No abstract

Phonocardiogram (PCG) signals are electrical recording of heart sounds containing vital information of diagnostic importance. Several signal processing methods exist to characterize PCG, however suffers in terms of sensitivity and specificity in accurately discriminating normal and abnormal heart sounds. Recently, a multiscale frequency (MSF) analysis of normal PCG was reported to characterize subtle frequency content changes in PCG which can aid in differentiating normal and abnormal heart sounds. In this work, it was hypothesized that MSF can discriminate normal PCG signal compared to an artifact, PCG with extra systolic heart sounds and murmur based on their varying frequency content. Various samples of PCG with normal and abnormal heart sounds were obtained from Peter Bentley Heart Sounds Database sampled at 44.1 kHz for analysis. The signal was filtered using a 4th order Butterworth lowpass filter with cutoff frequency at 200 Hz to remove higher frequency noise and MSF estimation was performed on the filtered dataset using custom MATLAB software. Mann-Whitney test was performed for statistical significance at p < 0.05. Results indicate that MSF successfully discriminated normal and abnormal heart sounds, which can aid in PCG classification with more sophisticated analysis. Validation of this technique with larger dataset is required.

No abstract

Introduction: Heart failure with preserved ejection fraction (HFpEF) is an increasingly common clinical syndrome with diagnostic challenges and no effective treatment. The high heterogeneity of HFpEF clinical syndrome demands novel technologies to distinguish from heart failure with reduced ejection Fraction (HFrEF). Currently, invasive hemodynamic exercise testing is performed to evaluate for HFpEF with right heart catheterization. Hypothesis: We hypothesize that a deep learning model can noninvasively detect patients with HFpEF using phonocardiogram (PCG). Methods: Eligible patients undergoing right heart catheterization were recruited after IRB approval. Eko duo stethoscope was used to record simultaneous ECG & PCG at the mitral area on the patients prior to right heart catheterization at baseline. Each recording was 30 seconds in length with a frequency range between 250 - 5000 Hz. R-wave peak detection was performed & beat to beat PCG annotations were performed. The annotated PCG signals were converted into Mel-frequency cepstral coefficients (MFCC) and padded to account for the difference in lengths. Deep Learning model was developed using a Sequential Neural Network with 80% data to train and validate the model and 20% hold out data was used for testing accuracy of the model. Receiver operating curve (ROC) was obtained to estimate area under the curve (AUC) for performance analysis. Results: 42 patients were enrolled with 25 patients diagnosed as HFpEF by right heart catheterization and 17 were reported as controls. 2544 & 1771 individual PCG annotations for HFpEF and controls were used for model training/validation and testing. The model performed reasonably well with accuracy of 0.89, F1 score of 0.88, precision of 0.80 and recall of 0.97 on the test data. ROC was obtained with AUC of 0.94. Conclusions: The results demonstrate the ability of the deep learning model to noninvasively detect HFpEF using PCG. Larger study is needed to validate these findings.

No abstract