Assisting Consumer Health Information Retrieval with Query Recommendations

Abstract

Health information retrieval (HIR) on the Internet has become an important practice for millions of people, many of whom have problems forming effective queries. We have developed and evaluated a tool to assist people in health-related query formation. Design: We developed the Health Information Query Assistant (HIQuA) system. The system suggests alternative/ additional query terms related to the user's initial query that can be used as building blocks to construct a better, more specific query. The recommended terms are selected according to their semantic distance from the original query, which is calculated on the basis of concept co-occurrences in medical literature and log data as well as semantic relations in medical vocabularies. Measurements: An evaluation of the HIQuA system was conducted and a total of 213 subjects participated in the study. The subjects were randomized into 2 groups. One group was given query recommendations and the other was not. Each subject performed HIR for both a predefined and a self-defined task. Results: The study showed that providing HIQuA recommendations resulted in statistically significantly higher rates of successful queries (odds ratio 5 1.66, 95% confidence interval 5 1.16-2.38), although no statistically significant impact on user satisfaction or the users' ability to accomplish the predefined retrieval task was found. Conclusion: Providing semantic-distance-based query recommendations can help consumers with query formation during HIR.

A Classifier to Evaluate Language Specificity of Medical Documents

“…Initial research in this area was done through collection and examination of health-related consumer queries, with the goal of finding a single, unambiguous label for each medical term [20]. Consumer's limited domain knowledge of the health field leads to the construction of simplistic queries observed in Zeng et al [21].…”

Design and Evaluation of the iMed Intelligent Medical Search Engine

“…At the second level, within each category, the corresponding search results are further divided into multiple sub-categories according to their aspects (e.g., symptom, diagnosis, and treatment the first level of the hierarchy cover only diseases, while these topics can be easily expanded to include other contents (e.g., exams). To help a searcher quickly digest search results and refine his inputs (e.g., the keywords in the "other inputs" text areas) [12], [20], [38], at each level of the search result hierarchy iMed suggests to him a few medical phrases related to his medical situation.…”

“…The other levels can be handled in a similar way. In general, good medical WSEs should automatically suggest diversified, related medical phrases [12], [20], [38] to help searchers quickly digest search results and refine their inputs (e.g., the keywords in the "other inputs" text area of iMed). These suggested medical phrases should be ordered by their relevance to the searcher's inputs.…”

“…Good medical WSEs should automatically suggest related medical phrases to help searchers quickly digest search results and refine their inputs [12], [20], [38]. At each level of the search result hierarchy, iMed generates a single candidate set of related medical phrases for all the formed queries by considering their different weights.…”

Mining document, concept, and term associations for effective biomedical retrieval: introducing MeSH-enhanced retrieval models

“…However, the issue of how to effectively use MeSH terms in health information retrieval is still under discussion to date. MeSH has been used to improve retrieval performance in a number of ways, such as query expansion (Stokes et al 2009), or terminology assistance for users (Zeng et al 2006). In these methods, MeSH terms that are related to users' information needs are first identified either automatically or manually by users.…”