Investigating the effects of vasodilator drugs on the turbulent sound caused by femoral artery stenosis using short-term Fourier and wavelet transform methods

Feasibility of Deep Learning-Based Analysis of Auscultation for Screening Significant Stenosis of Native Arteriovenous Fistula for Hemodialysis Requiring Angioplasty

OBJECTIVE

To investigate the feasibility of using a deep learning-based analysis of auscultation data to predict significant stenosis of arteriovenous fistulas (AVF) in patients undergoing hemodialysis requiring percutaneous transluminal angioplasty (PTA).

MATERIALS AND METHODS

Forty patients (24 male and 16 female; median age, 62.5 years) with dysfunctional native AVF were prospectively recruited. Digital sounds from the AVF shunt were recorded using a wireless electronic stethoscope before (pre-PTA) and after PTA (post-PTA), and the audio files were subsequently converted to mel spectrograms, which were used to construct various deep convolutional neural network (DCNN) models (DenseNet201, EfficientNetB5, and ResNet50). The performance of these models for diagnosing ≥ 50% AVF stenosis was assessed and compared. The ground truth for the presence of ≥ 50% AVF stenosis was obtained using digital subtraction angiography. Gradient-weighted class activation mapping (Grad-CAM) was used to produce visual explanations for DCNN model decisions.

RESULTS

Eighty audio files were obtained from the 40 recruited patients and pooled for the study. Mel spectrograms of "pre-PTA" shunt sounds showed patterns corresponding to abnormal high-pitched bruits with systolic accentuation observed in patients with stenotic AVF. The ResNet50 and EfficientNetB5 models yielded an area under the receiver operating characteristic curve of 0.99 and 0.98, respectively, at optimized epochs for predicting ≥ 50% AVF stenosis. However, Grad-CAM heatmaps revealed that only ResNet50 highlighted areas relevant to AVF stenosis in the mel spectrogram.

CONCLUSION

Mel spectrogram-based DCNN models, particularly ResNet50, successfully predicted the presence of significant AVF stenosis requiring PTA in this feasibility study and may potentially be used in AVF surveillance.

Coronary artery disease risk reclassification by a new acoustic-based score

To determine the potential of a non-invasive acoustic device (CADScor®System) to reclassify patients with intermediate pre-test probability (PTP) and clinically suspected stable coronary artery disease (CAD) into a low probability group thereby ruling out significant CAD. Audio recordings and clinical data from three studies were collected in a single database. In all studies, patients with a coronary CT angiography indicating CAD were referred to coronary angiography. Audio recordings of heart sounds were processed to construct a CAD-score. PTP was calculated using the updated Diamond-Forrester score and patients were classified according to the current ESC guidelines for stable CAD: low < 15%, intermediate 15–85% and high > 85% PTP. Intermediate PTP patients were re-classified to low probability if the CAD-score was ≤ 20. Of 2245 patients, 212 (9.4%) had significant CAD confirmed by coronary angiography ( ≥ 50% diameter stenosis). The average CAD-score was higher in patients with significant CAD (38.4 ± 13.9) compared to the remaining patients (25.1 ± 13.8; p < 0.001). The reclassification increased the proportion of low PTP patients from 13.6% to 41.8%, reducing the proportion of intermediate PTP patients from 83.4% to 55.2%. Before reclassification 7 (3.1%) low PTP patients had CAD, whereas post-reclassification this number increased to 28 (4.0%) (p = 0.52). The net reclassification index was 0.209. Utilization of a low-cost acoustic device in patients with intermediate PTP could potentially reduce the number of patients referred for further testing, without a significant increase in the false negative rate, and thus improve the cost-effectiveness for patients with suspected stable CAD.

Classification of healthy and abnormal swallows based on accelerometry and nasal airflow signals

BACKGROUND

Dysphagia assessment involves diagnosis of individual swallows in terms of the depth of airway invasion and degree of bolus clearance. The videofluoroscopic swallowing study is the current gold standard for dysphagia assessment but is time-consuming and costly. An ideal alternative would be an automated abnormal swallow detection methodology based on non-invasive signals.

OBJECTIVE

Building upon promising results from single-axis cervical accelerometry, the objective of this study was to investigate the combination of dual-axis accelerometry and nasal airflow for classification of healthy and abnormal swallows in a patient population with dysphagia.

METHODS

Signals were acquired from 24 adult patients with dysphagia (17.8±8.8 swallows per patient). The abnormality of each swallow was quantified using 4-point videofluoroscopic rating scales for its depth of airway invasion, bolus clearance from the valleculae, and bolus clearance from the pyriform sinuses. For each scale, we endeavored to automatically discriminate between the 2 extreme ratings, yielding 3 separate binary classification problems. Various time, frequency, and time-frequency domain features were extracted. A genetic algorithm was deployed for feature selection. Smoothed bootstrapping was utilized to balance the two classes and provide sufficient training data for a multidimensional feature space.

RESULTS

A Euclidean linear discriminant classifier resulted in a mean adjusted accuracy of 74.7% for the depth of airway invasion rating, whereas Mahalanobis linear discriminant classifiers yielded mean adjusted accuracies of 83.7% and 84.2% for bolus clearance from the valleculae and pyriform sinuses, respectively. The bolus clearance from the valleculae problem required the lowest feature space dimensionality. Wavelet features were found to be most discriminatory.

CONCLUSIONS

This exploratory study confirms that dual-axis accelerometry and nasal airflow signals can be used to discriminate healthy and abnormal swallows from patients with dysphagia. The fact that features from all signal channels contributed discriminatory information suggests that multi-sensor fusion is promising in abnormal swallow detection.

Quantitative analysis of heart sounds and systolic heart murmurs using wavelet transform and AR modeling

A quantitative approach integrating AR modeling and wavelet transform is presented in this paper to analyze the digitized phonocardiogram. The recognition of the first and the second heart sounds (S(1) and S(2)) were facilitated with wavelet transform without referring to the QRS waveform. We found that the Daubechies wavelet is most effective in identifying S(1) and S(2). In addition, the boundaries of S(1), S(2), and the onset and duration of the systolic murmur thus identified within the systole could be marked using the wavelet-filtered signal's strength. Furthermore, quantitative measures derived from a 2(nd) order AR model were used to delineate the configuration and pitch of the systolic murmur found within through piecewise segmentation. The proposed approach was tested and proved effective in delineating a set of clinically diagnosed systolic murmurs. The suggested AR and wavelet transform combined approach can be generalized with minor adjustments to delineate diastolic murmurs as well.

Enhancement of spectral analysis of myoelectric signals during static contractions using wavelet methods

In this paper, we introduce wavelet packets as an alternative method for spectral analysis of surface myoelectric (ME) signals. Both computer synthesized and real ME signals are used to investigate the performance. Our simulation results show that wavelet packet estimate has slightly less mean square error (MSE) than Fourier method, and both methods perform similarly on the real data. Moreover, wavelet packets give us some advantages over the traditional methods such as multiresolution of frequency, as well as its potential use for effecting time-frequency decomposition of the nonstationary signals such as the ME signals during dynamic contractions. We also introduce wavelet shrinkage method for improving spectral estimates by significantly reducing the MSE's for both Fourier and wavelet packet methods.

Analysis of pattern reversal visual evoked potentials (PRVEP's) by spline wavelets

In this study, the pattern-reversal visual evoked potentials (PRVEP's) collected from normal and demented subjects are investigated by applying the quadratic spline wavelet analysis. The data are decomposed into six octave frequency bands. For quantitative purposes, the wavelet coefficients in the residual waveform representing the delta-theta band activity (0-8 Hz) are explored to characterize the (N70-P100-N130) complex. Specifically, the coefficients corresponding to the location of N70, P100, and N130 peaks are investigated for their sign in order to test whether they represent a consistent (N70-P100-N130) complex in the averaged waveform. Waveforms with normal latency (N70-P100-N130) complex are observed to have positive second, negative third, and positive fourth coefficients in amplitude in their residual scale standing for the delta-theta (0-8 Hz) band activity. The method allows for the analysis of oscillatory-phase behavior of the normal and pathological PRVEP's in their delta-theta band based on a few quantitative measures consistent with the time-frequency occurrence of the major components of the evoked potential.

Investigating the effects of opioid drugs on electrocortical activity using wavelet transform

Fetal electrocortical activity (ECoG) is characterized by two distinct patterns: HVSA (high voltage, slow activity) and LVFA (low voltage, fast activity). Using the wavelet transform (WT), we recently reported that the frequency characteristics of these two ECoG patterns undergo significant maturational changes prior to birth (Akay et al. 1994a). We now report that fetal ECoG can also be significantly affected by pharmacological agents. In this paper, we compared the effects of two opioid drugs (morphine and [D-Pen2, D-Pen5]-enkephalin, DPDPE) on fetal ECoG, using the chronically instrumented fetal lamb model. Morphine was infused intravenously (i.v.) at 2.5 mg/h, while DPDPE was infused into the lateral cerebroventricle (i.c.v.) at 30 micrograms/h. The ECoG was analyzed using WT. We performed multi-resolution decomposition for four sets of parameters D2j where -1 < j < -4. The four series WTs represent the detail signal bandwidths: (1) 16-32 Hz, (2) 8-16 Hz, (3) 4-8 Hz, (4) 2-4 Hz. The data were subjected to statistical analysis using the Kolmogorov-Smirnov (KS) test. Both morphine and DPDPE resulted in a significant increase in power in the first wavelet band, while power was reduced in the second, third and fourth wavelet bands. In addition, both drugs resulted in a disruption of the normal cyclic pattern between the two ECoG patterns. There was a difference in the time course of action between morphine and DPDPE. This is the first occasion in which continuous ECoG has been subjected to rigorous statistical analysis. The results suggest that the WT-KS method is most suitable for quantitating changes in the ECoG induced by pharmacological agents.