Automatic Decision Support for Clinical Diagnostic Literature Using Link Analysis in a Weighted Keyword Network.

We present a novel approach to recommending articles from the medical literature that support clinical diagnostic decision-making, giving detailed descriptions of the associated ideas and principles. The specific goal is to retrieve biomedical articles that help answer questions of a specified type about a particular case. Based on the filtered keywords, MeSH(Medical Subject Headings) lexicon and the automatically extracted acronyms, the relationship between keywords and articles was built. The paper gives a detailed description of the process of by which keywords were measured and relevant articles identified based on link analysis in a weighted keywords network. Some important challenges identified in this study include the extraction of diagnosis-related keywords and a collection of valid sentences based on the keyword co-occurrence analysis and existing descriptions of symptoms. All data were taken from medical articles provided in the TREC (Text Retrieval Conference) clinical decision support track 2015. Ten standard topics and one demonstration topic were tested. In each case, a maximum of five articles with the highest relevance were returned. The total user satisfaction of 3.98 was 33% higher than average. The results also suggested that the smaller the number of results, the higher the average satisfaction. However, a few shortcomings were also revealed since medical literature recommendation for clinical diagnostic decision support is so complex a topic that it cannot be fully addressed through the semantic information carried solely by keywords in existing descriptions of symptoms. Nevertheless, the fact that these articles are actually relevant will no doubt inspire future research.

Improving the Quality and Utility of Electronic Health Record Data through Ontologies.

The translational research community, in general, and the Clinical and Translational Science Awards (CTSA) community, in particular, share the vision of repurposing EHRs for research that will improve the quality of clinical practice. Many members of these communities are also aware that electronic health records (EHRs) suffer limitations of data becoming poorly structured, biased, and unusable out of original context. This creates obstacles to the continuity of care, utility, quality improvement, and translational research. Analogous limitations to sharing objective data in other areas of the natural sciences have been successfully overcome by developing and using common ontologies. This White Paper presents the authors' rationale for the use of ontologies with computable semantics for the improvement of clinical data quality and EHR usability formulated for researchers with a stake in clinical and translational science and who are advocates for the use of information technology in medicine but at the same time are concerned by current major shortfalls. This White Paper outlines pitfalls, opportunities, and solutions and recommends increased investment in research and development of ontologies with computable semantics for a new generation of EHRs.

Semantic representation of consumer questions and physician answers.

The aim of this study was to identify the underlying semantics of health consumers' questions and physicians' answers in order to analyze the semantic patterns within these texts. We manually identified semantic relationships within question-answer pairs from Ask-the-Doctor Web sites. Identification of the semantic relationship instances within the texts was based on the relationship classes and structure of the Unified Medical Language System (UMLS) Semantic Network. We calculated the frequency of occurrence of each semantic relationship class, and conceptual graphs were generated, joining concepts together through the semantic relationships identified. We then analyzed whether representations of physician's answers exactly matched the form of the question representations. Lastly, we examined characteristics of the answer conceptual graphs. We identified 97 semantic relationship instances in the questions and 334 instances in the answers. The most frequently identified semantic relationship in both questions and answers was brings_about (causal). We found that the semantic relationship propositions identified in answers that most frequently contain a concept also expressed in the question were: brings_about, isa, co_occurs_with, diagnoses, and treats. Using extracted semantic relationships from real-life questions and answers can produce a valuable analysis of the characteristics of these texts. This can lead to clues for creating semantic-based retrieval techniques that guide users to further information. For example, we determined that both consumers and physicians often express causative relationships and these play a key role in leading to further related concepts.

A Metrics Ontology. An intellectual infrastructure for defining, managing, and applying metrics.

This paper presents the beginnings of a comprehensive ontology for organizing information about metrics and its potential application to defining and managing metrics in the CTSA (Clinical and Translational Science Award) project. The aim is to support an integrated database of all metrics used by CTSA components. The ontology is given as an entity-relationship conceptual data schema. Its completion should draw on metrics definition templates that can be found in many places.

Helping healthcare consumers understand: an "interpretive layer" for finding and making sense of medical information.

Healthcare consumers need to find, comprehend, and interpret health information before making informed decisions. Recent work by others and our own work suggest that mis-matches in representations of health information used by consumers and professionals occur at different levels of knowledge representation, such as terminology (i.e., form or surface structure and concept or meaning) and semantic relation-ships. A challenge for consumer health informatics research is to devise a comprehensive strategy to bridge the gap between consumer understanding and biomedical knowledge at all levels. We propose a framework to inform the design of an "interpretive layer" to "mediate" between lay (illness model) and professional (disease model) perspectives, at all levels. In our view, the goal is to assist consumers in identifying terms to describe their needs, finding and understanding relevant information, and applying that knowledge for informed healthcare decision making.

Exploring medical expressions used by consumers and the media: an emerging view of consumer health vocabularies.

Healthcare consumers often have difficulty expressing and understanding medical concepts. The goal of this study is to identify and characterize medical expressions or "terms" (linguistic forms and associated concepts) used by consumers and health mediators. In particular, these terms were characterized according to the degree to which they mapped to professional medical vocabularies. Lay participants identified approximately 100,000 term tokens from online discussion forum postings and print media articles. Of the over 81,000 extracted term tokens reviewed, more than 75% were mapped as synonyms or quasi-synonyms to the Unified Medical Language System (UMLS) Metathesaurus. While 80% conceptual overlap was found between closely mapped lay (consumer and mediator) and technical (professional) medical terms, about half of these overlapping concepts contained lay forms different from technical forms. This study raises questions about the nature of consumer health vocabularies that we believe have theoretical and practical implications for bridging the medical vocabulary gap between consumers and professionals.