Today's expert systems deal with domains of narrow specialization. For expert systems to perform competently over a broad range of tasks, they will have to be given very much more knowledge. ... The next generation of expert systems ... will require large knowledge bases. How will we get them?

- Edward Feigenbaum, Pamela McCorduck, H. Penny Nii, from The Rise of the Expert Company

The primary goal of expert systems research is to make expertise available to decision makers and technicians who need answers quickly. There is never enough expertise to go around -- certainly it is not always available at the right place and the right time. Portable with computers loaded with in-depth knowledge of specific subjects can bring decades worth of knowledge to a problem. The same systems can assist supervisors and managers with situation assessment and long-range planning. Many small systems now exist that bring a narrow slice of in-depth knowledge to a specific problem, and these provide evidence that the broader goal is achievable.

These knowledge-based applications of artificial intelligence have enhanced productivity in business, science, engineering, and the military. With advances in the last decade, today's expert systems clients can choose from dozens of commercial software packages with easy-to-use interfaces.

Each new deployment of an expert system yields valuable data for what works in what context, thus fueling the AI research that provides even better applications.

Introductory Readings

Expert Systems - Make a Diagnosis. Part of It's Alive! - From airport tarmacs to online job banks to medical labs, artificial intelligence is everywhere. By Jennifer Kahn. Wired Magazine (March 2002/ Issue 10.03). "Intuition may seem like a human trick, but machines can be pretty good at it, too. Underlying a hunch are dozens of tiny, subconscious rules - truths we've learned from experience. Add them up and you get instinct: a doctor's sense that a patient's stomachache might really be appendicitis, for example. Program those rules into a computer and you get an expert system - one of many that can screen lab tests, diagnose blood infections, and identify tumors on a mammogram."

Expert Systems. Section 1.2.3 of Chapter One (available online) of George F. Luger's textbook, Artificial Intelligence: Structures and Strategies for Complex Problem Solving, 5th Edition (Addison-Wesley; 2005)."One major insight gained from early work in problem solving was the importance of domain-specific knowledge. A doctor, for example, is not effective at diagnosing illness solely because she possesses some innate general problem-solving skill; she is effective because she knows a lot about medicine. Similarly, a geologist is effective at discovering mineral deposits because he is able to apply a good deal of theoretical and empirical knowledge about geology to the problem at hand. Expert knowledge is a combination of a theoretical understanding of the problem and a collection of heuristic problem-solving rules that experience has shown to be effective in the domain. Expert systems are constructed by obtaining this knowledge from a human expert and coding it into a form that a computer may apply to similar problems.

This reliance on the knowledge of a human domain expert for the system's problem solving strategies is a major feature of expert systems."

Expert Systems Standard Grade Bitesize Revision & Test. A Computing Studies General Purpose Package from BBC Education Scotland.

Expert Systems. From the Artificial Intelligence entry in Encyclopædia Britannica from Encyclopædia Britannica Premium Service. "The basic components of an expert system are a knowledge base, or KB, and an inference engine. The information to be stored in the KB is obtained by interviewing people who are expert in the area in question. The interviewer, or knowledge engineer, organizes the information elicited from the experts into a collection of rules, typically of an 'if-then' structure. Rules of this type are called production rules. The inference engine enables the expert system to draw deductions from the rules in the KB." (Excerpt from page 20, Knowledge and Inference.)

Expert Systems - Computers as sages. By Howard Rheingold. Digital Deli (1984; It is posted on www.atariarchives.org with the approval of Steve Ditlea, editor of the book, for archival purposes only.). "Should you ever want to drill for oil, diagnose a disease or synthesize a new molecule, you can ask Prospector, MYCIN or Dendral for some sage advice. They are certified experts in their respective fields. They are also computer programs. We all depend on expert assistance-from doctors, attorneys, automobile mechanics, computer repairmen. Wouldn't it be nice to have our own experts?"

• Also see the companion article at the bottom of the page: Expert Systems History - "Edward A. Feigenbaum was one of the people in artificial intelligence research who decided, in the mid-1960s, that it was important to know how much a computer program can know and that the best way to find out would be to try to construct an artificial expert. While looking for an appropriate field of expertise, Feigenbaum encountered Joshua Lederberg, the Nobel laureate biochemist, who suggested that organic chemists sorely needed assistance in determining the molecular structure of chemical compounds. Together with Bruce Buchanan, Lederberg and Feigenbaum began work on Dendral, the first expert system, in 1965 at Stanford University."

Introduction to Expert Systems. From expertise2go.com. "This tutorial shows you how a computer-based expert system emulates the behavior of a human advisor, presents terminology unique to the field and introduces the activities that must be accomplished to build expert systems."

• Don't miss their Expert System Glossary and the rest of their tutorials and demos.

Expert Systems and Artificial Intelligence. Part of the Introduction by Robert S. Engelmore and Edward Feigenbaum for the May 1993 Japanese Technology Evaluation Center panel's report about Knowledge-Based Systems in Japan, and now available from the World Technology Evaluation Center (WTEC). Topics covered include "The Building Blocks of Expert Systems" ("Every expert system consists of two principal parts: the knowledge base; and the reasoning, or inference, engine.") and "Knowledge Engineering" ("[T]he art of designing and building expert systems, and knowledge engineers are its practitioners".).

• Be sure to check out the Table of Contents for additional information including, Expert Systems Building Tools: Definitions, by H. Penny Nii: "An expert system tool, or shell, is a software development environment containing the basic components of expert systems. Associated with a shell is a prescribed method for building applications by configuring and instantiating these components."

