.com/p/phenochf-corpus.