Academia.eduAcademia.edu

Outline

Title
Abstract
Statistical Methods
The Value of Raw Data
Clustering Methods
Kernel Method
Nearest-Neighbours Method
The Spiegelhalter-Knijl-Jones Method
If Antecedent Then Conclusion
Descriptive Methods
Discussion
Patient Specific Models
Combining Statistical and Knowledge-Based Methods
Monte Carlo Inference Methods
Scarcity of Training Data
Test Data Retrospective VB Prospective
Trial Design
References
All Topics
Computer Science
Artificial Intelligence

An interoduction to expert system

Profile image of aa aaaa aa

Abstract

This monograph provides an introduction to the theory of expert systems. The task of medical diagnosis is used as a unifying theme throughout. A broad perspective is taken, ranging from the role of diagnostic programs to methods of evaluation. While much emphasis is placed on probability theory, other calculi of uncertainty are given due consideration.

Related papers

Expert systems and expert behavior
Walton Sumner

Journal of Medical Systems, 1992

Iliad 4.0 and QMR 2.03 are computer-based diagnostic knowledge bases that can play many roles in decision support and other areas of medical practice, but neither appears ready to assume the role of an expert diagnostic consultant. In contrast to human experts, these programs have problems related to recognition of their own limitations, interpretation of continuous data, recognition of dependent findings, selection of tests, and description of the impact of certain tests. Suggestions to improve these aspects of knowledge bases are offered.

View PDFchevron_right
Usage of Expert Classification in Diagnostic Expert Systems ’ Knowledge Bases Construction
Aleksandr Koval

2019

Studies of resent years in the field of artificial intelligent led to a number of major achievements. The most significant of these was the development of powerful computer systems, known as systems based on knowledge. They are based on the program, designed to represent and apply actual knowledge from subject domain to problem solving. Diagnostic belongs to weakly structured domains, so that the essential (sometimes only) source of information in this domain is experts. In this paper the possibility of computerized construction of diagnostic expert systems’ knowledge bases is described on the basis of solving the problem of expert classification. The described in the work approach provides a complete build of consistent knowledge bases of diagnostic expert systems.

View PDFchevron_right
Expert Systems For Technical Diagnosis-Some Practical Issues
Danail Dochev

In: Proc. IEA/AIE'93, 1993

View PDFchevron_right
Towards validation of expert systems as medical decision aids
Marius Fieschi

International journal of bio-medical computing, 1990

Expert system evaluation is an important step in knowledge engineering development and is clearly not a simple process. The aim of this paper is to introduce methodological aspects of medical knowledge base validation. We distinguish two components of the evaluation: verification and validation. In the first part, the difficulties of evaluation are analysed, problems with some techniques used in the evaluation process are discussed. In the second part, our experiment gives guidelines to present these aspects and underline what and when to evaluate.

View PDFchevron_right
Expert System-A Review Article .
Ijesrt Journal

International Journal of Engineering Sciences & Research Technology, 2013

One of the largest area of applications of artificial intelligence is in expert systems, or knowledge based systems as they are often known. This type of system seeks to exploit the specialised skills or information held by group of people on specific areas. It can be thought of as a computerised consulting service. It can also be called an information guidance system. Such systems are used for prospecting medical diagnosis or as educational aids. They are also used in engineering and manufacture in the control of robots where they inter-relate with vision systems.

View PDFchevron_right
Expert System for Diseases diagnosis
Moshood A Hambali

It is moral responsibility of a nation to provide good medical services to the people because healthy people make healthy nation. Medical science field is a gargantuan and complex field that requires a large number of expertises. It is obvious that developing countries are facing challenge of shortage of medical expertise in medical science which eventually affects the traditional method of diagnosing diseases. Due to this, they are unable to provide sound medical services to patients. Patients also get to hospital to meet a huge number of queues. This paper addresses the various challenges that exist in the traditional method of disease diagnosis. A rulebased expert system is developed to diagnose Malaria, Typhoid Fever, Cholera, Tuberculosis, and Breast Cancer. The proposed Medical Expert System (MES) contains forty six (46) rules to effectively diagnose the diseases. The system is found capable of assisting medical experts in diagnosing diseases and to provide good health services to their patients.

