In August of 1980, Stanford University was the site of the annual workshop on artificial intelligence in medicine (AIM). This specialized area of medical computer science research had been born almost ten years earlier with the near-simultaneous development of AIM research groups at Massachusetts Institute of Technology (in collaboration with physicians from the Tufts New England Medical Center), the University of Pittsburgh, Rutgers University, and Stanford. These small groups of computer scientists working in the field were drawn together naturally by their common interests and by the establishment of the SUMEX-AIM network (Stanford University Medical EXperimental Computer for Artificial Intelligence in Medicine). This computing resource was established by the Biotechnology Resources Program of the NIH in 1974 and consisted of a pair of computers, one at Rutgers and one at Stanford, linked by a communications network. The funding for SUMEX-AIM not only provided computing power for researchers exploring the potential of artificial intelligence techniques in medicine but also established a series of annual workshops so that the investigators could gather to,share their insight, results, and ideas regarding approaches to the difficulties they encountered.

JANICE S. AIKINS Dr. Aikins received her Ph.D. in computer science from Stanford University in 1980. She is currently a research computer scientist at IBM's Palo Alto Scientific Center. She specializes in designing systems with an emphasis on the explicit representation of control knowledge in expert systems. ROBERT L. BLUM Dr. Blum received his M.D. from the University of California Medical School at San Francisco in 1973. From 1973 to 1976 he did an internship and residency in the Department of Internal Medicine at the Kaiser Foundation Hospital in Oakland, California, where he was chief resident in 1976.

The resulting instrument produces interpretations as well as the usual protein electrophoresis curves and component percentages. It is a commercially available productthe first marketed medical device to have used AI techniques in its development.

Specialization and generalization are accomplished by adding or deleting elements in these lists. The use of symbolic categories of belief (definite, probable, and possible) provides a specifiable means for manipulating the rules. While based on a simple idea, the SEEK program convincingly demonstrates the value of a rich('v structured representation and of reasoning from cases as a way of constructing a model. That is, exjJert knowledge is inseparable from case experience (Schank, 1983), in so far as knov.Jledge explains the cases. The use of a knowledge base to provide an explanatm), model has characterized other recent AIM work as well (cf.

Working in the EMYCIN environment, they were delighted to find that they could more easily distill their criteria for test interpretation by using the production rule formalism.

J. Barclay Adams, M.D., Ph.D. Associate Physician Department of Medicine Brigham and Women's Hospital Harvard Medical School Boston, Massachusetts 02115 Janice s. Aikins, Ph.D. Research Computer Scientist IBM Palo Alto Scientific Center 1530 Page Mill Road Palo Alto, California 94304 James s. Bennett, M.S. Senior Knowledge Engineer Teknowledge, Inc. 525 University Avenue Palo Alto, California 94301 Sharon Wraith Bennett, R.Ph.

Steps toward a theoretic foundation for complex knowledge-based CAI.

There is little doubt that the decision to use rules to encode infectious disease knowledge in the nascent MYCIN system was largely influenced by our experience using similar techniques in DENDRAL. However, as mentioned in Chapter 1, we did experiment with a semantic network representation before turning to the production rule model. The impressive published examples of Carbonell's SCHOLAR system (Carbonell, 1970a; 1970b), with its ability to carry on a mixed-initiative dialogue regarding the geography of South America, seemed to us a useful model of the kind of rich interactive environment that would be needed for a system to advise physicians. Our disenchantment with a pure semantic network representation of the domain knowledge arose for several reasons as we began to work with Cohen and Axline, our collaborating experts. First, the knowledge of infectious disease therapy selection was ill-structured and, we found, difficult to represent using labeled arcs between nodes. Unlike South American geography, our domain did not have a clear-cut hierarchical organization, and we found it challenging to transfer a page or two from a medical textbook into a network of sufficient richness for our purposes. Of particular importance was our need for a strong inferential mechanism that would allow our system to reason about complex relationships among diverse concepts; there was no precedent for inferences on a semantic net that went beyond the direct, labeled relationships between nodes.1 Perhaps the greatest problem with a network representation, and the greatest appeal of production rules, was our gradually recognized need to deal with small chunks of domain knowledge in interacting with our expert collaborators.

Artificial Intelligence (AI) is that branch of computer science dealing with symbolic, nonalgorithmic methods of problem solving. Several aspects of this statement are important for understanding MYCIN and the issues discussed in this book. First, most uses of computers over the last 40 years have been in numerical or data-processing applications, but most of a person's knowledge of a subject like medicine is not mathematical or quantitative. It is symbolic knowledge, and it is used in a variety of ways in problem solving. Also, the problem-solving methods themselves are usually not mathematical or data-processing procedures but qualitative reasoning techniques that relate items through judgmental rules, or heuristics, as well as through theoretical laws and definitions.

Artificial intelligence, or AI, is largely an experimental science--at least as much progress has been made by building and analyzing programs as by examining theoretical questions. MYCIN is one of several well-known programs that embody some intelligence and provide data on the extent to which intelligent behavior can be programmed. As with other AI programs, its development was slow and not always in a forward direction. But we feel we learned some useful lessons in the course of nearly a decade of work on MYCIN and related programs. In this book we share the results of many experiments performed in that time, and we try to paint a coherent picture of the work.