• RENJITHA T R
• SURYA KRISHNAN G R
• UTHARA B
• ROOPESH T S
• DEEPA MERIN JOSE

The purpose of this paper is to identify the failure condition of the heart from the heart sounds. The suggested method applies the LSTM(Long Short Term Memory) model for the detection. Through this, the process of detection of heart failure becomes automated. Here a combined form of traditional machine learning and deep learning is used for delivering the abnormality prediction with an accuracy rate of 98%. The recent Physionet dataset is used from which 80% of data is used to train the model and the remaining 20% is used as test data. The input to the model is a recorded PCG(Phonocardiograph) and the output gives either of the two predictions that is normal or abnormal. Sometimes even the expert doctors fails to detect the variations normal working of heart,but the PCG signals do depict the variations. Proposed model can detect the abnormal condition even before the stage in which it becomes clinically evident thereby decreasing the chances of worsening of the disease. So the patient gets timely care and treatments to safeguard his life.

LSTM MODEL FOR THE DETECTION OF CHRONIC HEART FAILURE FROM HEART SOUNDS

"LSTM MODEL FOR THE DETECTION OF CHRONIC HEART FAILURE FROM HEART SOUNDS", International Journal of Emerging Technologies and Innovative Research (www.jetir.org), ISSN:2349-5162, Vol.11, Issue 4, page no.g200-g201, April-2024, Available :http://www.jetir.org/papers/JETIR2404622.pdf

"LSTM MODEL FOR THE DETECTION OF CHRONIC HEART FAILURE FROM HEART SOUNDS", International Journal of Emerging Technologies and Innovative Research (www.jetir.org | UGC and issn Approved), ISSN:2349-5162, Vol.11, Issue 4, page no. ppg200-g201, April-2024, Available at : http://www.jetir.org/papers/JETIR2404622.pdf