Predicting Arrhythmic Risk in Heart Attack Patients Using Machine Learning
Author Information
Author(s): Cumitini Luca, Giubertoni Ailia, Rossi Lidia, D'Amario Domenico, Grisafi Leonardo, Abbiati Paola, D'Ascenzo Fabrizio, De Ferrari Gaetano Maria, Patti Giuseppe
Primary Institution: Department of Translational Medicine University of Eastern Piedmont Novara Italy
Hypothesis
Can the PRAISE score effectively predict arrhythmic complications in patients with acute coronary syndrome?
Conclusion
The PRAISE score can accurately identify patients at high risk for arrhythmic events during hospitalization for acute coronary syndrome.
Supporting Evidence
- The PRAISE score showed a significant association with the risk of atrial fibrillation (AF) and ventricular arrhythmias (VA).
- Patients with a high AF PRAISE score had a 19% incidence of in-hospital AF compared to 1% in those with a low score.
- The PRAISE score had a high specificity of 99% for predicting in-hospital AF.
- A high VA PRAISE score was associated with a 2.5-fold increased risk of VA occurring within 48 hours.
Takeaway
Doctors can use a special score called PRAISE to figure out which heart attack patients might have heart rhythm problems while they're in the hospital.
Methodology
This was a prospective observational study that monitored patients with acute coronary syndrome for arrhythmias using continuous electrocardiographic monitoring.
Potential Biases
Potential biases inherent to observational studies may affect the results.
Limitations
The study is observational, which may introduce bias, and the sample size limits the statistical power of the findings.
Participant Demographics
Participants included 365 patients, predominantly men (78%), with a mean age of 67 years.
Statistical Information
P-Value
0.0001
Confidence Interval
95% CI 0.82–0.94
Statistical Significance
p<0.05
Digital Object Identifier (DOI)
Want to read the original?
Access the complete publication on the publisher's website