The CLEF query interface is designed to provide effective, efficient and secure access to aggregated data for performing a variety of tasks: assisting in diagnosis or treatment, identifying patterns in treatment, selecting subjects for clinical trials, monitoring the participants in clinical trials.

Rationale

An analysis of free text queries written by medical professional shows that such queries are very complex and often ambiguous. Traditionally, user interfaces to medical databases have been complex graphical interfaces that are not particularly easy to use by a casual user. On the other hand, queries expressed in free natural language are sensitive to errors of composition (misspellings, ungrammaticalities) or processing (at the lexical, syntactic or semantic level). Also, the inherent ambiguity of natural language makes complex query processing difficult. In the process of querying medical databases, the users (medical researchers, clinicians) should be able to construct complex queries containing a large number of parameters involved in conditional and temporal structures.

The CLEF solution

• Query editing
  
  

  The CLEF query interface uses the conceptual authoring technique through WYSIWYM editing, which alleviates the need for expensive syntactic and semantic processing of the queries. It provides the users with an interface for editing the conceptual meaning of a query instead of the surface text.
  The WYSIWYM interface presents the contents of a knowledge base to the user in the form of a feedback text. In the case of query editing, the content of the knowledge base is a yet to be completed formal representation of the users query. The interface presents the user with a natural language text that corresponds with the incomplete query and guides them towards editing a semantically consistent and complete query. In this way, the users are able to control the interpretation that the system gives to their queries. The user starts by editing a basic query frame, where concepts to be instantiated (anchors) are clickable spans of text with associated pop-up menus containing options for expanding the query.
  
  More about the query editor here
  
  

• Answer generation
  
  

  Responses to aggregated queries are lists of patients that fulfil the query requirements. Apart from the features requested in the query, each patient in the result set has their age and gender specified.
  The task of the answer generator is to process and organise the result set and to present it to the user (medical researcher) in a meaningful format.
  
  Examples of graphical and textual answers, here

Please address any problems or questions about this page to