VIDEO - Rule-Based Expert Systems and Knowledge Engineering: part one of Patrick Winston's online Artificial Intelligence course for ArsDigita University. Video available via the AAAI Video Archive.

Expert System Tutorial. Major George Hluck. "The purpose of this brief and introductory tutorial is to quickly educate the reader on expert systems. The material presented in this tutorial is also used in our advanced course, Military Applications of Artificial Intelligence, which is taught during the second and third terms at the U.S. Army War College in Carlisle, PA."

Expert Systems: video clip of Herbert A. Simon explaining the anatomy of an expert system. From AI: What Can it Do? Where is it Going? (March 21, 1990) and part of the Carnegie Mellon University Archives' exhibit: Mind Models - Artificial Intelligence Discovery. At Carnegie Mellon: Into the Future.

Knowledge Engineers and Epistemological Entrepreneurs. Chapter 13 of the 1985 edition of Howard Rheingold's Tools for Thought (The MIT Press). "Expert systems as they exist today are made of three parts -- a base of task-specific knowledge, a set of rules for making decisions about that knowledge, and a means of answering people's questions about the reasons for the program's recommendations. The 'expert' program does not know what it knows through he raw volume of facts in the computer's memory, but by virtue of a reasoning-like process of applying the rule system to the knowledge base; it chooses among alternatives, not through brute-force calculation, but by using some of the same rules of thumb that human experts use. ... In the 1980s, there is little question that expert systems can be highly effective, if not superior to human expertise, in certain highly specialized fields. Twenty years ago, few people, even inside the artificial intelligence community, were confident that it could be done at all. ... Expert systems are now in commercial and research use in a number of fields. A partial sampling: ...."

• Visit Exsys and be sure to check out their Knowledge Automation Expert Systems demos.

Artificial intelligence gets real. By Daniel Lyons. Forbes Global (November 30, 1998) ."By contrast, Feigenbaum succeeded by thinking small. Unlike his rivals, he didn't set out to recreate all of human intelligence in a computer. His idea was to take a particular expert -- a chemist, an engineer, a pulmonary specialist -- and figure out how that person solved a single narrow problem. Then he encoded that person's problem-solving method into a set of rules that could be stored in a computer."

Introduction to AI and Expert Systems. By Carol E. Brown and Daniel E. O'Leary. The tutorial uses summaries and outline form to explain AI, reasoning, and knowledge engineering. Examples of expert systems used in business accounting are described.

OpenClinical offers this overview of Clinical Decision Support Systems (CDSSs) which includes:

• a section about Early AI / Decision Support Systems, and
• a collection of AI / Decision Support Systems in clinical practice.

An early look at artificial Intelligence. The Computer Chronicles (1984 television broadcast) / video available from The Internet Archive. "Guests include Edward Feigenbaum of Stanford University, Nils Nilsson of the AI Center at SRI International, Tom Kehler of Intellegenetics, Herb Lechner of SRI, and John McCarthy of Stanford." Seller of Software Used in Bankruptcy Petitions Held ‘Preparer.’ By Tina Bay. Metropolitan News-Enterprise (February 28, 2007). "The seller of web-based software used to prepare bankruptcy petitions qualifies as a 'bankruptcy petition preparer' subject to the requirements of the U.S. Bankruptcy Code, the Ninth U.S. Circuit Court of Appeals ruled yesterday. The court unanimously agreed with a Ninth Circuit Bankruptcy Appellate Panel that now-defunct Ziinet.com owner and operator Henry Ihejirika violated 11 U.S.C. Sec. 110, which imposes certain obligations on bankruptcy petition preparers and penalizes negligent or fraudulent preparation. The court also affirmed the BAP’s conclusion that Ihejirika had engaged in the unauthorized practice of law. ... One of the sites owned and operated by Ihejirika was the 'Ziinet Bankruptcy Engine,' which represented itself to prospective customers as being 'an expert system' and claimed to 'know [ ] bankruptcy laws right down to those applicable to the state' in which the particular user lived."

• The Reynoso v. Frankfort Digital Services, Ltd. opinion is avaiable from the United States Court of Appeals for the Ninth Circuit. Be sure to see footnote 9: "... we express no view as to whether software alone, or other types of programs, would constitute the practice of law."
• Also see this article: Beware the Unauthorized Practice of Law in Cyberspace. By Shari Claire Lewis. New York Law Journal / available from Law.com (June 6, 2007). "Consider the recent decision by the 9th U.S. Circuit Court of Appeals in In re Reynoso [fn]. ... Frankfort sold access to Web sites where customers could access browser-based software for preparing bankruptcy petitions and schedules, as well as informational guides promising advice on various aspects of relevant bankruptcy law. Included in the site was the following representation: 'Ziinet is an expert system and knows the law. Unlike most bankruptcy programs which are little more than customized word processors the Ziinet engine is an expert system. It knows bankruptcy laws right down to those applicable to the state in which you live.' ... The circuit [court] concluded that Frankfort had engaged in the unauthorized practice of law. It observed that Frankfort's sites offered extensive advice on how to take advantage of so-called loopholes in the Bankruptcy Code, promised services comparable to those of a 'top-notch bankruptcy lawyer,' and described its software as 'an expert system' that would do more than function as a 'customized word processor.' Moreover, the appellate court added, the software went 'far beyond providing clerical services.' It determined where (particularly, in which schedule) to place information provided by the debtor, selected exemptions for the debtor, and supplied relevant legal citations. Providing such personalized guidance amounted to the practice of law, the appellate court held."

