PDF herunterladen
Methods Inf Med 1994; 33(02): 205-213
DOI: 10.1055/s-0038-1635005
Original Article
Schattauer GmbH

Case-Based Explanation for Medical Diagnostic Programs, with an Example from Gynaecology

R. Stamper
1   The Programming Research Group, Oxford University Computing Laboratory, Oxford, UK
,
B. S. Todd
1   The Programming Research Group, Oxford University Computing Laboratory, Oxford, UK
,
P. Macpherson
2   The Nuffield Department of Obstetrics and Gynaecology, John Radcliffe Hospital, Oxford, UK
› Institutsangaben
We are grateful to Tony Hoare for providing valuable suggestions and advice. We would like to thank the Consultants in the Nuffield Department of Obstetrics and Gynaecology, John Rad-cliffe Hospital, Oxford, for permission to collect and use clinical data from patients under their care. Richard Stamper is supported by a SERC Research grant (SERC GR/F47077). Bryan Todd is supported by a SERC Advanced Fellowship in Information Technology (SERC B/ITF/269).
Weitere Informationen

Publikationsverlauf

Publikationsdatum:
08. Februar 2018 (online)

   Lizenzen und Reprints

Abstract:

One of the most accountable methods of providing machine assistance in medical diagnosis is to retrieve and display similar previously diagnosed cases from a database. In practice, however, classifying cases according to the diagnoses of their nearest neighbours is often significantly less accurate than other statistical classifiers. In this paper the transparency of the nearest neighbours method is combined with the accuracy of another statistical method. This is achieved by using the other statistical method to define a measure of similarity between the presentations of two cases. The diagnosis of abdominal pain of suspected gynaecological origin is used as a case study to evaluate this method. Bayes’ theorem, with the usual assumption of conditional independence, is used to define a metric on cases. This new metric was found to correspond as well as Hamming distance to the clinical notion of “similarity” between cases, while significantly increasing accuracy to that of the Bayes’ method itself.

Keywords

Computer-Aided Diagnosis - Nearest Neighbours - Database Retrieval - Abdominal Pain - Explanations
 

