Myocardial Infarction Prediction

Myocardial Infarction Clinical Trial

Official title:

Prediction of Acute Myocardial Infarction With Artificial Neural Networks in Patients With Nondiagnostic Electrocardiogram

Clinical Trial Details — Status: Completed

Administrative data

• NCT number: NCT01870258
• Other study ID #: 90-8037
• Status: Completed
• Phase: N/A
• First received: May 24, 2013
• Last updated: June 4, 2013
• Start date: January 2011
• Est. completion date: June 2012

Study information

• Verified date: June 2013
• Source: Shiraz University of Medical Sciences
• Contact: n/a
• Is FDA regulated: No
• Health authority: Iran: national institiute of health
• Study type: Interventional

Clinical Trial Summary

prediction of MI in patients with chest pain and nondiagnostic ECG was done in 2 weeks

Description:

Myocardial infarction remains one the leading causes of mortality and morbidity and involves a high cost of care. Early prediction can be helpful in preventing the development of myocardial infarction with appropriate diagnosis and treatment. Artificial neural networks have opened new horizons in learning about the natural history of diseases and predicting cardiac disease.

Methods: A total of 935 cardiac patients with chest pain and nondiagnostic electrocardiogram (ECG) were enrolled and followed for 2 weeks in two groups based on the appearance of myocardial infarction. Two types of data were used for all patients: nominal (clinical data) and quantitative (ECG findings). Two different artificial neural networks - radial basis function (RBF) and multi-layer perceptron (MLP) - were used.

Recruitment information / eligibility

• Status: Completed
• Enrollment: 1100
• Est. completion date: June 2012
• Est. primary completion date: April 2012
• Accepts healthy volunteers: No
• Gender: Both
• Age group: 40 Years to 72 Years

Eligibility

Inclusion Criteria:

• patient with chest pain refered to ER with nondiagnostic ECG

Exclusion Criteria:

• 1) Absence of a history of myocardial infarction

• 2) Absence of bundle branch block, Wolf-Parkinson-White abnormality, ventricular hypertrophy or previous ECG signs of myocardial infarction,

• 3) Absence of a history of percutaneous coronary surgery or coronary artery bypass grafting,

• 4) Absence of ECG abnormalities attributable to drugs such as digoxin or tricyclic antidepressants.

Study Design

Allocation: Non-Randomized, Endpoint Classification: Safety/Efficacy Study, Intervention Model: Parallel Assignment, Masking: Double Blind (Subject, Caregiver, Investigator, Outcomes Assessor), Primary Purpose: Diagnostic

Related Conditions & MeSH terms

• Artificial Neural Network
• Infarction
• Myocardial Infarction

Intervention

Other:
• ANN prediction of myocardial infarction

Locations

Country	Name	City	State
n/a

Sponsors (1)

Lead Sponsor	Collaborator
Shiraz University of Medical Sciences

Outcome

Type	Measure	Description	Time frame	Safety issue
Primary	myocardial infarction		2 weeks	Yes
Secondary	hospital admission due to cardiac events	may be includes unstable angina, cardiac arrest or PCIor CABG	2 weeks	Yes