General Readings

Automating the Underwriting of Insurance Applications. By Kareem S. Aggour and William Cheetham. In Proceedings of the Seventeenth Innovative Applications of Artificial Intelligence Conference, 1451-1458. Menlo Park, Calif.: AAAI Press. "An end-to-end system was created at Genworth Financial to automate the underwriting of Long Term Care (LTC) and Life Insurance applications. Relying heavily on Artificial Intelligence techniques, the system has been in production since December 2002 and today completely automates the underwriting of 19.2 percent of the LTC applications. A fuzzy logic rules engine encodes the underwriter guidelines and an evolutionary algorithm optimizes the engine’s performance. Finally, a natural language parser is used to improve the coverage of the underwriting system."

• This application was one of 7 that received the 2005 AAAI Award for Innovative Applications of AI. As stated in the press briefing: "General Electric Company / Genworth Financial - Automating the underwriting of insurance applicationsThose watching this year’s Wimbledon Tennis Championships on TV have likely been entertained by the Genworth advertisements featuring Andre Agassi with his wife Steffi Graff and their wunderkind son. Look under the covers of this $98 billion company with annual sales of $11 billion, and you will find an innovative AI-based underwriting system that is giving this insurance giant a competitive advantage. The automated underwriting system processes 3,500 applications per week for Long Term Care insurance, with near 100 percent accuracy. This has improved decision consistency, significantly reduced the number of incorrect decisions, and saved an estimated $500,000 annually in phone interviews previously required for additional information. In May of 2004, Genworth Financial was spun off from the General Electric Company. At the time of the IPO, stock analysts specifically cited this advanced technology as one of the key advantages GNW has over its competitors."

AI in Australia and New Zealand. By the Australian Computer Society National Committee for AI. IEEE Intelligent Systems (July/August 2004). "Australian industry plays a role in AI research, too. The Computer Sciences Corporation (previously The Continuum Company), for example, has made significant contributions. Of the various expert systems the CSC developed in the late nineties, COLOSSUS is still widely used by several major Australian insurance companies. In fact, COLOSSUS, which helps insurance adjusters assess personal injury claims, has been a worldwide success for CSC. The COLOSSUS project began in 1989 with merely an in-house system to process a huge volume of backlog claims at GIO Australia. It has since grown to multiple business units in CSC, offering different versions for the US, UK, and Australian markets. The system can handle third-party general-damages and workers-compensation claims and has penetrated much of the US market. In Australia, Trowbridge also uses COLOSSUS for their statistical study on claims data."

• Visit CSC's COLOSSUS page.

Developing and Deploying Knowledge on a Global Scale. By James Borron, David Morales, and Philip Klahr. AI Magazine17(4): Winter 1996, 65-76. "Reuters is a worldwide company focused on supplying financial and news information to its more than 40,000 subscribers around the world. To enhance the quality and consistency of its customer- support organization, Reuters embarked on a global knowledge development and reuse project. The resulting system is in operational use in North America, Europe, and Asia. The system supports 38 Reuter products worldwide. This article presents a case study of Reuter experience in putting a global knowledge organization in place, building knowledge bases at multiple distributed sites, deploying these knowledge bases in multiple sites around the world, and maintaining and enhancing knowledge bases within a global organizational framework. This project is the first to address issues in multicountry knowledge development and maintenance and multicountry knowledge deployment. These issues are critical for global companies to understand, address, and resolve to effectively gain the benefits of global knowledge systems."

Rule-Based Expert Systems --The MYCIN Experiments of the Stanford Heuristic Programming Project. Bruce G. Buchanan and Edward H. Shortliffe, editors (1984). Reading, MA: Addison-Wesley. The entire book is now available online from AAAI's Classic Books in AI collection. "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. The book is intended to be a critical analysis of several pieces of related research, performed by a large number of scientists. We believe that the whole field of AI will benefit from such attempts to take a detailed retrospective look at experiments, for in this way the scientific foundations of the field will gradually be defined. It is for all these reasons that we have prepared this analysis of the MYCIN experiments."

A Different Kind of Laboratory Mouse. By Grant Buckle. DigitalJournal.com (November 20, 2004). "It is possible to find viable alternatives to tests on live animals and, thanks to technology, at least some of them can saved without abandoning important research. ... In silico testing is an example of how technology continues to successfully create beneficial methods because once a model has such data, it may be able to predict the likely effects of chemicals and drugs without testing on live animals. But tests using computer models are still relatively new, so they’re not yet sufficient for making final decisions about the safety of drugs or chemicals for human consumption. The good news, though, is that if pre-screening with computer models determines that a compound is likely to be dangerous, the developer can decide not to pursue it further, saving time and money. ... A handful of software packages exist for doing in silico testing. ... Lhasa Ltd., a spinoff of the chemistry department of the University of Leeds in England, developed Deductive Estimation of Risk from Existing Knowledge (DEREK) for Windows, a knowledge-base expert system that analyzes the structure of chemicals and predicts whether they will be toxic. ... Computer models are still not good enough to be used as the only means of testing new drugs and chemicals, but with the ballooning growth of technology, never say never. As artificial intelligence improves, and science sees a few more breakthroughs in the way the models are developed, it might not be that far off."

Expert Systems: How Far Can They Go? Part One. By Randall Davis. AI Magazine 10(1): Spring 1989, 61-67 - and - Expert Systems: How Far Can They Go? Part Two. ByRandall Davis. AI Magazine 10(2): Summer 1989, 65-77. "A panel session at the 1985 International Joint Conference on artificial intelligence in Los Angeles dealt with the subject of knowledge-based systems; the session was entitled "Expert Systems: How Far Can They Go?" The panelists included Randall Davis (Massachusetts Institute of Technology); Stuart Dreyfus (University of California at Berkeley); Brian Smith (Xerox Palo Alto Research Center); and Terry Winograd (Stanford University), chairman. The article begins with Winograd's original charge to the panel, followed by lightly edited transcripts of the panel's remarks. Part 1 includes presentations from Winograd and Dreyfus. Part 2, which will appear in the Summer 1989 issue, includes presentations from Smith and Davis and concludes with the panel discussion. Although three years have passed since this session took place, the issues raised and the points discussed are no less relevant today."

