Automatic Artifact Detection in Impedance Cardiogram Using Pulse Similarity Index.

Area of Science:

• Biomedical Engineering
• Cardiovascular Physiology
• Signal Processing

Background:

• Impedance Cardiography (ICG) is a noninvasive method for assessing cardiac hemodynamics.
• ICG accuracy is compromised by motion artifacts, electrode displacement, and cardiovascular conditions.
• Reliable estimation of cardiac output and pre-ejection period is crucial for clinical applications.

Purpose of the Study:

• To develop and validate an automated algorithm for detecting and excluding corrupted ICG cardiac cycles.
• To improve the accuracy and reliability of hemodynamic parameter measurements from ICG data.
• To address the limitations of ICG sensitivity to artifacts and pathologies.

Main Methods:

• A novel pulse similarity index was developed to quantify ICG cycle corruption.
• The index analyzes ICG cycle features including activity, structure, shape, and pattern.
• The algorithm was validated against expert annotations on sleep study data from 20 participants.

Main Results:

• The artifact rejection algorithm achieved 96% accuracy in detecting corrupted ICG cycles.
• The method successfully identified corrupted cycles with both normal and out-of-range amplitudes.
• The algorithm demonstrated robustness across various artifact types and severity levels.

Conclusions:

• The proposed algorithm effectively detects and excludes corrupted ICG cardiac cycles.
• This automated approach enhances the reliability of noninvasive hemodynamic monitoring.
• The algorithm shows significant potential for applications requiring precise, long-term cardiac monitoring.