Synapse
⌘+K
Synapse
PulseExploreClubsResearchersJournals
Instagram
HomeClubsExplore
January 1, 1996The LancetOpen Access

Artificial neural network outperforms ED physicians by achieving 96% sensitivity for acute MI.

View Full Paper
Ask AI
Bookmark
Share

Why the study?

Does an artificial neural network improve diagnostic accuracy for acute myocardial infarction compared to emergency department physicians in patients presenting with anterior chest pain?

Population

1070 patients 18 years or older presenting to the emergency department of a teaching hospital in California…

Comparison

Artificial neural network diagnosis based on… vs Emergency department physicians' clinical…

Design

Cohort

Key result

An artificial neural network achieved a diagnostic sensitivity of 96.0% and specificity of 96.0% for acute myocardial infarction, compared to 73.3% and 81.1% for emergency department physicians.

Authors

WBWilliam G. BaxtJSJan Skóra

Discussion

Loading...

Member takes

Overview

May support AI-assisted AMI diagnosis; leaves open prospective validation before clinical adoption.

Study Design

Type

Observational (n=1,070)

Multicenter

No

Structured PICO

Does an artificial neural network improve diagnostic accuracy for acute myocardial infarction compared to emergency department physicians in patients presenting with anterior chest pain?

P
Population
1,070 patients aged 18 years or older presenting to an emergency department with anterior chest pain and suspected acute myocardial infarction.
E
Exposure
Artificial neural network diagnosis based on patient data collected by physicians during their evaluations.
C
Comparator
Emergency department physicians' clinical diagnosis.
O
Outcome
Diagnostic sensitivity and specificity for acute myocardial infarction.

Main Result

Absolute Event Rate: 96% vs 73.3%

An artificial neural network demonstrated significantly higher sensitivity and specificity for diagnosing acute myocardial infarction compared to emergency department physicians in patients presenting with anterior chest pain.

Cite This Study

Baxt et al. (1996) conducted an observational in Acute myocardial infarction (n=1,070). Artificial neural network vs. Emergency department physicians was evaluated on Diagnostic sensitivity for myocardial infarction. An artificial neural network achieved a diagnostic sensitivity of 96.0% and specificity of 96.0% for acute myocardial infarction, compared to 73.3% and 81.1% for emergency department physicians.

synapsesocial.com/papers/6aa6fe75cd36d0f46f00a2a9https://doi.org/10.1016/s0140-6736(96)91555-x
View Full Paper
Ask AI
Bookmark
Share

Also Consider

Synapse has enriched 5 closely related papers on similar clinical questions. Consider them for comparative context:

  1. 1Use of an Artificial Neural Network for the Diagnosis of Myocardial Infarction1991 · 479 citations
  2. 2Use of an Artificial Neural Network for Data Analysis in Clinical Decision-Making: The Diagnosis of Acute Coronary Occlusion1990 · 294 citations
  3. 3A Computer Protocol to Predict Myocardial Infarction in Emergency Department Patients with Chest Pain1988 · 660 citations
  4. 4Use of a Rapid Assay of Subforms of Creatine Kinase MB to Diagnose or Rule Out Acute Myocardial Infarction1994 · 330 citations
  5. 5Candidates for Thrombolysis among Emergency Room Patients with Acute Chest Pain1989 · 163 citations