PubMed Health⌕ Search
Home/Archive/PubMed

PubMed · 8846709

Developing decision support systems: a change in emphasis.

D L Pitty·P I Reeves
View original source ↗Export metadata ↓

Abstract

Against a backdrop of many demonstrably proficient expert systems that are not routinely used, and a user community that is skeptical of the benefits of using such technology in healthcare, the AIM funded Dilemma project is attempting to introduce decision support technology into shared care environments within scenarios from the specialties of oncology and cardiology. This paper outlines the experiences of one work-package of the Dilemma project which is concerned with the development of applications with a decision support component for use in shared care of coronary artery disease patients. We suggest reasons why expert systems have failed to gain acceptance in the past, and conclude that a shift in emphasis from building expert systems to building clinically useful applications that have an expert system component may improve the chances of acceptance of this technology in the future.

Explore related subjects

Coronary DiseaseDatabases, FactualDecision Making, Computer-AssistedDecision Support Systems, ManagementDecision Support TechniquesHumansMedical Record LinkageMedical Records Systems, ComputerizedSystems IntegrationJournal ArticleResearch Support, Non-U.S. Gov't

Keep this discovery

Explore connections, maps & timelines

BibTeXRIS

D L Pitty, P I Reeves. Developing decision support systems: a change in emphasis.. https://doi.org/10.1016/0169-2607(95)01657-f

Cite the original work for its findings. Save a collection to share your selection of sources.

KEEP EXPLORING

Related citations

PubMed1998

Correct utilization of exercise electrocardiographic leads in differentiation of men with coronary artery disease from patients with a low likelihood of coronary artery disease using peak exercise ST-segment depression.

In this study we compared the diagnostic characteristics of the individual exercise electrocardiographic leads, 3 different lead sets comprising standard leads and the effect of the partition value in the detection of coronary artery disease (CAD). The diagnostic variable used was ST-segment depression at peak exercise, and the study population consisted of 101 patients with CAD and 100 patients with a low likelihood of the disease. The lead system used was the Mason-Likar modification of the standard 12-lead system and exercise tests were performed on a bicycle ergometer. The comparisons were performed by means of receiver-operating characteristic analysis and by determining sensitivities at a fixed 95% specificity. These properties, defined here as diagnostic capacity, were the most efficacious in leads I, -aVR, V4, V5, and V6. Diagnostic capacities in leads aVL, aVF, III, V1, and V2 were quite poor; statistical comparisons indicated significant differences between these leads and lead V5 (p < or = 0.0001 in each case). Use of the maximum value of ST-segment depression at peak exercise derived from all 12 leads produced a considerable decrease in the diagnostic capacity of the exercise electrocardiogram compared with lead V5. The exclusion of leads aVL, V1, and III improved the diagnostic capacity compared with the 12-lead set, but it was still smaller than that of lead V5. With use of a lead set with the 5 best leads increased the diagnostic capacity over other lead sets and over any individual lead. Further improvement was noted when a 50% smaller partition value was applied to leads I and -aVR than for the other leads (p = 0.041). In conclusion, this study suggests that use of leads I, -aVR, V4, V5, and V6 is the most influential when differentiating between patients with CAD and patients with a low likelihood of disease using peak exercise ST-segment depression. The effective use of leads I and -aVR requires the partition value applied for these leads to be 50% smaller than that used for the lateral precordial leads.

Coronary Disease↗