Methods
A total of 13949 clinical data of arrhythmia were collected from 13145 patients who were treated with artificial intelligence ECG network in our hospital. Computer analysis was performed using Lepu artificial intelligence ECG network system to obtain the analysis results of artificial intelligence algorithm. Taking the diagnostic results of the physician team as the gold standard, the sensitivity, specificity, positive prediction rate, and negative prediction accuracy rate in the screening test were used to assess the effectiveness of the artificial intelligence ECG algorithm compared with the gold standard.
Results
Seventeen types of arrhythmia events including sinus arrhythmia and atrial fibrillation were diagnosed by ECG algorithm based on artificial intelligence. The comprehensive sensitivity, specificity and accuracy of these 17 types of arrhythmia events were 98.08%, 99.84% and 99.84%, respectively. Among them, the consistency Kappa coefficients of 6 types of arrhythmias (pairing of supraventricular contractions, atrial escape and ventricular escape, etc.) were greater than 0.4 but less than 0. 75, which meet the consistency requirements but without strong consistency.
Conclusion
The test results of artificial intelligence -based ECG algorithm for arrhythmia is highly consistent with the clinical ECG test results. The artificial intelligence-based ECG algorithm has good clinical practice prospects.
For more information, please visit: https://en.lepumedical.com/products/ai-view/
Email Us: