Expert Systems for the Prediction of Ovulation: Comparison of an Expert System Shell (Expertech Xi Plus) with a Program Written in a Traditional Language (BASIC)

Abstract

The use of an expert system shell (EXPERTECH Xi Plus) in the construction of an expert system for the diagnosis of infertility has been evaluated. A module was devised for predicting ovulation from the medical history alone. Two versions of this system were constructed, one using the expert system shell, and the other using QuickBASIC. The two systems have been compared with respect to: (1) ease of construction; (2) ease of knowledge base update; (3) help and explanation facilities; (4) diagnostic accuracy; (5) acceptability to patients and clinicians; (6) user-friendliness and ease of use; (7) use of memory space; and (8) run time. The responses of patients and clinicians were evaluated by questionnaires. The predictions made by the computer systems were compared to the conclusions reached by clinicians and to the “gold standard” of day 21 progesterone.

The conclusions of this pilot study are: (1) the construction of this expert system was NOT facilitated by the use of this expert system shell; (2) update of the knowledge base was not facilitated either; (3) the expert system shell offered built-in help and explanation facilities, but as the system increased in complexity these became less useful; (4) after initial adjustment of decision thresholds the diagnostic accuracy of the system equalled that of the clinician; (5) the patient response to computer history-taking was very favorable but much less favorable to computer diagnosis; (6) the clinicians took a positive attitude to computer diagnosis; (7) the systems were easy to use; (8) the expert systems shell required much more memory space and had a much slower response time than the system written in BASIC.

Key-Words

Computer-Aided Diagnosis - Expert Systems - Expert System Shell - Infertility

• REFERENCES

• 1 Shortliffe EH. Computer-Based Medical Consultations: MYCIN. New York: American Elsevier Publ; 1976
• 2 Weiss SM, Kulikowski CA, Amarl S, Safir A. A model-based method for computer-aided medical decision-making. Artif Intell 1978; 11: 145-72.
• 3 Pople HE. The formation of composite hypotheses in diagnostic problem solving. An exercise in synthetic reasoning. In: Proc 5th Int Conf Artificial Intelligence Vol 2. Los Altos Calif: M Kaufmann Publ; 1977: 1030-7.
• 4 Miller RA, Pople HE, Myers JD. Internist I, an experimental computer-based diagnostic consultant for general internal medicine. N Eng J Med 1982; 307: 468-76.
• 5 Pople HE. Heuristic methods for imposing structure on ill-structured problems; the structuring of medical reasoning. In: Szolovits P. ed. Artificial Intelligence in Medicine. Boulder CO: Westview Press; 1982: 119-90.
• 6 Szolovits P, Patil RS, Schwartz WB. Artificial intelligence in medical diagnosis. Ann Int Med 1988; 108: 80-7.
• 7 Ellis D. The artificial expert. In: Ellis D. ed. Medical Computing and Applications. Chichester: Ellis Horwood Publ; 1987: 81-117.
• 8 Schreiner A, Chard T. Some observations on the use of a “scoring system” in medical computer expert systems. (To be published).
• 9 Alvey PL, Myers CD, Greaves MF. High performance for expert systems: I. Escaping from the demonstrator class. Med Inform 1987; 12: 85-95.
• 10 Alvey PL, Preston NJ, Greaves MF. High performance for expert systems: II. a system for leukaemia diagnosis. Med Inform 1987; 12: 97-114.
• 11 Miller RA, McNeil MA, Challinor SM, Masai FE, Myers DJ. The INTERNIST-1/QUICK MEDICAL REFERENCE project: Status Report. West J Med 1986; 145: 816-22.
• 12 Teach RL, Shortliffe EH. An analysis of physicians’ attitudes. In: Buchanan BG, Shortliffe EH. eds. Rule Based Expert Systems: The MYCIN Experiment of the Stanford Heuristic Programming Project. Reading Mass: Addison-Wesley Publ; 1984: 635-52.
• 13 Adams ID, Chan M, Clifford PC. et al. Computer aided diagnosis of acute abdominal pain: a multicentre study. Br Med J 1986; 293: 800-4.
• 14 de Dombal FT, Leaper DJ, Staniland JF, McCann AP, Horrocks JC. Computer aided diagnosis of acute abdominal pain. Br Med J 1972; 02: 9-13.
• 15 de Dombal FT, Leaper DJ, Horrocks JC, Staniland JT, McCann AP. Human and computer aided diagnosis of acute abdominal pain: further report with emphasis on performance of clinicians. Br Med J 1974; 01: 376-80.
• 16 Carroll B. Artificial intelligence: expert systems for clinical diagnosis: are they worth the effort?. Behav Sci 1987; 32: 274-92.
• 17 Clancey WJ, Letsinger R. NEOMYCIN: Reconfiguring a rule-based expert system for application to teaching. In: Proc 7th Int Congress Artificial Intelligence Vol 2. Los Altos Calif: M Kaufmann. Publ; 1981: 829-36.
• 18 Lilford RJ, Bingham P, Fawdry R, Setchell M, Chard T. The development of on-line history-taking systems in antenatal care. Meth Inform Med 1983; 22: 189-97.
• 19 Lilford RJ, Evans D G, Chard T. The use of a patient-interactive micro-computer system to obtain histories in an infertility and gynaecological endocrinology clinic. Am J Obstet Gynec 1983; 15: 374-9.
• 20 Lilford RJ, Bingham P, Bowe GL, Chard T. Computerized histories facilitate patient care in a termination of pregnancy clinic: the use of a small computer to obtain and reproduce patient information. Br J Obstet Gynaec 1985; 92: 333-40.
• 21 Puppe B, Puppe F. A knowledge representation concept facilitating construction and maintenance of large knowledge bases. Meth Inform Med 1988; 27: 10-6.
• 22 Salzman GC, Krall RB, Marinuzzi JG. Knowledge engineering software: a demonstration of a high-end tool. Ann Quant Cytol Histol 1988; 10: 219-24.
• 23 Wiener F. SMR simulating medical reasoning – an expert shell for non-AI experts. Comp Meth Prog Biomed 1988; 26: 19-32.
• 24 Chaver RM. SNET: Integrating hypermedia and decision analysis for medical expert systems. Med Dec Making 1988; 08: 329.