Methods Inf Med 1988; 27(03): 111-117
DOI: 10.1055/s-0038-1635530
Original Article
Schattauer GmbH

Pro. M. D. - A Diagnostic Expert System Shell for Clinical Chemistry Test Result Interpretation

Pro. M.D. - Eine diagnostische Expertensystemschale zur Interpretation von klinischchemischen Untersuchungsergebnissen
B. Pohl
1   (From the Institute of Laboratory Medicine [Director: Prof. Dr. Chr. Trendelenburg], Klinikum der Stadt Frankfurt, Frankfurt, FRG)
,
Chr. Trendelenburg
1   (From the Institute of Laboratory Medicine [Director: Prof. Dr. Chr. Trendelenburg], Klinikum der Stadt Frankfurt, Frankfurt, FRG)
› Institutsangaben
Weitere Informationen

Publikationsverlauf

Publikationsdatum:
17. Februar 2018 (online)

Summary

The history and main features of the diagnostic expert system Pro. M. D. are presented. An illustrative case report from a knowledge base for the evaluation of disorders of lipid metabolism helps to explain Pro. M. D.’s functions. The knowledge representation syntax is explained for the different types of rules. Knowledge bases currently in development are outlined. A new concept of probability reasoning and other recent improvements are discussed briefly. Implementation details are described with special regard to the inference function. Evaluation problems are discussed and Pro. M. D. is compared to other known diagnostic computer systems.

Die Entstehung und die wichtigsten Merkmale von Pro. M.D. werden vorgestellt. Ein beispielhafter Ergebnisbericht, der mit Hilfe einer Wissensbasis zur Diagnose von Fettstoffwechselstörungen erstellt wurde, erläutert die Arbeitsweise von Pro. M.D. Die Syntax der Wissensnotation wird für die verschiedenen Regeltypen erklärt. Auf die bisher entwickelten und die sich noch in Entwicklung befindlichen Wissensbasen wird eingegangen. Ein neues Konzept zur Wahrscheinlichkeitsrechnung und andere neue Verbesserungen werden kurz diskutiert. Details der Implementierung, insbesondere der Schlußfolgerungsfunktion, werden erläutert. Probleme der Evaluationen werden besprochen und eine Einordnung vergleicht Pro. M.D. mit anderen diagnostischen Computersystemen.

