Computer-based clinical decision support (CDS) = the use of the computer to bring relevant knowledge to bear on the health care and well being of a patient. The general aim of CDS can be one or both of the following: * To make data about a patient easier to assess by, or more apparent to, a human. * To foster optimal problem-solving, decision-making, and action by the human. The exact nature of a particular form of CDS depends on its specific purpose. The decision support is provided to a user—who may be a physician, a nurse, a laboratory technologist, a pharmacist, a patient, or other individual with a need for it. In some instances, the user may be a computer program rather than a human user. Many possible settings can give rise to this need, such as a problem arising in clinical practice, a health maintenance/preventive care question of a patient, or a train- ing/educational exercise. A primary task of the computer is to select knowledge that is pertinent, and/or to process data to create the pertinent knowledge. To the extent that the computer can make the selection based on patient-specific data, the relevance of the CDS to the individual patient is enhanced. The selection of knowledge and processing of data involve carrying out some sort of inferencing process, algorithm, rule, or association method. The result of CDS is to perform some action, usually to make a recommendation.
Lack of CDS in Usage: Reasons for lack of widespread dissemination and adoption of CDS are both technical and nontechnical, and appear to relate to the complexity of providing CDS. This is true not only for inherently complex types of CDS such as differential diagnosis and treatment selection, but even for more simple forms such as alerts and reminders.
Knowledge generation and validation. The knowledge underlying CDS can be generated in a variety of possible ways. These are examined in Section III of this book. In general, the knowledge is initially unstruc- tured and unassembled, or even only implicit, and must be extracted (from experts, from databases, or from the literature), organized and synthesized, analyzed for consistency and accuracy, and represented in an unambiguous form that can be computer-interpretable and acted upon. There may be gaps or overlaps with existing knowledge, calling for studies to refine the knowledge. Any synthesis of knowledge about a topic should have an appropriate expiration date, at which time the sources should be re-reviewed and the knowledge updated if necessary. Thus each item of knowledge must go through a continuous life cycle process