Implementation of Portable Ultrasound for Heart Disease Detection Using Cloud Computing-Based Machine Learning

Heart disease has become the leading cause of death today. Electrocardiogram (ECG) is a device used to detect the patient's heart condition. This ECG test is painless but can provide important information to diagnose the patient's heart condition. The ECG signal produced becomes a reference for health practitioners to detect heart disease. Arrhythmia refers to irregularities in the rhythm of the heartbeat. The classification of ECG signals has attracted many researchers to study in recent years. In this study, classification using deep learning has shown very good results in detecting arrhythmias. The preprocessing process is carried out using normalize bound and autoencoder. ECG signals are segmented into short signals before going into the classification section. The proposed classification method uses DNN (Deep Neural Network). Where the DNN classification method gets excellent results, namely accuracy reaches 99.8%, sensitivity 87.77%, specificity 99.81%.

Background. Machine learning allows applying various intelligent algorithms to produce diagnostic and/or prognostic models. Such models can be used to determine the functional state of the heart, which is diagnosed by speckle-tracking echocardiography. To determine the patient's heart condition in detail, a classification approach is used in machine learning. Each of the classification algorithms has a different performance when applied to certain situations. Therefore, the actual task is to determine the most efficient algorithm for solving a specific task of classifying the patient's heart condition when applying the same speckle-tracking echocardiography data set. Objective. We are aimed to evaluate the effectiveness of the application of prognostic models of logistic regression, the group method of data handling (GMDH), random forest, and adaptive boosting (AdaBoost) in the construction of algorithms to support medical decision-making on the diagnosis of coronary heart disease. Methods. Video data from speckle-tracking echocardiography of 40 patients with coronary heart disease and 16 patients without cardiac pathology were used for the study. Echocardiography was recorded in B-mode in three positions: long axis, 4-chamber, and 2-chamber. Echocardiography frames that reflect the systole and diastole of the heart (308 samples in total) were taken as objects for classification. To obtain informative features of the selected objects, the genetic GMDH approach was applied to identify the best structure of harmonic textural features. We compared the efficiency of the following classification algorithms: logistic regression method, GMDH classifier, random forest method, and AdaBoost method. Results. Four classification models were constructed for each of the three B-mode echocardiography positions. For this purpose, the data samples were divided into 3: training sample (60%), validation sample (20%), and test sample (20%). Objective evaluation of the models on the test sample showed that the best classification method was random forest (90.3% accuracy on the 4-chamber echocardiography position, 74.2% on the 2-chamber, and 77.4% on the long axis). This was also confirmed by ROC analysis, wherein in all cases, the random forest was the most effective in classifying cardiac conditions. Conclusions. The best classification algorithm for cardiac diagnostics by speckle-tracking echocardiography was determined. It turned out to be a random forest, which can be explained by the ensemble approach of begging, which is inherent in this classification method. It will be the mainstay of further research, which is planned to be performed to develop a full-fledged decision support system for cardiac diagnostics.

The most difficult task in medicine is making a diagnosis of heart illness. Since the decision is dependent on a huge number of clinical and pathological information, the diagnosis of heart illness is challenging. This is such as resulted in a significant increase in interest among academics and medical professionals in accurate and efficient cardiac disease prediction. Since time is of the essence in cases of heart sickness, getting the appropriate diagnosis quickly is essential. Since heart disease is the leading cause of death globally, early detection of heart disease is crucial. With the proper case of training and testing, machine learning has recently emerged as one of the most advanced, trust worthy, and helpful technologies in the medical industry, offering the most assistance for sickness prediction. The main goal of this endeavor is to examine various heart disease prediction models and choose pertinent heart disease variables using a genetic approach. Genetically optimized prediction models outperform conventional prediction models in terms of performance. Analyzing heart disease using UCI datasets. The Cleveland database is the only one that ML researchers have used thus far. The patient's heart condition is indicated in the “target” field. It is positioned in the target column and has an integer value between 0 (no presence) and 1 (presence). The goal is the dependent variable, while the other factors are the independent variables.