• Also see: Expert Systems: Where Are We? And Where Do We Go from Here? By Randall Davis. AI Magazine 3(2): Spring 1982, 3-22. "Work on Expert Systems has received extensive attention recently, prompting growing interest in a range of environments. Much has been made of the basic concept and of the rule-based system approach typically used to construct the programs. Perhaps this is a good time then to review what we know, asses the current prospects, and suggest directions appropriate for the next steps of basic research. I'd like to do that today, and propose to do it by taking you on a journey of sorts, a metaphorical trip through the State of the Art of Expert Systems. We'll wander about the landscape, ranging from the familiar territory of the Land of Accepted Wisdom, to the vast unknowns at the Frontiers of Knowledge. I guarantee we'll all return safely, so come along...."

OncoLogic™ - A Computer System to Evaluate the Carcinogenic Potential of Chemicals. EPA (U. S. Environmental Protection Agency)"What is an expert system?An expert system is a computer program that mimics the judgment of experts by following sets of knowledge rules that are based on studies of how chemicals cause cancer in animals and humans. An expert system, like OncoLogic™, asks for chemical and use information from the user and following the knowledge rules incorporated into the system, uses the responses to construct an estimation of the most likely results."

• Also see these related pages at the EPA site:
  • Cancer Expert System, or OncoLogic ™, Fact Sheet

A Personal View of Expert Systems: Looking Back and Looking Ahead. By Edward A. Feigenbaum. "This was an acceptance sppech for the Feigenbaum Medal presented at the World Congress on Expert Systems at Orlando, Florida, December 1991." Available in several formats from CiteSeer.

Expertise in Context: Human and Machine. Edited by Paul J. Feltovich, Kenneth M. Ford, and Robert R. Hoffman. AAAI Press. "Computerized 'expert systems' are among the best known applications of artificial intelligence. But what is expertise? The nature of knowledge and expertise, and their relation to context, is the focus of active discussion --- even controversy --- among psychologists, philosophers, computer scientists, and other cognitive scientists. The questions reach to the very foundations of cognitive theory --- with new perspectives contributed by the social sciences. These debates about the status and nature of expert knowledge are of interest to and informed by the artificial intelligence community --- with new perspectives contributed by 'constructivists' and 'situationalists.' The twenty-three essays in this volume discuss the essential nature of expert knowledge, as well as such questions such as how 'expertise' differs from mere 'knowledge,' the relation between the individual and group processes involved in knowledge in general and expertise in particular, the social and other contexts of expertise, how expertise can be assessed, and the relation between human and computer expertise."

PI in a Box: A Knowledge-Based System for Space Science Experimentation. By Richard Franier, Nicholas Groleau, Lyman Hazelton, Silvano Colombano, Michael Compton, Irving Statler, Peter Szolovits, and Laurence Young. AI Magazine 15(1): Spring 1994, 39-56. "The principal investigator (PI)-IN-A-BOX knowledge based system helps astronauts perform science experiments in space. ... The system is in use on the ground for mission training and was used in flight during the October 1993 space life sciences 2 (SLS-2) shuttle mission."

Expert System computer programs for analysis of Archaeological material. By Roger Grace. Nicely illustrated explanations of the LITHAN [LITHic ANalysis of stone tools] and FAST [Functional Analysis of Stone Tools] expert sysytems.

LifeCode: A Deployed Application for Automated Medical Coding. By Daniel T. Heinze, Mark Morsch, Ronald Sheffer, Michelle Jimmink, Mark Jennings, William Morris, and Amy Morsch. AI Magazine 22(2): Summer 2001, 76-88. This paper is based on the authors' presentation at the Twelfth Innovative Applications of Artificial Intelligence Conference (IAAI-2000). "LifeCode is a natural language processing (NLP) and expert system that extracts demographic and clinical information from free-text clinical records."

Ramp Activity Expert System for Scheduling and Coordination at an Airport. Geun-Sik Jo, Jong-Jin Jung, Ji-Hoon Koo, and Sang-Ho Hyun. AI Magazine 21(4): Winter, 2000, 75-82. "By user-driven modeling for end users and near-optimal knowledge-driven scheduling acquired from human experts, races can produce parking schedules for about 400 daily flights in approximately 20 seconds; human experts normally take 4 to 5 hours to do the same."

Worldwide Perspectives and Trends in Expert Systems. By Jay Liebowitz. AI Magazine 18(2): Summer 1997, 115-119. "Some people believe that the expert system field is dead, yet others believe it is alive and well. To gain a better insight into these possible views, the first three world congresses on expert systems (which typically attract representatives from some 45-50 countries) are used to determine the health of the global expert system field in terms of applied technologies, applications, and management. This article highlights some of these findings."

New Tools Help Hospitals Handle Terror Attacks And Other Disasters. By Marianne Kolbasuk McGee. InformationWeek (April 14, 2005). "When hospitals deal with a disaster, whether treating dozens of casualties from a serious highway pileup or hundreds of potential terrorist-attack victims, emergency workers and hospital administrators rely predominately on ringed binders containing hundreds of pages of emergency instructions and procedures. ... To help make disaster management more efficient, health-care purchasing group Amerinet is making available to its 1,800 hospital members a new interactive, Web-based disaster-management system developed by PortBlue Corp., a maker of expert-system software. PortBlue's new Hospital Incident Response System helps hospital workers deal with smaller-scale crises, such as an internal fire; larger disasters, like plane crashes; and potential national emergencies, such as biological or chemical attacks, PortBlue CEO and founder Paul Dimitruk says."