 
  • REFERENCES

  • 1 Adlassnig K. P. A Fuzzy Logical Model of Computer-Assisted Medical Diagnosis. Meth. Inform. Med 1980; 19: 141-148.
  • 2 Adlassnig K. P, Kolarz G, Scheithauer W. Present State of the Medical Expert System CADIAG-2. Meth. Inform. Med 1985; 24: 13-20.
  • 3 Adlassnig K. P, Kolarz G, Scheithauer W, Grabner H. Approach to a Hospital-Based Application of a Medical Expert System. Med. Inform 1986; 11: 205-223.
  • 4 Albert A. On the Use and Computation of Likelihood Ratios in Clinical Chemistry. Clin. Chem 1982; 28: 1113-1119.
  • 5 Allen J. F. An Interval-Based Representation of Temporal Knowledge. Proc. 7th IJCAI. 1981: 221-226.
  • 6 Bayes T. An Essay towards Solving a Problem in the Doctrine of Chances. Philos. Trans. R. Soc. Lond. (Biol.) 1753; 53: 370
  • 7 Bubser S. Syntaxgesteuertes Werkzeug zur inkrementellen Generierung und Modifikation von Wissensbasen. Diplomarbeit, Univ. Heidelberg. 1988
  • 8 Buchanan B. G, Shortliffe E. H. Rule-Based Expert Systems. Reading, Massachusetts: Addison-Wesley; 1984
  • 9 Clayton P. D, Gardner R. M, Larsen K. G, Pryor T. A, Warner H. R. HELP/PATHLAB Integration – A Decade of Experiences using an Expert System Interface to a Clinical Laboratory System. Proc. 5th International Conference on Computing in Clinical Laboratories, Stuttgart, June 1985. Brak-kenheim: Verlag Georg Kohl; 1985: 108-113.
  • 10 Clocksin W. F, Mellish C. S. Programming in Prolog. New York: Springer; 1981
  • 11 Coleman T. G, Randall J. E. HUMAN – A Comprehensive Physiological Model. The Physiologist 1983; 26: 15-21.
  • 12 Davenport P. M, Morgan A. G, Darnborough A, de Dombal F. T. Can Preliminary Screening of Dyspeptic Patients Allow More Effective Use of Investigational Techniques?. Brit. Med. J 1985; 290: 217-220.
  • 13 diPrimero F, Brewka G. BABYLON: Kernel System of an Integrated Environment for Expert Systems Development and Operation. Proc. 5th Int. Workshop on Expert Systems and their Applications, Avignon. 1985: 573-583.
  • 14 de Dombal F. T, Leaper D. J, Staniland J. R, McCann A. P, Horrocks J. C. Computeraided Diagnosis of Acute Abdominal Pain. Brit. Med. J 1972; II: 9-13.
  • 15 de Dombal F. T. Medical Diagnosis from a Clinician’s Point of View. Meth. Inform. Med 1978; 17: 28-35.
  • 16 de Dombal F. T. Evaluation of Decision Making by Humans and Computers in Acute Abdominal and Acute Chest Pain. Lecture Notes in Medical Informatics, Vol. 22. Berlin – Heidelberg – New York – Tokyo: Springer; 1983: 42-53.
  • 17 Dempster A. P. A Generalization of Bayesian Inference. Roy. Statis. Soc. Ser. B 1968; 30: 205-247.
  • 18 Dickinson C. J. A Computer Model of Human Respiration. Lancaster, England: MTP Press Ltd; 1977
  • 19 Duda R. O, Hart P. E, Nilsson N. J. Subjective Bayesian Methods for Rule-Based Inference Systems. Proc. of the 1976 AFIPS National Computer Conference 45 (1976). New York: 1976: 1075-1082.
  • 20 Eger H. Servolip – Das Expertensystem zur Fettstoffwechsel-Diagnostik. Extracta Diagnostica 1988; 2: 26-31.
  • 21 Expert-Systems-Ltd: PROLOG-2, Technical Reference Manual. Expert Systems International Ltd; Oxford, England: 1985
  • 22 Fischer M. Eine Wissensbasis zur Unterstützung der serologischen Hepatitisdiagnostik. Doctoral Thesis. Univ. Tübingen.: 1988
  • 23 Gordon J, Shortliffe E. H. The Dempster-Shafer Theory of Evidence. in 1984; 8: 272-292.
  • 24 Gordon J, Shortliffe E. H. A Method for Managing Evidential Reasoning in a Hierarchical Hypothesis Space. Artificial Intelligence 1985; 26: 323-357.
  • 25 Habbema J. D. F, Hilden J, Bjerregaard B. The Measurement of Performance of Probabilistic Diagnosis – I. The Problem, Descriptive Tools, and Measures Based on Classification Matrices. Meth. Inform. Med 1978; 17: 217-226.
  • 26 Habbema J. D. F, Hilden J, Bjerregaard B. The Measurement of Performance of Probabilistic Diagnosis IV. Utility Considerations in Therapeutics and Prognostics. Meth. Inform. Med 1981; 20: 80-96.