View PDFchevron_right
Problems in applying expert system technology to Radiographic Image Interpretation
Masataka Uetani

Journal of Digital Imaging, 1989

View PDFchevron_right
Development of an Expert System for Reducing Medical Errors
Mohamed Ramadan

International Journal of Software Engineering & Applications, 2013

Recent advances in patient safety have been hampered by the hard dealing with the development of a uniform classification of patient safety concepts in a systematic way. Therefore, many believe that medical expert systems have great potential to improve health care. A framework for computer-based medical errors diagnoses of primary systems' deficiencies is presented. Results of this research assisted in developing the hierarchical structure of the medical errors expert system which was written and complied in CLIPS. It has 225 rules, 52 parameters and 830 conditional paragraphs. The system prompts the user for response with suggested input formats. The system checks the user input for consistency within the given limits. In addition, the system was validated through numerous consultations with the experts in the field. The benefits that are gained from such types of expert systems are eliminating the fear from dealing with personal mistake, and providing the update information and helps medical staff as a learning tool.

View PDFchevron_right
Expert systems: An overview
Stephen Kaisler

IEEE Journal of Oceanic Engineering, 1986

The purpose of this article is to introduce readers to the basic principles of rule-based expert systems. Four topics are discussed in subsequent sections: (1) Definition; (2) Structure of an expert system; (3) State of the art and (4) Impact and future research.

View PDFchevron_right
Expert Systems Based Clinical Assessment and Tutorial Project
Frank Papa

1992

This project at the Texas College of Osteopathic Medicine (Fort Worth) evaluated the use of an artificial-intelligence-derived measure, "Knowledge-Based Inference Tool" (KBIT), as the basis for assessing medical students' diagnostic capabilities and designing instruction to improve diagnostic skills. The instrument was designed to address the problem that, in medicine, diagnostic expertise is problem-specific and appears to be more a factor of the student's knowledge base than cognitive skills. This study determined that the KBIT produced reliable and valid (based on comparisons of diagnostic accuracy of experts with those of novices) for four different problem areas: Weakness, Red Eye, Papulosquamous Disorders, and Elevated Creatinine. Additionally the study showed that two expert/KBIT-derived instructional approaches significantly improved the diagnostic accuracy of treatment student groups when compared to a control group and to students conventionally trained. After the executive summary and a project overview, this report describes the project's background and origins, its components and activities, and results. Attached is a related article titled "An Expert Program Shell Designed for Extracting Disease Prototypes' and Their Use as Models for Exploring the 'Strong Problem-Solving Methods' Employed in Clinical Reasoning" (F.J. Papa; S. Meyer). (DB)

View PDFchevron_right

References (81)

