© Jirsak/Shutterstock.com
3 Facts About MYCIN Expert System
- MYCIN was advanced for its time and had a competence level comparable to blood infection specialists and greater accuracy than general practitioners. The thought processes that it used were similar to human thought.
- Researchers wrote this system in Lisp, a set of multiple programming languages designed to work with artificial intelligence. This system was the first system of its kind invented for medical usage.
- MYCIN’s foundations came from another framework developed at Stanford called DENDRAL. This system helped find new chemical compounds in the organic chemistry field.
MYCIN Expert System History
Edward Shortliffe, the developer, was with the Department of Medicine and Computer Science at Stanford University School of Medicine. During its usage, this expert system provided recommendations about antibiotics to use for patients with meningitis. Advantages of this system included a high degree of accuracy; however, disadvantages included not exceeding human competency levels to that high a degree.
MYCIN Expert System: How It Worked
MYCIN was an expert system using backward chaining, a form of artificial intelligence. In this context, backward chaining helped determine that the patient had an infection and worked back through several steps to determine the type of bacteria and which antibiotics to use. Advantages included making it easier to find out the causes because of the known endpoint.
Quick Facts
- Created
- 1972
- Creator
- Edward Shortliffe
- Original Use
- MYCIN Expert System was a backward chaining expert system that was one of the earliest uses of artificial intelligence. Uses involved identifying bacteria occurring in blood infections and meningitis, among other bacterial infections. Another benefit was to find the right antibiotics for the type of infection and the proper dosage.
MYCIN Expert System: Historical Significance
Experts describe MYCIN Expert System as having laid the foundations for all similar systems, making the design stand out in computer history. Although disadvantages included having an acceptable, rather than a high level of accuracy, this tool helped pave the way for further advancement in artificial intelligence. The system saw a lot of testing but never saw use in a clinical setting.
Researchers have learned from the advantages and disadvantages of this system to use its foundation ns in other applications. Examples of expert systems that have used similar technology include PXDES and CaDet, which medical professionals use to predict and identify cancer.
