Physicians' Diagnoses Compared with Aiaorithmic Differentiation of Causes of Jaundice

Abstract

Clinical data were collected in 194 cases of jaundiced patients treated at the "Adolfo Lopez Mateos" ISSSTE Hospital in Mexico City from July 1985 to July 1986. A copy of the clinical history of each patient was given to each of four physicians--one recently graduated from medical school, another in his first year of gastroenterology, and two others who were experienced gastroenterologists. The same clinical data were processed by a computer set up to use a modified Danish COMIC algorithm. All physicians and the computer technician were blinded to the "gold standard" pathologic diagnoses, with which their diagnoses were compared. Accuracy rates of the physicians in distinguishing intrahepatic (medical) from extrahepatic (surgical) jaundice were 78%, 86%, 86%, and 91%, and the accuracy of computer-assisted diagnoses was 96%. Chi-squared analysis of the diagnoses of three of the physicians and those of the computer showed significant differences (p between 0.1 and 0.01). For the diagnoses of the remaining physician, however, no significant difference was found after chi-squared continuity correction.

What People Want From Their Professionals: Attitudes Toward Decision‐making Strategies

“…In the first comprehensive review of this research, Meehl () found that actuarial methods equalled or outperformed clinical methods in all 20 instances. His review ignited extensive research comparing the two methods across a range of domains (e.g., Boom et al, ; Dunnette, Kirchner, Erickson, & Banas, ; Goldberg, ). Subsequently, a meta‐analysis by Grove et al () of 136 studies found that 47% favored actuarial predictions, 48% yielded equal performance, and only 6% favored clinical predictions.…”

Computer-Aided Decision Support in Hepatology

“…This Danish team used two other methods in the same population with the same data: a logistic discrimination model (24) and a decision tree (23). The logistic discrimination model with minor changes was proved robust in Sweden (19) and in Mexico (12); it was superior t o clinicians in Mexico (13) but not in Denmark (22). The three methods have been compared: the Bayes rule is the most accurate biologic data for the diagnosis of 11 possible causes of jaundice in 309 subjects.…”