Greer M L
College of Pharmacy, University of Saskatchewan, Saskatoon, Canada.
Ann Pharmacother. 1992 Feb;26(2):244-50. doi: 10.1177/106002809202600221.
RXPERT, a prototype, computer-based, expert system that models the decision-making processes for an ambulatory (non-hospital) formulary, is described as an example of how expert systems may be used to support pharmacy decision making. Basic information about expert-system technology is provided through this example.
Computer-assisted decision making is becoming an important and accepted aspect of complex, health-related decisions. Because expert-system support may become an integral component of future, complex, pharmacy decision making, it is important for pharmacists to become familiar with this technology and its possibilities for supporting pharmacy decisions.
Expert systems offer the potential advantages of making the human decision-making process explicit, more consistent, easily duplicated in many locations simultaneously, and easy to update and document. Although an expert system is seldom intended to replace human decision makers, it can provide valuable support for complex, multivariable decisions. Typical knowledge-acquisition and knowledge-engineering techniques, as well as the characteristics and structure of expert systems, are described, relative to the development of the RXPERT prototype.
Although RXPERT is not yet in use, the process for using an expert system to support an individual committee member's personal assessment of a drug product is described. Decision-support expert systems are potentially useful to pharmacists in complex decision-making tasks.
RXPERT是一个基于计算机的专家系统原型，它模拟了门诊（非医院）处方集的决策过程，被作为专家系统如何用于支持药学决策的一个例子进行描述。通过这个例子提供了有关专家系统技术的基本信息。
计算机辅助决策正成为复杂的、与健康相关决策中一个重要且被认可的方面。由于专家系统支持可能会成为未来复杂药学决策的一个不可或缺的组成部分，药剂师熟悉这项技术及其支持药学决策的可能性很重要。
专家系统具有使人类决策过程明确、更一致、能在许多地点同时轻松复制以及易于更新和记录等潜在优势。尽管专家系统很少旨在取代人类决策者，但它可为复杂的多变量决策提供有价值的支持。相对于RXPERT原型的开发，描述了典型的知识获取和知识工程技术，以及专家系统的特征和结构。
尽管RXPERT尚未投入使用，但描述了使用专家系统支持个别委员会成员对药品进行个人评估的过程。决策支持专家系统在复杂决策任务中对药剂师可能有用。