  1. fuzzy relation R is a. fuzzy subset of aX p, where a and {J are the domain and range types of R, respectively. The degree of membership PR( U, v) of a. pair (tt, v) to R is the degree to which R rela.tes u to v. For example, regarding scores obta.ined by rolling a die, let LOTLESS be the relation 'is a lot lower than'. Shown below is ODe possible characteriza tion of this relation. PLOTLESS == {(I, 1)~0.0, (I, 2)~0.l, (1, 3) ~0.5, (1, 4) ~0.
  2. 9, (1, 5) ~ 1.0, (1, 6)~ 1.0, (2, 1) ~ 0.0, (2, 2)~0.0, (2, 3)~ 0.1, (2, 4)~0.5, (2, 5)~0.9, (2,6)~ 1.0, (3, 1) ~ 0.0, (3, 2)~0.0, (3, 3) ~O.O. (3,4)~0.1, (3, 5) ~0.2, (3,6)~0.7, (4, 1) ~O.O, (4, 2)~0.0, (4, 3) ~O.O, (4,4)~0.O, (4, 5)~0.1, (4,6)~0.3, (5, 1) ~O.O, (5, 2)~0.0, (5, 3)~0.0, (5,4)~ 0.0, (5, 5)~0.0, (5,6)~ 0.1, (6, 1) ~O.O, (6, 2)~0.0, (6, 3)~0.0, (6,4)~ 0.0, (6,5)~0.0, (6,6)~0.O) In general, if we know that two variables x : a. and y : fJ are relat.ed by a relation R, where IlR : (0 X fJ) -. [0,11, and we learn the actual value of x, then we can infer that y lies in the (fuzzy) image of x through R. For exa.rnple, suppose x and yare the scores obtained on two consecutive rolls of a die, and we are told that x 'is a lot lower than' y. If then we learn that x is act11ally 2, adopting the characterization of LOTLESS given above we can conclude that y is a member of the set B where J1-B = oX v: fJ. J1-LoTLESS(2, v)
  3. I ~ 0.0, 2 ~ 0.0, 3 ~ 0.1, 4 ~ 0.5, 5 ~ 0.9, 6 ~ 1.0} J1-HIGH So we conclude that y is 'high'. The Compositional Rule of Fuzzy Inference In the case that all we knO\\i of x is, say, that it is either 2 or 3, we obtain two alternative fuzzy restrictions on y, either of which may be appropriate. Naturally, therefore, the resulta.nt set is given by the fuzzy uuion of the two. This pdnciple readily extends to larger (crisp) sets of possible values of x. Zadeh [Zad73] generalized this principle to the case when the vaJue of x is known only fuzzily. This is expressed as the 'Compositional Rule of Fuzzy Bibliography [Ada;
  4. Adams JB. A probability model of medical reasoning and the MYCIN model. Jvfathematical Biosciences (1976) 32 177 86.
  5. Adams ID, Chan M, Clifford PC, Cooke WM, Dal los Y, De Dombal FT, Edwards MH, Hancock DM, Hewett DJ, McIntyre N, Somerville PG, Spiegel hal ter DJ, Wellwood J, Wilson DH. Computer~aideddiag nosis of acute abdominal pain: a. multicentre study. British Medical Jaurnal (1986) 293800-4.
  6. Adlassnig KP. A fuzzy logical model of computer-assisted medical diagnosis. Methods of Information in Medicine (1980) 19 iii 141-8.
  7. Aikens JS, Kunz JC, Fallat RJ. PUFF: an expert sys tem for interpretation of pulmonary function data. Comput ers and Biomedical Research (1983) 16 199-208.
  8. Aikens JS. Prototypical knowledge for expert 5ystems. At•• tiftcial Intelligence (1983) 20 163~210. [Ait76} Aitchison J, Aitken eGG. Multivariate binary discrimi nation by the kernel method. Biometrika (1976) 63 iii 413• 20.
  9. Anderson JA. Logistic discrimination, in Krishnaiah PR, Kanal LN (eds). Handbook of Statistics 2. North Holland, Amsterdam, New York, Oxford (1982) 169-91.
  10. Andreassen SM, Woldbye M, Falck B, Andersen SK. MUNIN -a causal probabilistic network for interpretation of electromyograpruc findings. Proceedings of the 10 th Inter national Joint Conference on Artificial Inte1l1'gence (1987) Milan, Italy. 88
  11. Bellman RE, Giertz M. On the analytic formalism of the theory of fuzzy sets. Information Sciences (1973) :1 149-56.
  12. Bleisch HL. Computer-based consulta.tion. American Jour nal of Medicine (1972) 53 285-91.
  13. Cargile J. The sorites pa.ra.dox. British Journal for Philos ophy of Science (1969) 20 193-202.
  14. Chard T. The effect of dependence on the performance of Ba.yes l theorem: an eva.luation using computer simulation. Computer Methods and Programs in Biomedicine (1989) 29 i 15-9.
  15. Clocksin WF, Mellish es. Programming in Prolog.
  16. Springer-Verla.g: BerHn, Heidelberg, New York (1981).
  17. Cooper GF. Current research directions in the development of expert systems based On belief networks. Applied Stochas tic Models and Data Analysis (1989) 5 i 39-52.
  18. Corlett RA, Todd SJ. A Monte Carlo approach to uncer tain inference, in Artificial Intelligence and its Applications.
  19. Croft OJ. Is computerized diagnosis possible? and Biomedical Research (1972) 5 351-67.
  20. Computers [D.w76] Dawid AP. Properties of diagnostic data distributions. Bio metrics (1976) 32647-58.
  21. Dempster AP. Upper and lower probabilities induced by a multi~valued mapping. Annals of Mathematical Statistics (1967) 38 ii 325-39.
