Intelligent use of advanced capabilities of diagnostic ECG algorithms in a monitoring environment

Area of Science:

• Cardiology
• Biomedical Engineering
• Medical Signal Processing

Background:

• Cardiac monitoring systems generate numerous ST-elevation notifications, but many are not critical ST-segment elevation myocardial infarction (STEMI).
• Conditions like acute pericarditis and benign early repolarization mimic STEMI, leading to non-actionable alerts.
• Existing diagnostic ECG algorithms struggle with noisy data common in monitoring environments.

Purpose of the Study:

• To develop a STEMI screening algorithm that accurately identifies critical ST-segment elevation myocardial infarction (STEMI) events.
• To reduce non-actionable ST-elevation notifications by filtering out confounding conditions.
• To enhance the reliability of real-time cardiac monitoring alerts.

Main Methods:

• Developed a multi-stage STEMI screening algorithm incorporating real-time ECG signal quality evaluation.
• The algorithm selects high-quality ECG segments for analysis by a diagnostic ECG algorithm.
• Utilized variation analysis of ST segments to differentiate STEMI from confounders.

Main Results:

• The developed STEMI screening algorithm significantly reduces the number of ST-elevation notifications compared to continuous monitoring.
• Improved signal quality selection enhances the accuracy of diagnostic ECG algorithm analysis in noisy environments.
• Effectively filters out non-actionable notifications caused by conditions mimicking STEMI.

Conclusions:

• A multi-stage STEMI screening algorithm with real-time signal quality evaluation enhances the specificity of cardiac monitoring alerts.
• This approach effectively reduces false positives, allowing clinicians to focus on critical STEMI events.
• The algorithm shows promise for improving the efficiency and reliability of real-time cardiac monitoring systems.