How accurate is computer-aided diagnosis?

A computer program for diagnosis of acute abdominal pain (CAD-A) was compared with an amended program (DIAG) and with clinical performance. The programs were tested at three Scottish hospitals, representing a range of practice, in 6962 cases. Accuracy of CAD-A lay in the range 48-59%, and of DIAG 56...

Full description

Saved in:

Bibliographic Details
Published in:	The Lancet (British edition) Vol. 2; no. 8668; p. 905
Main Author:	Sutton, G C
Format:	Journal Article
Language:	English
Published:	England 14.10.1989
Subjects:	Abdomen, Acute - diagnosis Abdomen, Acute - epidemiology Bayes Theorem Clinical Competence - standards Diagnosis, Computer-Assisted - methods Diagnosis, Computer-Assisted - standards Diagnosis, Differential Evaluation Studies as Topic Humans Methods Pain - etiology Predictive Value of Tests Prospective Studies Retrospective Studies Scotland - epidemiology Software Design Scotland
ISSN:	0140-6736
Online Access:	Get more information
Tags:	Add Tag No Tags, Be the first to tag this record!

Description
Summary:	A computer program for diagnosis of acute abdominal pain (CAD-A) was compared with an amended program (DIAG) and with clinical performance. The programs were tested at three Scottish hospitals, representing a range of practice, in 6962 cases. Accuracy of CAD-A lay in the range 48-59%, and of DIAG 56-62%. Clinical accuracy was constant at 65%. These figures suggest that computer systems based on Bayes' formula have no useful role in the diagnosis of acute abdominal pain.
Bibliography:	ObjectType-Article-2 SourceType-Scholarly Journals-1 ObjectType-Feature-1 content type line 23
ISSN:	0140-6736
DOI:	10.1016/S0140-6736(89)91560-2