Related Experiment Videos
Discrimination of ischemia and normal sinus rhythm for cardiac signals using a modified k means clustering algorithm
Maneesh Shrivastav1, Paul Iaizzo
1Medtronic Cardiac Rhythm Management, Minneapolis, MN, USA. maneesh@ieee.org
Insights
This study introduces mathematical methods to analyze heart signals, effectively distinguishing between normal and ischemic heartbeats. These techniques offer potential for improved diagnosis and treatment of myocardial ischemia.
Area of Science:
- Biomedical Engineering
- Cardiology
- Computational Biology
Background:
- Coronary heart disease affects over 15 million Americans, with significant economic and social impacts.
- Myocardial infarction (MI) affects approximately 8 million Americans.
- Effective diagnosis and treatment of myocardial ischemia are crucial for patient outcomes.
Purpose of the Study:
- To develop and evaluate mathematical techniques for extracting key features from action potential signals.
- To differentiate between signals from ischemic and normal heart regions.
- To assess the clinical significance for diagnosing or treating myocardial ischemia.
Main Methods:
- Acquired action potential signals from swine models with localized ischemia.
- Utilized transmural electrodes for signal acquisition.
- Applied a modified means clustering technique on paired data for feature evaluation in multidimensional space.
Main Results:
- Identified promising features for clustering and separation of ischemic and normal heartbeats.
- Demonstrated efficacy using frequency domain computations, morphology analyses, and isoelectric point evaluations.
- Validated findings through a cross-validation approach.
Conclusions:
- Mathematical feature extraction from action potential signals shows potential for distinguishing ischemic from normal heart tissue.
- The developed methods may aid in the efficacious diagnosis or treatment of myocardial ischemia.
- Further research could integrate these techniques into clinical practice.
Abstract:
Over 15 million Americans are affected by coronary heart disease, according to the American Heart Association. Approximately 8 million have suffered a myocardial infarction. The economic and social consequences of this disease are staggering. A plethora of experimental and established therapies exist for this disease, such as stem cell therapy, growth factor injection, engineered cell transfection, etc. The use of these techniques relies on targeted therapeutic delivery. This paper describes mathematical techniques to extract key features from acquired action potential signals from ischemic and normal regions of the same heart. Using a modified means clustering technique on paired data, the best features are evaluated in multidimensional space. The results indicate promising clustering and separation of ischemic and normal beats using frequency domain computations, morphology analyses, and isoelectric point evaluations. Features were tested with data collected from a swine model of localized ischemia implanted with transmural electrodes and evaluated with a cross-validation approach. This research may have clinical significance to aid in the efficacious diagnosis or treatment of myocardial ischemia.