• Also see: What are Expert Systems? and Knowledge Management Overview from PortBlue.

The F-16 Maintenance Skills Tutor. By Christopher Marsh. The Edge - The MITRE Advanced Technology Newsletter (March 1999). "The F-16 Maintenance Skills Tutor simulates the experience of on-the-job training including running tests, moving switches, replacing components, taking measurements, and asking an expert for help. This is done by giving the student realistic guided simulations of real-life problem situations using software models and high resolution graphics backed by an expert system that knows how to troubleshoot. This gives the student an experience that is progressive (easier problems are given to the student first). It provides explanations and help (when requested by the student), and it gives the student practice in the mechanics of expert problem solving."

An Expert System Using Nonmonotonic Techniques for Benefits Inquiry in the Insurance Industry. Leora Morgenstern and Moninder Singh. In Proceedings Fifteenth International Joint Conference on Artificial Intelligence, Morgan Kaufmann (1997). Available from Leora Morgenstern's homepage. Abstract: "Describes BenInq, an expert system used in the medical insurance industry by both customer service representatives, who answer questions about the extent of a patient's coverage for medical care, and policy modifiers, who frequently change coverage rules. Reasoning is performed by inheriting business rules, represented as formulae of first-order logic, in a semantic network in which formulae are attached to the nodes."

Stanford Medical Informatics: Uncommon research, common goals. By Mark A. Musen. MD Computing (January/February 1999). "DENDRAL demonstrated the power of encoding large amounts of domain knowledge for use by an automated reasoning system, and offered one of the first examples of rule-based programming."

An Intelligent System for Case Review and Risk Assessment in Social Services. By James R. Nolan. AI Magazine 19(1): Spring 1998, 39-46. "This article reports on the development and implementation of DISXPERT, an intelligent rule-based system tool for referral of social security disability recipients to vocational rehabilitation services."

An Expert System for Automotive Diagnosis. By Jeff Pepper. From Ray Kurzweil's book, The Age of Intelligent Machines (1990). "This 'expert in a box' will guide a human technician through the entire service process, from the initial customer interview at the service desk to the diagnosis and repair of the car in the garage."

LAPS: Cases to Models to Complete Expert Systems. By Joseph S. di Piazza and Frederick A. Helsabeck. AI Magazine 11(3): Fall 1990, 80-107. A unique program for interviewing experts that interweaves knowledge gathering, organizing, and testing.

Technology, Work and the Organization: The Impact of Expert Systems. By Rob Weitz (1990). AI Magazine 11(2): Summer, 1990, 50-60.

A UMLS-based Knowledge Acquisition Tool for Rule-based Clinical Decision Support System Development. By Soumeya L. Achour, MS, DVM, Michel Dojat, Eng, PhD, Claire Rieux, MD, Philippe Bierling, MD, PhD, and Eric Lepage, MD, PhD. Journal of the American Medical Informatics Association 8 (4): 351­360. July 2001. Abstract: "Decision support systems in the medical field have to be easily modified by medical experts themselves. The authors have designed a knowledge acquisition tool to facilitate the creation and maintenance of a knowledge base by the domain expert and its sharing and reuse by other institutions. The Unified Medical Language System (UMLS) contains the domain entities and constitutes the relations repository from which the expert builds, through a specific browser, the explicit domain ontology. The expert is then guided in creating the knowledge base according to the pre-established domain ontology and condition­action rule templates that are well adapted to several clinical decision-making processes. Corresponding medical logic modules are eventually generated. The application of this knowledge acquisition tool to the construction of a decision support system in blood transfusion demonstrates the value of such a pragmatic methodology for the design of rule-based clinical systems that rely on the highly progressive knowledge embedded in hospital information systems."

Related Videos

Browsing videos (sidebar) will show several relevant videos. A good overview is:

• "Computer Chronicles" -- a TV panel discussion about expert system, with Edward Feigenbaum, Nils Nilsson, John McCarthy & others, 1984.

Related Resources

"Berkeley Expert Systems Technology (BEST) lab is an Artificial Intelligence, Expert Systems and Information Technologies laboratory in the Department of Mechanical Engineering at University of California at Berkeley."

Demos - an eclectic mini-collection:

• Expert System demos from Acquired Intelligence, Inc.: 1) "The Whale Watcher expert system combines artificial intelligence, marine biology and web technology to produce an interactive system that helps you with whale identification." 2) "Douglas-Fir Cone and Seed Insects System ... is intended to assist seed orchard managers and cone and seed collectors, dealers and researchers in the identification of insects associated with Douglas fir cones." and 3) "The Graduate Admissions Screening System demonstrates the use of ACQUIRE¨ with an administrative screening task - the categorization of student applications for admission to graduate school."
• Knowledge Automation Expert System demos and case studies from Exsys.
• MedEthEx demo based on the paper: MedEthEx: A Prototype Medical Ethics Advisor. By Michael Anderson, Susan Leigh Anderson, and Chris Armen. In Proceedings of the Eighteenth Innovative Applications of Artificial Intelligence Conference, July 16 – 20 2006. Menlo Park, Calif.: AAAI Press.
• Medical Expert System demos from EasyDiagnosis assist with the diagnosis of Constipation and Depression.
• OSHA Expert Systems.