  22. De Dombal FT, Leaper DJ, Staniland JR, McCann AP, Horrocks JC. Computer-aided diagnosis of a.c:ute ab dominal pain. British Medical Journal (1972) 2 9•13.
  23. De Dombal FT. Medical diagnosis from a clinicia.n's point of \flew. Methods of Infonnalion in Medicine (1978) 17 i 28 35.
  24. De Dombal FT. Diagnosis 0/ Acute Abdominal Pain. Churchill Livingstone: Edinburgh, New York, London (1980).
  25. De Dombal FT. Clinical decision making and the com puter: consultant, expert, or just another test? British Jour rial of Healthcare Computing (1984) 1 7-14.
  26. Duda R, Gaschnig J, Hart P. Model design in the PROSPECTOR consultant system for mineral exploration, in Michie D (ed). Expert Systems in the Micro-Electronic Age. Edinburgh University Pre6s: Edinburgh (1979) 153-67.
  27. Edwards DAW. Flow charts, diagnostic keys, and algo rithms in the diagnosis of dysphagia. Scottish Medical Jour nal (1970) 15 x 378-85.
  28. Fleschi M. ArtiJiciallntelligence in Medicine. Chapman and Halt: London, New York, Tokyo, Melbourne, Madras (1990).
  29. Fox JR, Alvey P. Computer-assisted medical decision making. British Medical Journal (1983) 287 742-6.
  30. Fryback DG. Bayes' theorem and conditional nonindepen dence of data in medical diagnosis. Computers and Biomed ical Re5earch (1978) 11 423-34.
  31. Gaines BR. Foundations of fuzzy reasoning. International Journal 0/ Man-Machine Studies (1976) 8 vi 623-68.
  32. Gill PW, Leaper DJ, Guillou PJ t Staniland JR , Hor rocks JC, De Dombal FT. Observer variation in clinical diagnosis -a computer-aided assessment of its magnitude and importance in 552 patients with abdominal pain. Methods 0/ In/ormation in Medicine (1973) 12 ii 108-13.
  33. Goguen JA. The logic of inexact concepts. Synthese (1969) 19325-73.
  34. Golumbic MC. Algorithmic Graph Theory Graphs. Academic Press: London (1980). and Perfect [Goo85] Goodall A. The Guide to Expert Systems. Learned Infor mation: Oxford, New Jersey (1985).
  35. Hajek P. Combining functions for certainty degrees in COD suJting 6ystems. International Journal of Man•Machine Stu.d ies. (1985) 22 59-76.
  36. Heckerman D. Proba.bilistic interpretations for MYCIN's certainty factors, in Kanal LN, Lemmer JF (eds). Uncer tainty in Artificial Intelligence. North~Holla.nd: Amsterdam, New York, Oxford, Tokyo (1986).
  37. Hersh HM, Caramazza A. A fuzzy set approach to mod~ ifiers and vagueness in natural la.nguage. Journal of Experi mental Psychology, General (1976) 105 iii 254-76.
  38. Jackson P. Introduction to Expert Systems. Wesiey, Reading Mass. (1985). Addison [J..87] Jaspers RBM, van der Helm FCT. Computer-aided di~ agnosis and treatment of brachial plexus injuries. Ledur€ Notes in Medical Informatics (1987) 33 237-46.
  39. Knill-Jones RP. A formal a.pproach to symptoms in dys pepsia. Clinics in Gastroenterology (1985) 14 iii 517-29.
  40. Lauritzen SL, Spiegelhalter DJ. Local computation with probabilities on graprucal structures and their application to expert systems. Journal of the Royal Statistical Society (Se~ rie' B) (1988) 50 ii 157-224.
  41. Lipkin ML, Hardy JD. Mechanical correlation of data in differential diagnosis of hematological diseases. Journal of the A merican Medical Association (1958) 166 ii 113-25.
  42. Lippmann RP. An introduction to computing with neural nets. IEEE Acoustics, Speech and Signal Processing Society Magazine (1987) April 4-22.
  43. Ludwig D, Heilbronn D. The design and testing of a new approach to computer-aided differential diagnosis. Methods of Information in Medicine (1983) 22 iii 156-66.
  44. McDermott J. R1: A rule-hased configurer of computer systems. Artificial Intelligence (1982) 19 i 39-88.
  45. Michie D. Personal Models of Rationality. Joumal of Sta tistical Planning and Inference (1990) 25 381-99.
  46. Miller RA, Pople HE, Myers JD. INTERNIST-II an ex perimental coInputer-based diagnostic consultant for general internal medicine. New England lo'u.mal 0/ Medicine (1982) 307 viii 468-76.
  47. Na.s54J
  48. Nash FA. Differential diagnosis: an apparatus to assist the logical faculties. Lancet (1954) 1 874-5.
  49. Neapolitan RE. Probabilistie Reasoning in Expert Syslems. John Wiley: New York, Chichester, Brisbane, Toronto, Sin gapore (19R9).
  50. Norusis MJ, Jacquez JA. Diagnosis I. Symptom noninde pendence in mathematical models for diagnosis. Computer's and Biomedical Research (1975) 8 156-72.
  51. Norusis 1\1J, Jacquez JA. Diagnosis II. Diagnostic mod els based on attribute clusters: a proposal and comparisons. Computers and Biomedieal Research (1975) 8 173-88.
  52. PatH RS, Szolovits P, Schwartz WH. Modeling knowl edge of the patient in acid-base and electrolyte disorders, in Szolovits P (ed). AAAS Selected Symposium 51. Bowker Publishing Company: Epping (1982) 191-226.
