The internet is viewed as an important channel for patient empowerment, enabling patients to feel more knowledgeable and take action to improve their own health. Internet use among seniors in the Netherlands is increasing, but it is not known if they also use it for health information, nor if seeking information on the internet has different consequences for empowerment than seeking information from other sources. We sought to investigate seniors' use of the internet compared to other resources for health information, and the consequences in terms of both subjective responses and actions taken. Using an email invitation and a web survey, we surveyed 100 elderly internet users, of which 85% had used the internet for health information. The consequences were similar for information found via internet and other sources, and generally positive. Over half reported feeling more knowledgeable and 51% reported making lifestyle changes, but fewer reported having taken other actions (e.g. discussing the information with their doctor). Encouraging the translation of knowledge into action represents an opportunity for empowerment in this population.

Short consultations and a large and growing amount of available medical information make searching for suitable information difficult for general practitioners. Thus information is often not searched for or not found, diminishing the quality of care. We propose a system that offers decision support by combining medical information sources with data from the electronic patient record. A first evaluation shows that a system like Medintel can be a useful supportive tool and can increase the quality of care provided by general practitioners.

Most test-selection algorithms currently in use with probabilistic networks select variables myopically, that is, test variables are selected sequentially, on a one-by-one basis, based upon expected information gain. While myopic test selection is not realistic for many medical applications, non-myopic test selection, in which information gain would be computed for all combinations of variables, would be too demanding. We present three new test-selection algorithms for probabilistic networks, which all employ knowledge-based clusterings of variables; these are a myopic algorithm, a non-myopic algorithm and a semi-myopic algorithm. In a preliminary evaluation study, the semi-myopic algorithm proved to generate a satisfactory test strategy, with little computational burden.

In diagnostic decision-support systems, a test-selection facility serves to select tests that are expected to yield the largest decrease in the uncertainty about a patient’s diagnosis. For capturing diagnostic uncertainty, often an information measure is used. In this paper, we study the Shannon entropy, the Gini index, and the misclassification error for this purpose. We argue that for a large range of values, the first derivative of the Gini index can be regarded as an approximation of the first derivative of the Shannon entropy. We also argue that the differences between the derivative functions outside this range can explain different test sequences in practice. We further argue that the misclassification error is less suited for test-selection purposes as it is likely to show a tendency to select tests arbitrarily. Experimental results from using the measures with a real-life probabilistic network in oncology support our observations.

Decision-support systems in medicine should be equipped with a facility that provides patient-tailored information about which test had best be performed in which phase of the patient's management. A decision-support system with a good test-selection facility may result in ordering fewer tests, decreasing financial costs, improving a patient's quality of life, and in an improvement of medical care in general. In close cooperation with two experts in oncology, we designed such a facility for a decision-support system for the staging of cancer of the oesophagus. The facility selects tests based upon a patient's health status and closely matches current routines. We feel that by extending our decision-support system with the facility, it provides further support for a patient's management and will be more interesting for use in daily medical practice. In this paper, we describe the test-selection facility that we designed for our decision-support system in oncology and present some initial results.

Background:: In the medical domain, establishing a diagnosis typically amounts to reasoning about the unobservable truth, based upon a set of indirect observations from diagnostic tests. A diagnostic test may not be perfectly reliable, however. To avoid misdiagnosis, therefore, the reliability characteristics of the test should be taken into account upon reasoning. Objective:: In this paper, we address the issue of modelling the reliability characteristics of diagnostic tests in a probabilistic network. Method:: To this end, we study the mathematical foundation of a test's characteristics and collate them with the probabilities required for a probabilistic network. Results:: We show that the standard reliability characteristics that are generally available from the literature have to be further detailed and stratified, for example by experts, before they can be included in a network. We demonstrate these modelling issues by means of a real-life probabilistic network in oncology.

Decision-support systems often include a strategy for selecting tests in their domain of application. Such a strategy serves to provide support for the reasoning processes in the domain. Generally a test-selection strategy is offered in which tests are selected sequentially. Upon building a system for the domain of oesophageal cancer, however, we felt that a sequential strategy would be an oversimplification of daily practice. To design a test-selection strategy for our system, we decided therefore to acquire knowledge about the actual strategy used by the experts in the domain and, more specifically, about the arguments underlying their strategy. For this purpose, we used an elicitation method that was composed of an unstructured interview to gain general insight in the test-selection strategy used, and a subsequent structured interview, simulating daily practice, in which full details were acquired. We used the method with two experts in our application domain and found that the method closely fitted in with their daily practice and resulted in a large amount of detailed knowledge.

Decision-support systems often include a strategy for selecting tests in their field of application. This strategy in essence captures procedural knowledge and serves to provide support for the reasoning processes involved. Generally, a test-selection strategy is offered in which tests are selected sequentially. For our field of application, we noticed that such a strategy would be an oversimplification, and decided to acquire knowledge about the actual strategy used by the experts. To this end, we composed a method that comprised an unstructured interview to gain general insight in the test-selection strategy used, and a subsequent structured interview, simulating daily practice through vignettes, to acquire full details. We used the method with two experts in our field of application and found that it closely fitted in with their daily practice and resulted in a large amount of detailed knowledge.

This article provides a framework to describe and compare content-based image retrieval systems. Sixteen contemporary systems are described in detail, in terms of the following technical aspects: querying, relevance feedback, result presentation, features, and matching. For a total of 44 systems we list the features that are used. Of these systems, 35 use any kind of color features, 28 use texture, and only 25 use shape features.