• The Wedding Planner. From Organizers for Us. "Not every part of The Wedding Planner for Us is a virtuoso demonstration of artificial intelligence (like we use for the envelope text and etiquette rules) or statistical analysis (like we use for projecting your attendance). After all, if you're writing thank-you notes, all you really need is a list of who gave you what, so you can check off which gifts you've sent thank-yous for ... and that's exactly what we give you. For every area of your wedding planning where we think that software can help you (not just give you busy work), we provide you with the tools you need to get the job done, as quickly and simply as possible."

Expert System Projects from AIAI, the Artificial Intelligence Applications Institute at the University of Edinburgh's School of Informatics. Projects include: Formation - "A knowledge-based document layout system now in use in the production of the British Telecom Yellow Pages," and EASE for Windows - "A knowledge-based system for assessing workplace exposure to potentially hazardous new substances."

Expert Systems. From PC AI Magazine / Knowledge Technology, Inc. In addition to an short overview and a glossary of terms, you'll find links to commercial vendors, academic research groups, articles, books, and more!

Expert Systems entry in Webopedia, the free online dictionary from the internet.com network of Web sites.

Expert Systems with Applications, published by Elsevier, "is a refereed international journal whose focus is on exchanging information relating to expert and intelligent systems applied in industry, government, and universities worldwide. The thrust of the journal is to publish papers dealing with the design, development, testing, implementation, and/or management of expert and intelligent systems, and also to provide practical guidelines in the development and management of these systems." A free sample issue is available via a link in the sidebar.

Expert Systems Developer Group, Penn State College of Agricultural Science. "The primary goal of the Expert Systems Developer Group (ESDG) is the development of expert systems to integrate the vast amount of information available in the agricultural sciences and make this information accessible for farm level decision making."

International Conference onIndustrial & Engineering Applications of Artificial Intelligence & Expert Systems: sponsored by ISAI, the International Society of Applied Intelligence.

• The 19th International Conference on Industrial & Engineering Applications of Artificial Intelligence & Expert Systems (IEA/AIE 2006).
• The 18th International Conference on Industrial & Engineering Applications of Artificial Intelligence & Expert Systems (IEA/AIE 2005).
• The 17th International Conference on Industrial & Engineering Applications of Artificial Intelligence & Expert Systems (IEA/AIE 2004).
• Proceedings are available from the ACM Portal.

The Joshua Lederberg Papers, part of the National Library of Medicine's Profiles in Science archival collection, contains a wealth of information about DENDRAL, "a prototype for expert systems and the first use of artificial intelligence in biomedical research."

• Computers, Artificial Intelligence, and Expert Systems in Biomedical Research. Excerpt: "The immediate impetus for Lederberg's research into biomedical applications of computers came from his participation in the National Aeronautics and Space Administration's Mars missions from 1961 onward, for which he designed a computer-controlled mass spectrometer capable of analyzing the Martian surface for signs of life. Lederberg soon applied the theoretical principles of computerized spectrometry to experimentation in the chemical laboratory, where, in 1965, they became the foundation of DENDRAL, a prototype for expert systems and the first use of artificial intelligence in biomedical research. DENDRAL (for Dendritic Algorithm) was a computer program devised by Lederberg, chairman of the Stanford computer science department Edward A. Feigenbaum, and chemistry professor Carl Djerassi for the elucidation of the molecular structure of unknown organic compounds taken from known groups of such compounds, such as the alkaloids and the steroids. ... Lederberg and his colleagues believed that artificial intelligence--the use of computers for manipulating symbols, for instance the combination of words in an 'if-then' inference, rather than for purely numerical calculation--could assimilate the rules of inductive reasoning and empirical judgment that guide scientists and physicians in their work, rules for which mathematical representations did not exist. Bruce Buchanan and others in Stanford's computer science department distilled these rules, which they called 'heuristics,' from extended interviews with Lederberg and other experts in their respective fields, and translated them into the formal code of symbolic computation."
• How DENDRAL was conceived and born. Typescript of Lederberg's November 5, 1987 talk at the Association for Computing Machinery Symposium on the History of Medical Informatics."As agreed with your organizers, this will be a somewhat personal history. They have given me permission to recall how I came to work with Ed Feigenbaum on DENDRAL, an exemplar of expert systems and of modelling problem-solving behavior. My recollections are based on a modest effort of historiography, but not a definitive survey of and search for all relevant documents. On the other hand, they will give more of the flow of ideas and events as they happened than is customary in published papers in scientific journals...."
• Also watch this video clip from an oral history interview with Dr. Lederberg.

OSHA [Occupational Safety & Health Administration] eTools andElectronic Products for Compliance Assistance: eTools, Expert Systems, eMatrix. "eTools are 'stand-alone,' interactive, Web-based training tools on occupational safety and health topics. They are highly illustrated and utilize graphical menus. Some also use expert system modules, which enable the user to answer questions, and receive reliable advice on how OSHA regulations apply to their work site. Expert Advisors are based solely on expert systems." These are just a few of the expert systems offered:

• "The Asbestos Advisor is an interactive compliance assistance tool. Once installed on your PC, it can interview you about buildings and worksites, and the kinds of tasks workers perform there. It will produce guidance on how the Asbestos standard may apply to those buildings and that work. Its guidance depends on your answers. It can provide general guidance and may, also, be focused on a particular project."
• OSHA's Lead in General Industry Advisor is multi-purpose, interactive, expert software. The Lead in General Industry Advisor assists employers, employees, and physicians and other health care providers to understand the requirements of the general industry standard on occupational exposure to LEAD (29 CFR 1910.1025).The software provides an introduction to the scope and logic of the regulation, and provides a framework to facilitate compliance.
• "OSHA's LOTO Plus Expert Advisor - Public Test Version is interactive, expert, diagnostic software. It will help you understand and apply OSHA standards that protect workers from the release of Hazardous Energy."
• The SafeCare Advisor: "This Expert Advisor software will create a customized report on the likely occupational safety and health hazards in a long term care facility."

