Methods Inf Med 1974; 13(02): 79-82
DOI: 10.1055/s-0038-1636132
Original Article
Schattauer GmbH

Clinician Versus Computer in the Choice of 11 Differential Diagnoses of Jaundice Based on Formalised Data

Kliniker Versus Computer Bei Der Wahl Von 11 Auf Formalisierte Daten GestÜtzten Differentialdiagnosen Der Gelbsucht
R. B. Stebn
1   (From the Liver Unit, King’s College Hospital and Medical School, London, and the Department of Medicine in Relation to Mathematics and Computing, Glasgoiv)
,
R. P. Knill-Jones
1   (From the Liver Unit, King’s College Hospital and Medical School, London, and the Department of Medicine in Relation to Mathematics and Computing, Glasgoiv)
,
R. Williams
1   (From the Liver Unit, King’s College Hospital and Medical School, London, and the Department of Medicine in Relation to Mathematics and Computing, Glasgoiv)
› Author Affiliations
Further Information

Publication History

Publication Date:
10 February 2018 (online)

The information on 20 jaundiced patients available within 48 hours of their admission to general hospitals in the London area was presented, firstly to a computer-assisted model for the diagnosis of jaundice, and secondly to each of 5 clinicians. When the diagnoses produced by each were compared with the final diagnoses on each patient the computer was correct in 70% of cases and the clinicians in between 45 and 65%. When second and third choices were taken into account the clinicians’ scores rose more than that of the computer. When the clinicians’ choices of diagnosis were compared with those of the computer, irrespective of the accuracy of either, a good correlation with the computer was obtained by 2 clinicians and a poorer one by the other 3. When the items of information most helpful to the clinicians in reaching their diagnoses were compared with those items most helpful to the computer, the correlation between clinician and computer was poor in all cases.

Die klinischen Daten von 20 ikterischen Patienten, die innerhalb 48 Stunden nach Aufnahme an einem der städtischen Spitäler hi London routinemäßig Vorlagen, wurden gleichzeitig einem speziellen Computer-Ikterus-Diagnosemodell und 5 klinisch tätigen Ärzten vorgelegt. Die erstellten Diagnosen stimmten im Falle des Computers in 70%, bei den Ärzten in 45—65% mit den endgültigen Diagnosen überein. Wurden auch die Diagnosenvorschläge der zweiten und dritten Wahl berücksichtigt, dann waren die Ärzte treffsicherer als der Computer. Beim Vergleich der Diagnosenvorschläge der Ärzte mit denen des Computers — ohne Berücksichtigung ihrer Richtigkeit — ergab sich eine gute Korrelation des Computers mit zwei und eine schlechtere mit den übrigen drei Ärzten. Wurden jedoch die klinischen Daten ausgewählt, die den Ärzten beziehungsweise clem Computer zur Diagnoseerstellung am wertvollsten erschienen, dann war die Korrelation zwischen Arzt und Computer in allen Fällen schlecht.

 
  • References

  • 1 Begon F, Dhumeaux D. The application of computer techniques to laboratory diagnosis: diseases of the liver and biliary systems. Minn. Med 54 1971; 101-103.
  • 2 Boyle J. A, Anderson J. A. Computer diagnosis: Clinical aspects. Brit. med. Bull 24 1968; 227-229.
  • 3 Burbank F. A computer diagnostic system for the diagnosis of prolonged, undifferentiated liver disease. Amer. J. Med 46 1969; 401-415.
  • 4 Cattaneo A. D, Luchelli P. E, Rocca E, Mattioli F, Becchi G. Computer versus clinical diagnosis of biliary tract diseases. Abdom. Surg 14 1972; 71-75.
  • 5 de Dombal F. T, Leaper D. J, Staniland J. R, McCann A. P, Horrocjks J. C. Computer-aided diagnosis of abdominal pain. Brit. med. J 1972; II, 9-13.
  • 6 de Dombal F. T, Horrocks J. C, Staniland J. R, Grillon P. J. Pattern recognition. A comparison of the performance of clinicians and nonclinicians. Meth. Inform. Med 11 1972; 32-37.
  • 7 Gustafson J. E. quoted in Bailey, N.T.J., Mathematical Approach to Biology and Medicine. 248 London: Wiley; 1967
  • 8 Leaper D. J, Gill P. W, Staniland J. R, Horrocks J. C, de Dombal F. T. Clinical diagnostic process: an analysis. Brit. med. J 1973; III: 569-573.
  • 9 Martin W. B, Apostalakos P. C, Roazon H. Clinical versus actuarial prediction in the differential diagnosis of jaundice. Amer. J. med. Sci 240 1960; 571-578.
  • 10 Schenker S, Balint J, Schiff L. Differential diagnosis of jaundice. Amer. J. dig. Dis 07 1962; 449-463.
  • 11 Sterling T. D, Nickson J, Pollock S. V. Is medical diagnosis a general computer problem?. J. Amer. med. Ass 19S 1968; 281-286.