Mycin

From Wikipedia, the free encyclopedia

Mycin was an expert system developed over 5 or six years in the early 1970s at the Stanford University; it was written in Lisp, by Edward Shortliffe under the direction of Bruce Buchanan and others; it derived from the earlier Dendral expert system, but considerably modified and extended the basic Dendral software. This computer system was designed to diagnose infectious blood diseases and recommend antibiotics, with the dosage adjusted for patient's body weight — the name derived from the antibiotics themselves, as many antibiotics have the suffix "-mycin".

1 Method
2 Results
3 Practical use
4 See also
5 Reference
6 External link

[edit] Method

Mycin operated using a fairly simple inference engine, and a knowledge base of ~500 rules. It would query the physician running the program via a long series of simple yes/no or textual questions. At the end, it provided a list of possible culprit bacteria ranked from high to low based on the probability of each diagnosis, its confidence in each diagnosis' probability, the reasoning behind each diagnosis (that is, Mycin would also list the questions and rules which led it to rank a diagnosis a particular way), and its recommended course of drug treatment.

Despite Mycin's success (see below), it is often now used as a cautionary tale in AI courses for people who generate their own ad hoc probability frameworks. Mycin had a limited depth to its reasoning hierarchy due to the noise introduced by its certainty factor system. This problem can be solved by using a rigorous probablistic framework, such as Bayesian statistics.

[edit] Results

Research conducted at the Stanford Medical School found MYCIN to have a correct diagnosis rate of about 65%, which was better than most physicians who were not specialists in diagnosing bacterial infections, and only slightly worse than those physicians who were themselves experts in the field (average correct diagnosis rate of about 80%).

[edit] Practical use

Mycin was never actually used in practice. This wasn't because of any weakness in its performance — in tests it outperformed members of the Stanford medical school. It was as much because of ethical and legal issues related to the use of computers in medicine — if it gives the wrong diagnosis, who can be held responsible? Issues with whether human experts would find it acceptable to use arose as well.

A difficulty that rose to prominence during the development of Mycin and subsequent complex expert systems has been the extraction of the necessary knowledge for the inference engine to use from the humans expert in the relevant fields into the rule base (the so-called knowledge engineering).