Other References Offline

Abdelguerfi, Mahdi, and Simon H. Lavington. 1995. Emerging Trends in Database and Knowledge-Base Machines: The Application of Parallel Architectures to Smart Information Systems. Los Alamitos, CA: IEEE Computer Society Press. Awad, Elias. 1996. Building Expert Systems: Principles, Procedures and Applications. Cambridge: Course Technology.

Buchanan, Bruce G., and Reid G. Smith. 1988. Fundamentals of Expert Systems. In Annual Review of Computer Science, Vol. 3, ed. Traub, Joseph F., Barbara J. Grosz, Butler W. Lampson, et al., 23-58. Palo Alto, CA: Annual Reviews, Inc.

Castillo, Enrique, Jose M. Gutierrez, and E. Castillo. 1996. Expert Systems and Probabilistic Network Models. New York: Springer Verlag.

Clancy, Paul, Gerald Hoenig, and Arnold Schmitt. 1989. An Expert System for Legal Consultation. In Proceedings of the Second Annual Conference on Innovative Applications of Artificial Intelligence, 125 - 135. Menlo Park, Calif.: AAAI Press. "This paper describes an expert system that was developed to assist attorneys and paralegals in the closing process for commercial real estate mortgage loans. The system identifies the legal requirements for closing the loans by considering the numerous individual features specific to each particular loan. It was felt that an expert system could provide significant benefits to this process, which is extremely complex and involves large amounts of money. To our knowledge, expert systems technology had not previously been applied to this domain. Successful development and implementation of the system resulted in the realization of the anticipated benefits, and a few others as well."

Droy, Jean-Michel, Stéfan J. Darmoni, Philippe Massari, Thierry Blanc, Fabienne Moritz, and Jacques Leroy. SETH: an expert system for the management on acute drug poisoning. Abstract: "The aim of SETH is to give specific advice concerning the treatment and monitoring of drug poisoning. Currently, the data base contains the 1153 most toxic or most frequently ingested French drugs from 78 different toxicological classes. The SETH expert system simulates expert reasoning, taking into account for each toxicological class, delay, clinical symptoms and ingested dose. It generates accurate monitoring and treatment advice, addressing also drug interactions and drug exceptions. The implementation of SETH began in April 1992 in our Poison Control Center. SETH is then daily used by residents as telephone response support on drug poisoning. Between April 1992 and October 1994, 2099 cases inputted by residents were analysed by SETH. Since that time three phases of evaluation have been performed. We conclude that an expert system in clinical toxicology is a valuable tool in the daily practice of a Poison Control Center."

Durkin, John 1994. Expert Systems : Design and Development. New York: Maxwell Macmillan International. Beginners will find the overview in Chapter 1 especially useful, along with the appendix of expert systems applications, listed and summarized by field (agriculture, business, education, and much more). Sections of the book are quite technical.

Dzierzanowski, James, and Susan Lawson. 1992. The Credit Assistant: The Second Leg in the Knowledge Highway for American Express. In Proceedings of the Fourth Annual Conference on Innovative Applications of Artificial Intelligence, ed. Scott, A. Carlisle and Phillip Klahr, 127-134. Menlo Park, Calif.: AAAI Press. "This chapter describes the development and deployment of the credit assistant (CA), a knowledge-based system to support credit operations for Travel-Related Services (TRS) of the American Express Company. "

Feigenbaum, Edward A., Pamela McCorduck, and H. P. Nii. 1988. The Rise of the Expert Company: How Visionary Companies are Using Artificial Intelligence to Achieve Higher Productivity and Profits. New York: Times Books.

Fuchs J, Heller I, Topilsky M, and Inbar M. CaDet, a computer-based clinical decision support system for early cancer detection. Cancer Detect Prev. 1999;23(1):78-87. Excerpt from PubMed record: "Clinical and epidemiological data related to early cancer detection and to cancer risk factors was collected from the literature and incorporated in a database, together with heuristic rules for evaluating this data. Individual data obtained from patients through a questionnaire are input into CaDet, a computerized clinical decision support system. A report summarizing patient data and cancer hypotheses, with a scoring system that reflects degrees of alarm, is generated."

Hayes-Roth, Frederick, and Neil Jacobstein. 1994. The State of Knowledge-Based Systems. Communications of the ACM 37 (3): 27-39.

Helfman, Richard, Ed Baur, John Dumer, Tim Hanratty, and Holly Ingham. Turbine Engine Diagnostics (TED). AI Magazine 20(1): Spring 1999, 69-76. "Turbine engine diagnostics (TED) is a diagnostic expert system to aid the M1 Abrams tank mechanic find-and-fix problems in the AGT-1500 turbine engine. TED was designed to provide the apprentice mechanic with the ability to diagnose and repair the turbine engine like an expert mechanic. The expert system was designed and built by the U.S. Army Research Laboratory and the U.S. Army Ordnance Center and School. This article discusses the relevant background, development issues, reasoning method, system overview, test results, return on investment, and fielding history of the project. Limited fielding began in 1994 to select U.S. Army National Guard units and complete fielding to all M1 Abrams tank maintenance units started in 1997 and will finish by the end of 1998. The Army estimates that TED will save roughly $10 million a year through improved diagnostic accuracy and reduced waste. The development and fielding of the TED program represents the Army’s first successful fielded maintenance system in the area of AI. Several reasons can be given for the success of the TED program: an appropriate domain with proper scope, a close relationship with the expert, extensive user involvement, and others that are discussed in this article."