  53. Pauker SG, Gorry GA, Kassirer JP, Schwarz WH. Towards the simulation of clinical cognition. Taking a present illness by computer. A merican Journal 0/ Medicine (1976) 60 981-96.
  54. Pearl J. Fusion, propagation, and structuring in belief net works. Artificial InteUigence (1986) 29 241-88.
  55. Pearl J. Evidential reasoning using 6tochastic simulation of causal models. Artificial Intdligence (1987) 32245-57.
  56. Peng Y, Reggia JA. A probabilistic causal model for diag nostic problem solving -Part I: integrating symbolic causal inference with numeric probabilistic inference. IEEE Trans action." on Systems, Man and Cybernetics (1987) 17 ii 146 62.
  57. Pople HE. Evolution or an expert system: from Internist to Caduceus, in De Lotto I, Stefanelli M (eds). Artificial Intelligence in Medicine. North-Holland: York, Oxford, Tokyo (1985) 179-208.
  58. Amsterdam, New
  59. Rumelhart DE, Hioton GE, Williams RJ. Learning representations by back-propagating errors. Nature (1986) 323 ix 533-6.
  60. Sandell HSH, Bourne JR. Expert systems in medicine: a biomedjcal engineering perspective. Critical Reviews in Biomedical Engineering (1985) 12 95-129.
  61. Seroussi B, The ARC & AURC Cooperative Group. Comparison of several discrimination methods: application to the acute abdomen pain diagnosis. Lecture Notes in Med ical Informatics (1985) 28 12-8.
  62. Seroussi B, The ARC & AURC Cooperative Group. Computer-aided diagnosis of acute abdominal pain when taking into account interactions. Methods of In/ormation in Medicine (1986) 25 iv 194-8.
  63. Seymour DG, Green M t Vaz FG. Making better de cisions: construction of clinica.l scoring systems by the Spiegelhalter-Knill-Jones approach. British Medical Journal (1990) 300 223-6.
  64. Shafer G. A Mathematical Theory of Evidence. Princeton University Press: Princeton, New Jersey (1976).
  65. Shortliffe EH. Computer~basedmedical consultations: MYCIN. American Elsevier: New York (1976).
  66. Shortliffe EH, Scott AC, Bischoff MB, Cambell AB, van Melle W, Jacobs CD. ONCOCIN: an expert system for oncology protocol management. Proceedings of the 7 th In ternational Joint Conference on Artificial Intelligence (1981) 876-81.
  67. Spiegelhalter DJ, Knill-Jones RP. Sta.tistical a.nd knowledge~ba.sed approa.ches to clinical decision.support sys tems, with a.n applica.tion in gastroenterology. Journal of the Royal Statistical Society (Series A) (1984) 147 i 35-77_
  68. Stanfill C, Waltz D. Toward memory-based reasoning. Communications of Ihe ACM (1986) 29 xii 1213•28.
  69. Sutton GC. Computer-aided diagnosis: Journal of Surgery (1989) 76 i 82-5.
  70. Swets JA. Measuring the accuracy of diagnostic systems. Science (1988) 240 1285-93.
  71. Tarjan RE, Yannakakis MY. Simple linear-time algo rithms to test chordaJity of graphs, test acyclidty of hy pergraphs, and selectively reduce acyclic hypergraphs. SIAM Journal on Computing (1984) 13 iii 566-79,
  72. Teach RL, Shortliffe EH. An analysis of physician at titudes re/!;arding computer-based clinical consultation sys tems. Computers and Biomedical Research (1981) 14 vi 542 58. ITit80] Titterington DM. A comparative study of kernel-ba'Jed density estimates for categorical data. Technometrics (1980) 22 ii 259-68.
  73. Tutz G. An alternative choice of smoothing for kernel based density estimates in discrete discriminant analysis. Biometrika (1986) 73 ii 405-11.
  74. Vastola EF. Assign: an automated screening system in gen eral neurology. Computers in Biology and Medicine (1973) 3 ii 101-9.
  75. Weiss SM, Kulikowski CA, Amarel S, Safir A. A model-based method for computer-aided medical decision making. Artificial Intelligence (19i8) 11 145-72.
  76. Winter RM, Baraitser M, Douglas JM. A computerized data base for the diagnosis of rare dysmorphic syndromes. Journal 0/ Medical Genetics (1984) 21 ii 121-3.
  77. Yu VL, Fagan LM, Wraith SM, Clanl:ey WJ, Scott AC, Hannigan J, Blum RL, BUl:hanan BG, Cohen SN. Antimicrobial selection by computer: a blinded evaln ation by infectious disease experts. Journal of the American Medical Association (1979) 242 1279-82.
  78. Zadeh LA. Fuzzy sets. In/ormation and Control (1965) 8 338-53.
  79. Z.d72] Zadeh LA. A fuzzy-set-theoretic interpretation of linguIstic hedge•. Journal of Cybernetic. (1972) 2 4-34.
  80. Z.d73] Zadeh LA. Outline of a new approach to the analysis of complex systems and decision processes. IEEE Trnnsactions on Systems, Man and Cybernetics (1973) 3 i 28-44.
  81. Zentgraf R. A note on Lancaster's definition of higher-order interactions. Biometrika (1975) 62 ii 375-78.