  • 27 Habbema J. D. F, Hilden J, Bjerregaard B. The Measurement of Performance of Probabilistic Diagnosis V. General Recommendations. Meth. Inform. Med 1981; 20: 97-100.
  • 28 Hilden J, Habbema J. D. F, Bjerregaard B. The Measurement of Performance of Probabilistic Diagnosis – II.Trustworthiness of the Exact Value of the Diagnostic Probabilities. Meth. Inform. Med 1978; 17: 227-237.
  • 29 Hilden J, Habbema J. D. F, Bjerregaard B. The Measurement of Performance of Probabilistic Diagnosis III. Methods Based on Continuous Functions of the Diagnostic Probabilities. Meth. Inform. Med 1978; 17: 238-246.
  • 30 Iglesias J. R, Kazner E, Aruffo C, Esparza J. A Model of Semiautomatic Type-Specific Diagnosis of Brain Tumors by Computed Tomography: Mathematical Fundaments and Practical Application. Brit. J. Rad 1986; 59: 895-900.
  • 31 Iglesias J. R, Pfannkuch F, Aruffo C, Kazner E, Cervos-Navarro J. Histopathological Diagnosis of Brain Tumors with the Help of a Computer: Mathematical Fundaments and Practical Application. Acta Neuropathologica 1986; 77: 130-135.
  • 32 Ishizuka M. Inference Methods Based on Extended Dempster and Shafer’s Theory for Problems with Uncertainty/Fuzzyness. New Generation Computing 1983; 1: 159-168.
  • 33 Kort C. Erweiterung und Erprobung eines wissensbasierten Systems zur Unterstützung der labormedizinischen Schilddrüsendiagnostik mit besonderer Berücksichtigung der Bereiche Hypothyreose, Schwangerschaft und Altersabhängigkeit. Doctoral Thesis. Univ. Tübingen: 1988
  • 34 Krautter W. Auswertealgorithmen für die labormedizinische Diagnostik unter Verwendung eines PROLOG-Systems. Diplomarbeit. 1986. Univ. Stuttgart:
  • 35 Lindley D. V. Probability and Medical Diagnosis. J. Roy. Coll. Phys 1975; 3: 197-204.
  • 36 Lindley D. V. The Role of Utility in Decision Making. J. Roy. Coll. Phys. Lond. 9 1975; 3: 225-230.
  • 37 Miller P. L. Critiquing Anesthetic Management: The ATTENDING Computer System. Anesthesiology 1983; 58: 362-369.
  • 38 Miller P. L, Black H. R. Medical Plan-Analysis by Computer: Critiquing the Pharmacologic Management of Essential Hypertension. Comput. Biomed. Res 1984; 17: 38-54.
  • 39 Miller P. L, Blumenfrucht S. J, Black H. R. An Expert System which Critiques Patient Workup : Modeling Conflicting Expertise. Comput. Biomed. Res 1984; 17: 554-569.
  • 40 Miller P. L. A Critiquing Approach to Expert Computer Advice: ATTENDING. London: Pitman; 1984
  • 41 Miller P. L. Critiquing: A different approach to expert Computer advice in medicine. Med. Inform 1986; 11: 29-38.
  • 42 Miller R. A, Pople Jr. H. E, Myers J. D. Internist-1, An Experimental Computer-Based Diagnostic Consultant for General Internal Medicine. N. Engl. J. Med 1982; 307: 468-476.
  • 43 Miller R. A, Masarie F. E, Myers J. D. Quick Medical Reference (QMR) for Diagnostic Assistance. M. D. Computing 3 1986; 5: 34-48.
  • 44 Morgan A. G, McAdam W. A. E, Walmsley G. I, Jessop A, Horrocks J. C, de Dombal F. T. Clinical Findings, Early Endoscopy, and Multivariate Analysis in Patients Bleeding from the Upper Gastrointestinal Tract. Brit. Med. J 1977; 2: 237-240.
  • 45 Nii H. P, Aiello N. AGE (Attempt to Generalize): A Knowledge Based Program for Building Knowledge Based Programs. Proc. 6th IJCAI. 1979: 645-655.
  • 46 Pearl J. On Evidential Reasoning in a Hierarchy of Hypotheses. Artificial Intelligence 1986; 28: 9-15.
  • 47 Pohl B, Trendelenburg Chr.. Pro. M. D. – Towards an optimal inference engine including temporal reasoning in medical diagnostics. Proc. 2nd Conference of Artificial Intelligence Europe. Wiesbaden, FRG: 1986
  • 48 Pohl B. Probabilistische Wissensverarbeitung – Anwendung der Wahrscheinlichkeitsrechnung in einem regelbasierten medizinischen Diagnosesystem. Doctoral Thesis. 1988. Univ. Freiburg i.Br.:
