Loes M. M. Braun

Towards patient-related information needs.

The quality of health care depends, among other factors, on the quality of a physicians domain knowledge. Since it is impossible to keep up with all new findings and developments, physicians usually have gaps in their domain knowledge. To handle exceptional cases, access to the full range of medical literature is required. The specific literature needed for appropriate treatment of the patient is described by a physicians information need. Physicians are often unaware of their information needs. To support them, this paper presents a first step towards automatically formulating patient-related information needs. We start investigating how we can model a physicians information needs in general. Then we propose an approach to instantiate the model into a representation of a physicians information needs using the patient data as stored in a medical record. Our experiments show that this approach is feasible. Since the number of formulated patient-related information needs is rather high, it has to be reduced. To reduce the number of formulated information needs we propose the use of additional knowledge. Four types of knowledge are discussed, viz. (a) knowledge about temporal aspects, (b) domain knowledge, (c) knowledge about a physicians specialism, and (d) a user model. Future research has to clarify which type of knowledge (or combination thereof) is most appropriate for our purpose. It is expected that the resultant set of information needs will have a manageable size and contributes to the quality of health care.

Information Retrieval in Medicine: The Visual and the Invisible (Information Retrieval im Gesundheitswesen: Das Visuelle und das Unsichtbare)

Summary Especially in knowledge-rich domains such as medicine perfect access to the literature is essential for professionals. Unfortunately, especially in knowledge-rich domains it is difficult to achieve perfect access: it is too difficult and too time consuming for users to formulate queries that yield the maximum of relevant documents and a minimum of non-relevant ones. The paper first discusses the challenges of information retrieval in medicine and various existing approaches. To address the challenges two completely opposite approaches are presented. The first supports the user by means of metabrowsing: a visual way of depicting the relations between domain concepts and documents. Metabrowsing relieves the user from the formulation of queries, while leaving him in full control. The second approach aims to minimize the interaction with the user. Information needs and queries are autonomously and proactively formulated by a software-agent who remains invisible to the user. The agent uses the electronic patient record of a particular patient and domain knowledge. As a result, the agent provides the doctor with literature that is relevant with respect to the patient at hand.