Related papers

An introdoction to expert systems
aa aa

This monograph provides an introduction to the theory of expert systems. The task of medical diagnosis is used as a unifying theme throughout. A broad perspective is taken, ranging from the role of diagnostic programs to methods of evaluation. While much emphasis is placed on probability theory, other calculi of uncertainty are given due consideration.

View PDFchevron_right
Medical Diagnosis and Expert Systems: Solving Problems, Problem Structures and Bayesian Networks
Xavier Huvelle

Medical Diagnosis and Expert Systems have a particular relationship. Since the birth of the Heuristic program from the Heuristic group headed by Feigenbaum and the beginning of the twentieth one century there were a lot of changes. In the first part of this paper I will introduce the topic of Medical Diagnosis and Expert Systems and how they are related. In the second part I will describe a small part of this story and how those changes can give us a different perspective about the development of Artificial Intelligence programs. The third part will be dedicated to Problem Solving and the structure of how we conceive problems. This part has its importance for explaining the differences of the solving methods for particular problem structures. The fourth part of this paper will characterize the Bayesian Networks and their links in structuring problems.

View PDFchevron_right
Medical Expert Systems for Diagnosis of Various Diseases
Jimmy Singla

International Journal of Computer Applications, 2014

Diseases should be treated well and on time. If they are not treated on time, they can lead to many health problems and these problems may become the cause of death. These problems are becoming worse due to the scarcity of specialists, practitioners and health facilities. In an effort to address such problems, studies made attempts to design and develop expert systems which can provide advice for physicians and patients to facilitate the diagnosis and recommend treatment of patients. This review paper presents a comprehensive study of medical expert systems for diagnosis of various diseases. It provides a brief overview of medical diagnostic expert systems and presents an analysis of already existing studies.

View PDFchevron_right
An Introduction to Expert Systems
Arthur DeTore

1989

As indicated in the quote above, the great Sherlock Holmes (and his physician creator, Sir Arthur Conan Doyle) realized the limitation of human memory and thought. A recent editorial in the Annals of Internal Medicine discussed this problem in the context of modern medicine and similarly referred to "the brain’s limited capacity for storage and processing" of medical information.2 In the past, physicians have attempted to overcome these limitations by the use of referrals, journals and textbooks but with unsatisfactory results.3 The conclusions of a study undertaken by the Massachusetts Medical Society and the National Academy of Sciences suggested that the situation could be improved with computer technology.4 One type of advanced computer technology designed specifically to assist in decision making is expert systems, the product of research in artificial intelligence.

View PDFchevron_right
Special issue: Medical Expert Systems
Keith Sullivan

The objective of our study is to design an expert system by modelling the knowledge and thinking process of a doctor. A fuzzy logic controller (FLC) is used to model the process and a genetic algorithm (GA) helps to select a number of good rules from a manually constructed large rule base of an FLC, based on the opinion of 10 doctors. The GA-based tuning is done off-line. Once the optimized rule base of the FLC is obtained, it can diagnose the disease, on-line. The scope of the present work has been extended to two diseases, namely Pneumonia and Jaundice. The symptoms of each disease are fed as inputs to the FLC and the output, i.e., grade of a disease is determined.

View PDFchevron_right

Related topics

  • Artificial Intelligence
  • Statistics
    • 580 California St., Suite 400
    San Francisco, CA, 94104
    © 2025 Academia. All rights reserved