Synapse
⌘+K
Synapse
PulseExploreClubsResearchersJournals
Instagram
HomeClubsExplore
March 31, 1988New England Journal of Medicine

The computer protocol had a significantly higher specificity (74% vs. 71%) in predicting the absence of infarction and a similar sensitivity (88.0% vs. 87.8%) in detecting the presence of infarction compared to physicians.

View Full Paper
Ask AI
Bookmark
Share

Why the study?

Does a computer protocol improve the prediction of myocardial infarction compared to unaided physician judgment in emergency department patients with chest pain?

Population

4,770 emergency department patients presenting with acute chest pain in a prospective validation cohort…

Comparison

A computer protocol to predict the presence of… vs Unaided physician clinical judgment regarding…

Design

Cohort

Authors

LGLee GoldmanECE. Francis CookDBDonald A. Brand

Discussion

Loading...

Member takes

Overview

Computer protocol may aid ruling out infarction in ED chest pain; hypothesis-generating and requires prospective validation before practice change.

Key Points

  • To develop and prospectively validate a computer protocol designed to predict myocardial infarction and optimize coronary care unit triage for patients presenting to the emergency department with acute chest pain.
  • Constructed a predictive computer protocol using clinical data collected from 1,379 emergency chest pain patients across two hospitals.
  • Prospectively evaluated the protocol across 4,770 patients treated at two university hospitals and four community hospitals, comparing its triage accuracy with decisions made by clinical physicians.
  • The computer protocol achieved significantly higher specificity than physicians in predicting the absence of infarction (74% vs. 71%) alongside equivalent sensitivity (88.0% vs. 87.8%).
  • Relying on the computer protocol for triage decisions would have decreased coronary care unit admissions among patients without myocardial infarction by 11.5% without compromising the care of individuals who developed emergent complications.

Structured PICO

Does a computer protocol improve the prediction of myocardial infarction compared to unaided physician judgment in emergency department patients with chest pain?

P
Population
4,770 emergency department patients presenting with acute chest pain in a prospective validation cohort across two university hospitals and four community hospitals (following a derivation cohort of 1,379 patients).
I
Intervention
A computer protocol to predict the presence of myocardial infarction.
C
Comparator
Unaided physician clinical judgment regarding whether to admit patients to the coronary care unit.
O
Outcome
Sensitivity and specificity in predicting the presence or absence of myocardial infarction.

A computer-derived protocol can predict myocardial infarction with higher specificity and similar sensitivity compared to unaided physician judgment, potentially reducing unnecessary coronary care unit admissions.

Limitations

  • Whether physicians who are aided by the protocol perform better than unaided physicians cannot be determined without further study

Cite This Study

Goldman et al. (1988) studied this question.

synapsesocial.com/papers/6a7d010a2935e92dbc7750f5https://doi.org/10.1056/nejm198803313181301
View Full Paper
Ask AI
Bookmark
Share