With the development of diagnostic devices over the past few decades, the algorithmic classification of heart sound recordings has become possible. Although this field has been under research for a relatively long time, the classification of such recordings is not yet straightforward.We were given a large manually classified database of heart sounds with the challenge [1]. We worked together with an experienced cardiologist to find the aspects affecting the classifications.To algorithmically classify a heart sound recording as normal or abnormal, it is necessary in most cases to accurately locate both the fundamental heart sounds and the systolic and diastolic regions. For this purpose we used the method provided in the example entry [2][3]. Minor modifications were made, such as tuning some of the parameters to match the database parameters.In the classification of the heart sounds, we were looking for the morphological features of the abnormal signals, for example, mitral stenosis, mitral insufficiency, aortic stenosis, aortic insufficiency, tricuspid stenosis and tricuspid insufficiency. We extracted several features from both time and frequency domains, for example, the frequency properties of systolic and diastolic segments and resampled wavelet envelope features.The extracted features were classified by the help of a support vector machine. In order to train the classifier, we used a reduced, sorted dataset with a more balanced ratio of abnormal and normal signals. During the official phase, our best scores on a random subset were 77.2% sensitivity, 85.2% specificity and 81.2% final modified accuracy (MAcc). Our scores for the entire test dataset are 83.77% sensitivity, 76.8% specificity and 80.28% MAcc. Our scores for the entire training dataset are 93.08% sensitivity, 84.70% specificity and 88.70% MAcc.

No abstract

This paper proposes a novel phonography-based method for Fetal Breathing Movement (FBM) detection by its excitation sounds. It requires significantly less effort than the current procedures, and it allows long-term measurement, even at home. More than 50 pregnancies in the third trimester were examined, for a minimum of 20 minutes, taking synchronous long-term measurements using a commercial phonocardiographic fetal monitor and a 3D ultrasound machine. To analyze the gained chaotic signal, the frequency band was split into single test-frequencies in the 15-35 Hz frequency band, and their signal-free (silent) zones were regarded as the starting point (SP) of the next motions. The analysis made other disturbing signals, such as fetal hiccups, trunk rotation and limb movements, or maternal heart beats, distinguishable. The dominant test-frequencies of the analysis were predicted by a Hidden Markov Model (HMM). The SPs of the motion units (episodes) were determined by some features of the FBM, applying weighting factors. The recorded material lasted for 16 hours altogether (with nearly 3.5 hours of FBM). Based on the results of HMM method, nearly 7500 FBM episodes were identified in the phonogram signal with an average length of 0.96±0.13 seconds. The procedure for phonography-based breathing movement detection can be combined with a fetal heart activity measurement, and thus allows very intensive, long-term monitoring of the fetus.

The detailed assessment of fetal breathing movement (FBM) monitoring can be a pre-indicator of many critical cases in the third trimester of pregnancy. Standard 3D ultrasound monitoring is time-consuming for FBM detection. Therefore, this type of measurement is not common. The main goal of this research is to provide a comprehensive image about FBMs, which can also have potential for application in telemedicine. Fifty pregnancies were examined by phonography, and nearly 9000 FBMs were identified. In the case of male and female fetuses, 4740 and 3100 FBM episodes were detected, respectively. The measurements proved that FBMs are well detectable in the 20–30 Hz frequency band. For these episodes, an average duration of 1.008 ± 0.13 s (p < 0.03) was measured in the third trimester. The recorded material lasted for 16 h altogether. Based on these measurements, an accurate assessment of FBMs could be performed. The epochs can be divided into smaller-episode groups separated by shorter breaks. During the pregnancy, the rate of these breaks continuously decreases, and episode groups become more contiguous. However, there are significant differences between male and female fetuses. The proportion of the episodes which were classified into minimally 10-member episode groups was 19.7% for males and only 12.1% for females, even at the end of the third trimester. In terms of FBM detection, phonography offers a novel opportunity for long-term monitoring. Combined with cardiac diagnostic methods, it can be used for fetal activity assessment in the third trimester and make measurement appreciably easier than before.

Objective: Atrial fibrillation (AF) is one of the most common serious abnormal heart rhythm conditions, and the number of deaths related to atrial fibrillation has increased by an order of magnitude in the past decades. We aim to create a system, which can provide help for cardiologist, classifying and highlighting important segments in recordings. Approach: In this paper, we propose a novel approach for AF detection using only a deep neural architecture without any traditional feature extractor for real-time automated suggestions of possible cardiac failures that can detect class invariant anomalies in signals recorded by a single channel portable ECG device. Results: Detecting the four categories: Normal, AF, Other and Noisy in terms of the official, F1 metric of hidden dataset maintained by the organizers of PhysioNet Computing in Cardiology Challenge 2017, our proposed algorithm has scored 0.88, 0.80, 0.69, 0.64 points respectively, and 0.79 on average.