@article{article_741785, title={Real Tıme Detection of S1 and S2 Heart Sounds}, journal={Journal of Cukurova Anesthesia and Surgical Sciences}, volume={3}, pages={62–68}, year={2020}, author={Turgay Yıldırım, Özge and Turgay, Ayşegül}, keywords={kardiyak oskültasyon, , kalp sesi segmentasyonu, fonokardiyogram, S1 S2 algılama, zarf, gerçek zamanlı algılama}, abstract={Introduction
Automatic detection of S1 and S2 heart sounds is critical for diagnostic decision support systems that use heart sound as a means for decision making. There were previously suggested methods in the literature but offline nature of these analysis is impractical since the output is needed during the auscultation not later. The aim of this study was to provide an algorithm for real-time detection of S1 and S2.
Materials and Methods
A total of 25 patients were included for the study. Group 1 consisted of healthy individuals. Group 2 consists of patients with systolic murmurs, diastolic murmurs, physiological or paradoxical splitting. Group 3 consisted of pathological atrial and ventricular gallops. The suggested method first filtered the audio data then an envelope is constructed from the signal energy. The standard deviation of the envelope is employed as a threshold value for peak detection. Consecutive three peak values are utilized to estimate current and future locations of S1 and S2 and heart rate. These future estimates are used to optimize misinterpretations in S1 and S2 locations of the next heart cycle. Results
Group 1 included 24% of the study group; Group 2 included 64% and Group 3 included 12% of the patients. The detection rate was 92%, 75% and 46% for Group 1, Group 2 and Group 3 patients, respectively. The overall success rate for all study population was 75%. Conclusion
In this study, the feasibility of real time detection of S1 and S2 is shown. The method achieved 75 % success rate in Group 2 patients, although S1 and S2 sounds were barely visible in most of the cases. The fall in success rate in Group 3 patients is consistent with the findings in literature, since S3 and S4 are usually misinterpreted as S1 and S2 in severe gallop cases.}, number={2}, publisher={Merthan TUNAY}