Key result
Automated acoustic cardiac activity classifier cuts diagnostic errors vs manual evaluation.
Why the study?
Early detection of heartbeat abnormalities is necessary to prevent sudden cardiac death, but recognizing heartbeats is difficult due to noise and frequency tuning challenges for doctors.
Skilled cardiologists follow a series of steps to recognize the heartbeats of a patient. But it is a very difficult task to tune to particular frequencies for a doctor. So, in this manuscript, it is sorted into two series MIT-BIH data set steps for processing the heartbeat of a person without noise from a respiratory system to save a person from false detection of heart diseases. So, we expect our work is useful for researchers, educators, physicians. If the speed of the heart is faster or slower than it is said to be it is called an abnormality. Sudden cardiac death may also be attained due to false detection of a heartbeat. So, the early detection of this heartbeat is necessary to save the life of the patients. So, the algorithm proposed in this paper is useful in removing unnecessary sounds by surroundings and the overall mortality rate due to heart diseases can be reduced.
No takes yet. Share an insight, caveat, or question.
Krishna et al. (2022) studied Cardiac disorders / Arrhythmia. Rectifier Acoustical Cardiac Activity Detection algorithm vs. Manual cardiologists' evaluation / Traditional threshold methods was evaluated on Detection errors (False Positives and False Negatives). The proposed automated rectifier acoustical cardiac activity detection classifier reduced diagnostic errors compared to manual evaluation by cardiologists (1/6 vs 3/6 errors at a 50% threshold).
Synapse has enriched 5 closely related papers on similar clinical questions. Consider them for comparative context: