Real-Time Multi-Level Neonatal Heart and Lung Sound Quality Assessment for Telehealth Applications

Abstract

In this study, a new method is proposed to assess heart and lung signal quality objectively and automatically on a 5-level scale in real-time, and to assess the effect of signal quality on vital sign estimation. A total of 207 10 s long chest sounds were taken from 119 preterm and full-term babies. Thirty of the recordings from ten subjects were obtained with synchronous vital signs from the Neonatal Intensive Care Unit (NICU). As a reference, seven annotators independently assessed the signal quality. For automatic quality classification, 400 features were extracted from the chest sounds. After feature ranking and selection, class balancing, and hyperparameter optimization, a variety of multi-class and ordinal classification and regression algorithms were trained. Then, heart rate and breathing rate were automatically estimated from the chest sounds. For the deep learning model, YAMNet, a deep convolutional neural network pre-trained on the AudioSet-Youtube corpus for sound classification was used. After modification of the final output layers of the neural network and class balancing, transfer learning was applied to YAMNet for heart and lung signal quality classification. The results of subject-wise leave-one-out cross-validation show that the best-performing models had a balanced accuracy of 56.8% and 51.2% for heart and lung qualities, respectively. The best-performing models for real-time analysis (<200 ms) had a balanced accuracy of 56.7% and 46.3%, respectively. Our experimental results underscore that increasing the signal quality leads to a reduction in vital sign error.

A Fusion of Handcrafted Features and Deep Learning Classifiers for Heart Murmur Detection

“…S1, systole, S2, and diastole. Heart segmentation was performed using a Hidden Semi-Markov Model, which takes into account heart rate range based on age group, which were (1) Neonate: 110-200 bpm, (2) Infant: 70-200 bpm, (3) Child: 60-170 bpm, (4) Adolescent: 40-170 bpm, (5) Young Adult: 40-130 bpm and (5) Unknown: 50-160 bpm [6].…”

“…Based on our past work on PCG signal quality, five types of features were extracted from the whole recordings, (1) statistical: variance, skewness and kurtosis of audio/autocorrelation signal, (2) entropy: sample, Shannon, Renyi and Tsallis, (3) power features: total power, various power ratios between 100-1000 Hz, 3 dB bandwidth, 1st, 2nd and 3rd quartiles as well as interquartile range, standard deviation, mean frequency, power centroid and max power, (4) MFCCs: minimum, maximum, mean, median, mode, variance and skewness of a 13-level decomposition in Mel scale and log energy with a window length of 25 ms and overlap length of 15 ms (5) autocorrelation: correlation prominence, sinusoid correlation and Hjorth activity to measure the strength of the signal periodicity [6]. The same features were extracted from segmented signals and averaged for each segment i.e., S1, systole, S2, diastole.…”

A Blind Filtering Framework for Noisy Neonatal Chest Sounds

“…The measure of quality utilised here for both the heart and lung sounds assessment is based on our previous work in [67]. Briefly, a linear regression model has been tuned in order to map a collection of audio features into a 5-point scale measuring signal quality for heart and lung sounds (from 1 for the lowest to 5 for the highest quality).…”

“…Then, the regression model is trained by a set of best features, while different cost functions (SVM and least-squares) and different regularization methods (lasso and rigid) are examined to obtain the best test results based on mean squared error. More description of the features and the regression can be found in [67].…”

Interpretation of lung disease classification with light attention connected module

“…The frequency of respiratory sounds measured by the stethoscope system is 100–2000 Hz, whereas humans are sensitive only to frequencies of 1000–2000 Hz [11] . Low-quality breath sounds complicate symptom monitoring and diagnosis or lead to misdiagnosis [12] . In addition, it is difficult to evaluate breath patterns during auscultation because a doctor’s experience with abnormal sounds is very important.…”