  • REFERENCES

  • 1 Seroussi B, The ARC. AURC Cooperative Group. Computer-aided diagnosis of acute abdominal pain when taking into account interactions. Meth Inform Med 1986; 25: 194-8.
    PubMedSuche in Google Scholar
  • 2 Sutton GC. How accurate is computer-aided diagnosis?. Lancet 1989; ii: 905-8.
    PubMedSuche in Google Scholar
  • 3 Gunn AA. The acute abdomen: the role of computer-assisted diagnosis. Baillieres Clin Gastroenterol 1991; 05: 639-65.
    CrossrefPubMedSuche in Google Scholar
  • 4 De Dombal FT, Leaper DJ, Staniland JR, McCann AP, Horrocks JC. Computer-aided diagnosis of acute abdominal pain. BMJ 1972; ii: 9-13.
    PubMedSuche in Google Scholar
  • 5 Adams ID, Chan M, Clifford PC. et al. Computer-aided diagnosis of acute abdominal pain: a multicentre study. BMJ 1986; 293: 80O-4.
    PubMedSuche in Google Scholar
  • 6 Lachenbruch PA, Mickey MR. Estimation of error rates in discriminant analysis. Tech-nomet 1968; 10: 1-11.
    CrossrefPubMedSuche in Google Scholar
  • 7 Glick N. Additive estimators for probabilities of correct classification. Pattern Recogn 1978; 10: 211-22.
    CrossrefPubMedSuche in Google Scholar
  • 8 Macartney FJ. Diagnostic logic. BMJ 1987; 295: 1325-31.
    CrossrefPubMedSuche in Google Scholar
  • 9 Teach R, Shqrtliffe E. An analysis of physician attitudes regarding computer-based clinical consultation systems. Comput Biomed Res 1981; 14: 542-58.
    CrossrefPubMedSuche in Google Scholar
  • 10 Young D, Chapman T, Poile C. Physician, reveal thyself. Br J Healthcare Comput 1990; 07: 16-21.
    PubMedSuche in Google Scholar
  • 11 Weyl S, Fries J, Wiederhold G, Germano F. A modular selfdescribing clinical database system. Comput Biomed Res 1975; 08: 279-93.
    CrossrefPubMedSuche in Google Scholar
  • 12 Fries JF, McShane DJ. ARAMIS (The American Rheumatism Association Medical Information System) - a prototypical national chronic-disease data bank. West J Med 1986; 145: 798-804.
    PubMedSuche in Google Scholar
  • 13 Cover TM, Hart PE. Nearest neighbour pattern classification. IEEE Trans Inf Theory 1967; 13: 21-7.
    CrossrefPubMedSuche in Google Scholar
  • 14 Stanfill C, Waltz D. Toward memory-based reasoning. Comm ACM 1986; 29: 1213-28.
    CrossrefPubMedSuche in Google Scholar
  • 15 Singer J, Sacks HS, Lucente F, Chalmers TC. Physician attitudes toward applications of computer data base systems. JAMA 1983; 249: 1610-4.
    CrossrefPubMedSuche in Google Scholar
  • 16 Loftsgaarden DO, Quesenberry CP. A non-parametric estimate of a multivariate density function. Ann Math Statist 1965; 36: 1049-51.
    CrossrefPubMedSuche in Google Scholar
  • 17 Stone CJ. Consistent nonparametric regression. Ann Statist 1977; 05: 596-645.
    PubMedSuche in Google Scholar
  • 18 Bounds DG, Lloyd PJ, Mathew BG. A comparison of neural network and other pattern recognition approaches to the di-agnosis of low back pain. Neural Networks 1990; 03: 583-91.
    CrossrefPubMedSuche in Google Scholar
  • 19 Sutton GC. Computer-aided diagnosis: a review. Br J Surg 1989; 76: 82-5.
    CrossrefPubMedSuche in Google Scholar
  • 20 Séroussi B. The ARC & AURC Cooperative Group. Comparison of several discrimination methods: Application to the acute abdomen. In: Objecti e Medical Section Making: Systems Approach in Disease Workshop. Berlin: Springer-Verlag. Lecture Notes in Medical Informatics; 1985. 28: 12-18.
    Suche in Google Scholar
  • 21 Croft DJ. Is computerized diagnosis possible?. Comput Biomed Res 1972; 05: 351-67.
    CrossrefPubMedSuche in Google Scholar
  • 22 Fukunaga K. Introduction to Statistical Pattern Recognition. (2nd ed).. Boston: Academic Press; 1990
    Suche in Google Scholar
  • 23 Fenyo G. Computer-aided diagnosis and decision-making in acute abdominal pain. Dig Dis 1990; 08: 639-65.
    PubMedSuche in Google Scholar
  • 24 Fox J, Barber D, Bardhan KD. A quantitative comparison with rule-based diagnostic inference. Meth Inform Med 1980; 19: 210-5.
    PubMedSuche in Google Scholar
  • 25 Titterington DM, Murray GD, Murray LS. et al. Comparison of discrimination tech-ni-ques applied to a complex data set of head-injured patients. J Roy Statist Soc Ser A 1981; 144: 145-75.
    CrossrefPubMedSuche in Google Scholar
  • 26 Ludwig D, Heilbronn D. The design and testing of a new approach to computer aided differential diagnosis. Meth Inf Med 1983; 22: 156-66.
    PubMedSuche in Google Scholar
  • 27 Kononenko I. Comparison of inductive and naive bayesian learning approaches to automatic knowledge acquisition. In: Fox J, Fieschi M, Engelbrecht R. eds. AIME 87. European Conference on Artificial Intelligence in Medicine. Berlin: Springer Verlag. Lecture Notes in Medical Informatics; 1987. 33 190-7.
    Suche in Google Scholar
  • 28 Spiegelhalter DJ, Knill-Jones RP. Statistical and knowledge-based approaches to clinical decision-support systems, with an application in gastroenterology. J Roy Statist Soc Ser A 1984; 147: 35-77.
    CrossrefPubMedSuche in Google Scholar
  • 29 Seymour DG, Green M, Vaz FG. Making better decisions: Construction of clinical scoring systems by the Spiegelhalter-Knill-Jo-nes approach. BMJ 1990; 300: 223-6.
    CrossrefPubMedSuche in Google Scholar
  • 30 Reggia JA, Perricone BT. Answer justification in medical decision support systems based on bayesian classification. Comput Biol Med 1985; 15: 161-7.
    CrossrefPubMedSuche in Google Scholar
  • 31 De Dombal FT. Clinical decision making and the computer: Consultant, expert, or just another test?. Br J Healthcare Comput 1984; 01: 7-14.
    PubMedSuche in Google Scholar
  • 32 Quinlan JR. Discovering rules by induction from large collections of examples. In: Michie D. eds Expert Systems in the Microelectronic Age. Edinburgh: Edinburgh University Press; 1979
    Suche in Google Scholar
  • 33 Cestnik B, Kononenko I, Bratko I. ASSISTANT 86: A knowledge elicitation tool for sophisticated users. In: Bratko I, Lavrac N. eds. Progress in Machine Learning: Proceedings of EWSL 87: 2nd European Working Session on Learning. Wilmslow: Sigma; 1987: 31-15.
    Suche in Google Scholar
  • 34 Gammerman A, Thatcher AR. Bayesian diagnostic probabilities without assuming independence of symptoms. Meth Inform Med 1991; 30: 15-22.
    PubMedSuche in Google Scholar
  • 35 Pirnat V, Kononenko I, Jane T, Bratko I. Medical estimation of automatically induced decision rules. In: Hunter J, Cookson J, Wyatt J. eds. AIME 89: Second European Conference on Artificial Intelligence in Medicine. Berlin: Springer-Verlag. Lecture Notes in Medical Informatics; 1989. 38 24-36.
    Suche in Google Scholar