  • 49 Pople Jr. H. E, Myers J. D, Miller R. A. DIALOG: A Model of Diagnostic Logic for Internal Medicine. Proc. 4th IJCAI. 1975: 848-855.
  • 50 Pryor T. A, Gardner R. M, Clayton P. D, Warner H. R. The HELP-System. J. Med. Syst 1983; 7: 87-102.
  • 51 Puppe F. Requirements for a Classification Expert System Shell and their Realization in MED2 . Applied Artificial Intelligence 1987; 1: 163-171.
  • 52 Puppe F. Diagnostisches Problemlösen mit Expertensystemen. Informatik-Fachberichte Band 148. Berlin, Heidelberg, New York: Springer; 1987
  • 53 Puppe B, Puppe F. A Knowledge Representation Concept Facilitating Construction and Maintenance of Large Knowledge Bases. Meth. Inform Med 1988; 27: 10-16.
  • 54 Savory S. Künstliche Intelligenz und Expertensysteme. München: Oldenbourg Verlag; 1985. (in German)
  • 55 Schmitt Y, Trendelenburg Chr.. Diagnosis of Hepatitis with the Pro. M. D. Expert System. Proc. 5th International Conference on Computing in Clinical Laboratories, Stuttgart. Brackenheim: Verlag Georg Kohl; 1985: 138-139.
  • 56 Shafer G, Logan R. Implementing Dempster’s Rule for Hierarchical Evidence. Artificial Intelligence 1987; 33: 271-298.
  • 57 Shortliffe E. H. Computer-Based Medical Consultations: MYCIN. New York: Elsevier; 1976
  • 58 Shortliffe E. H. An Expert System for Oncology Protocol Management, in [8]. 1984: 653-665.
  • 59 Trendelenburg Chr., Zeller H, Krautter W, Schmitt Y. Pro. M.D. – An Expert System for Medical Diagnosis Written in PROLOG. Proc. 1st Conference of Artificial Intelligence Europe. 1985. Wiesbaden, FRG:
  • 60 Trendelenburg Chr.. Zum Einsatz sogenannter Expertensystem zur Unterstützung labormedizinischer Diagnostik: Das System Pro. M.D. Labor-Medizin 1986; 9 (05) 284-293.
  • 61 Trendelenburg Chr., Wieland H, Kögler D, Schmitt Y, Krusse-Jarres J. D. Development of a Knowledge Base on Disorders of Lipid Metabolism for the Expert System Pro. M. D. J. Clin. Chem. Clin, Biochem 1986; 24: 814
  • 62 Trendelenburg Chr., Wieland H. Routine Use of a Clinical Chemistry Expert System with a Knowledge Base on Disorders of Lipoprotein Metabolism. Biochem. Clin 1986; 10: 928-929.
  • 63 Trendelenburg Chr., Pohl B. Pro. M.D. – Medizinische Diagnostik mit Expertensystemen: Eine Einführung mit Diskette für die Expertensystemschale Pro. M.D. Stuttgart: Thieme; 1988. (in press)
  • 64 van Melle W, Shortliffe E. H, Buchanan B. G. EMYCIN: A Knowledge Engineers’ Tool for Constructing Rule-Based Expert Systems, in [8]. 1984: 302-313.
  • 65 Warner H. R. Computer-Assisted Medical Decision Making. New York: Academic Press; 1979
  • 66 Weiss S, Kulikowsky C. EXPERT: A System for Developing Consultation Models. Proc. 6th IJCAI. 1979: 942-950.
  • 67 Wichmann H. E, Spechtmeyer H, Gerecke D, Gross R. A Mathematical Model of Erythropoiesis in Man. Lecture Notes in Biomathematics, Vol. 11. Berlin, Heidelberg, New York, Tokyo: Springer; 1976: 157-179.
  • 68 Wieland H. Lipoprotein-Quantifizierung nach elektrophoretischer Trennung: Indikation und Interpretation. Deutsche Ges. Klin. Chemie – Mitt 1985; 2: 48-57.
  • 69 Wieland H, Trendelenburg Chr.. Expert System for the Evaluation of Disturbances of Lipid Metabolism and Assessment of Risk for Coronary Heart Disease. Proc. 3rd International Congress on Automation and New Technology in The Clinical Laboratory, Kobe, Japan, September. 1988: 5-8.
  • 70 Winko S. Aufbau eines wissensbasierten Systems zur Unterstützung der labormedizinischen Schilddrüsendiagnostik mit erweiterungsfähiger Struktur, erstellt für die Bereiche Euthyreose und Hypothyreose. Doctoral Thesis, Univ. Tübingen. 1988
  • 71 Zeller H. Expertensystem zur Unterstützung der Beurteilung klinisch-chemischer Laborbefunde, implementiert in der Logik-Programmiersprache PROLOG. Softwarepraktikum. 1984. Institut für Informatik, Universität Stuttgart:
  • 72 Zadeh L. A. Fuzzy Sets. Information and Control 1965; 8: 338-353.