Jackson, Peter. Forthcoming. Introduction to Expert Systems, 3rd edition. London: Longman Addison Wesley. (Or see 2nd edition, 1986.)

Liebowitz, Jay. 1997. Handbook of Applied Expert Systems. Boca Raton, FL: CRC Press.

Mahesh, Kavi, and Sergei Nirenburg. 1997. Knowledge-Based Systems for Natural Language. In The Computer Science and Engineering Handbook, ed. Allen B. Tucker, Jr., 637-653. Boca Raton, FL: CRC Press, Inc.

Mann, Charles K., and Stephen R. Ruth, editors. 1992. Expert Systems in Developing Countries : Practice and Promise. Boulder, CO: Westview Press.

McDermott, J. 1982. A Rule-Based Configurer of Computer Systems. Artificial Intelligence 19 (1): 39-88.

Meltzer, S., and D. Sriram. 1990. ReValuator--An Expert System Approach to Actuarial Valuations . In Proceedings of the Second Annual Conference on Innovative Applications of Artificial Intelligence, ed. Rappaport, Alain and Reid Smith, 39-48. Menlo Park, Calif.: AAAI. "Expert system technology has now matured so that task-oriented business programs can be rapidly prototyped, developed, coded, and deployed on desktop and laptop personal computers. This rapid development and deployment is especially true when the task is well defined, and the target user has little knowledge in the specified domain. This paper sketches the successful implementation of an actuarial program designed to assist a nonactuary in detailed actuarial analysis."

Pereira, M.A., Schaefer, M.B., and Marques, J.L.B. Remote Expert System of Support the Prostate Cancer Diagnosis. In Proceedings of the 26th AnnualInternational Conference of the IEEE Engineering in Medicine and Biology Society. 2004. 26: 3412-3415. From the abstract: "This paper presents the development of a remote expert system in urological area to support the prostate cancer diagnosis. The prostate cancer is one of the most common cancers among men and the second most frequent death cause by cancer in men. The combination of expert system with the benefits of remote computing allows that several doctors and client applications of urological area use the benefits of expert system of support the detection of prostate cancer. ... The expert system presented good results, showing a great potential to support the physicians in the diagnosis of prostate cancer."

Phelps, R., F. Ristor, D. Mukherjee, et al. 1991. INCA-An Innovative Approach to Constructing Large-Scale Real-Time Expert Systems. In Innovative Applications of Artificial Intelligence 2, ed. Rappaport, Alain and Reid Smith, 3-14. Menlo, Ca: AAAI

Rich, Elaine, and Kevin Knight. 1991. Expert Systems. In Artificial Intelligence, New York: McGraw Hill. Chapter 20 gives a ten page overview of expert systems.

Shell, Pete, Gonzalo Quiroga, Juan A. Hernandez-Rubio, Eduardo Encinas, Jose Garcia, and Javier Berbiela. 1992. Cresus: An Integrated Expert System for Cash Management. In Proceedings of the Fourth Annual Conference on Innovative Applications of Artificial Intelligence, ed. Scott, A. Carlisle and Phillip Klahr, 151-170. Menlo Park, Calif.: AAAI. "Cresus is a unique application of state-of-the-art expert system technology to the real-world financial problem of cash management. By automating the work of company treasurers, it saves substantial amounts of both money and time every day. Real-world test cases show that cresus performs better and much faster than the human expert: In minutes, it generates a combination of operations that efficiently balances all banking accounts in a 15-day period. It uses user-friendly window technology to control the human-machine dialogue and has been integrated into the work environment of a major electric company in Spain. Written in Common Lisp using unix workstations, it was jointly developed by Union Fenosa, Carnegie Mellon University, and Norsistemas Consultores."

Stefik, Mark. 1995. Introduction to Knowledge Systems, San Francisco: Morgan Kaufmann. Beginners will find the Chapter 3 overview of expert systems especially useful, and will want to look at some of the other sections on symbol-level, knowledge-level, troubleshooting, and more.

Talebzadeh, Houman and Sanda Mandutianu, and Christian F. Winner. 1995. Countrywide Loan-Underwriting Expert System. AI Magazine 16(1): Spring 1995, 51-64. "Countrywide loan-underwriting expert system (clues) is an advanced, automated mortgage-underwriting rule-based expert system. The system was developed to increase the production capacity and productivity of Countrywide branches, improve the consistency of underwriting, and reduce the cost of originating a loan. The system receives selected information from the loan application, credit report, and appraisal. It then decides whether the loan should be approved or whether it requires further review by a human underwriter. If the system approves the loan, no further review is required, and the application is funded. clues has been in operation since February 1993 and is currently processing more than 8500 loans each month in over 300 decentralized branches around the country."

Torsun, I. S. 1995. Foundations of Intelligent Knowledge-Based Systems. New York: Academic Press.

Turban, Efraim, and Jr. Louis E. Frenzel 1992. Expert Systems and Applied Artificial Intelligence. New York: Maxwell Macmillan International.

Walker, Terri C., and Richard K. Miller. 1990. Expert Systems Handbook : An Assessment of Technology and Applications. Englewood Cliffs, NJ: Prentice-Hall.

Weiss, Sholom M., and Casimir A. Kulikowski. 1991. Computer Systems that Learn: Classification and Prediction Methods from Statistics, Neural Nets, Machine Learning, and Expert Systems. San Mateo, CA: Morgan Kaufmann.