Cardiac Ablation is an effective treatment of arrhythmia in which physicians terminate fast heart rate by transecting abnormal electrical conduction pathways in the heart with RF energy. During the procedure, physicians diagnose the condition of the heart and locate ablation sites by analyzing electrical signals sensed by catheters inserted into the heart. Due to the limited observation of the patient's heart, there may exist multiple heart conditions that can explain historical observations, causing ambiguities in the patient's heart condition. During the procedure, physicians have to visualize and continuously update these suspected heart conditions in their mind, causing heavy mental burden on the physicians. In this paper, cardiac electrophysiology is formalized using a physiological model of the heart, such that the diagnosis problem during cardiac ablation can be formalized as parameter identification and state estimation problems with the heart model. We then propose a model-based clinical assist system which partially solves the diagnosis problem during cardiac ablation. The system enumerates suspected heart conditions by creating digital twins of the patient's heart with heart models. The heart models are used to represent and visualize suspected heart conditions, and are systematically updated and removed with new information during the ablation procedure. The system provides more rigorous and intuitive interpretation of current understanding of the patient's heart, and improves the accuracy and efficiency of cardiac ablation procedures by relieving the physicians from demanding low-level reasoning.

Aim. To assess right heart condition in patients with coronavirus disease 2019 (COVID-19) pneumonia.Material and methods. One hundred and five patients with COVID-19 pneumonia were divided into 3 groups depending on the involvement of lung parenchyma: group I — 0-25%, II — 25-50%, III — 50-75%. The clinical status of patients was assessed using the NEWS2 and SHOKS-COVID scales. A complete blood count and biochemical blood tests were performed to determine the level of N-terminal pro-brain natriuretic peptide (NT-proBNP) and troponin I. Echocardiography was performed to assess the right heart structural, hemodynamic and functional parameters.Results. In patients with COVID-19 pneumonia, with an increase in lung parenchyma involvement, the intensity of systemic inflammatory response increased: C-reactive protein, group I — (4 [1,9; 35] mg/l), in III — (70,5 [33; 144] mg/l) (pI-III=0,012); myocardial stress marker level increased: NT-proBNP, group I — 77 [48; 150] ng/l, group III — 165 [100; 287] ng/l (pI-III=0,047). The dependence of NT-proBNP on C-reactive protein level was revealed (r=0,335, p=0,03). Intergroup comparison did not reveal significant differences between the main right heart functional parameters: TAPSE, Tei index (PW and TDI), FAC of the right ventricle (RV) (p>0,05). However, differences in the tricuspid annular peaks were found as follows: group I — 0,14 [0,12; 0,14] m/s, group II — 0,14 [0,12; 0,15] m/s, group III — 0,16 [0,14; 0,17] m/s (pI-II=0,012, pI-III=0,014) and RV global longitudinal strain: group I — 19,63±7,72%, group III — 27,4±5,93% (pI-III=0,014). The relationship between the RV global longitudinal strain and SHOKS-COVID score was confirmed (r=0,381; p=0,024).Conclusion. Patients with COVID-19 pneumonia showed no signs of right heart dysfunction. The development of RV hyperfunction was noted. Most likely, this is a compensatory mechanism in response to acute RV afterload. NT-proBNP increase under conditions of an inflammatory response may indicate myocardial stress. The results obtained allow to expand our understanding of the right heart condition in patients with COVID-19 pneumonia.

Objective To investigate the differences of heart mass and lung mass in forensic autopsy cases and to explore their application value in forensic identification. Methods The data from 1 614 autopsy cases accepted by center of Medico-legal Investigation of China Medical University between 2007 to 2016 were collected. The correlation of heart and lung mass with age, height, body weight, and body mass index （BMI）, as well as differences in different causes of death were analyzed by GraphPad Prism 6.0 software. Results The heart mass and lung mass of males were higher than those of females （P<0.05）. The heart mass of males and females was positively correlated with age, height, body weight and body mass index （BMI） （P<0.05）. The heart mass of patients dying from sudden cardiac death （SCD） was significantly higher than those dying from other causes of death. The lung mass of patients dying from drowning and delayed treatment was higher than those dying from other causes of death （P<0.05）. Conclusion In forensic practice, measurement of the heart mass and lung mass has certain significance for differential diagnosis and diagnosis of different causes of death.

In this paper we consider a portable cardioanalyzer for assessment of heart conditions without limiting patient movement including ECG recorder with external electrodes, wireless transmitter for work in networks of the third and fourth generation and a computing module. As the computing module we use a MCU with developed software. The characteristics of the closest analogs are considered. Distinctive features of the proposed portable cardioanalyzer for assessment of the state of heart without limiting patient movement are the definition of the critical patient's heart condition in real time based on non-invasive heart conditions diagnosis methods protected by patents and automatic ambulance call if the patient's heart is in a critical condition.

AimThe aim of the paper is to present the risk of pregnancy for mother and her child in a young patient who had a surgery to repair Tetralogy of Fallot (ToF), who gave a birth to her firstborn by having a cesarean section.Case report23 years old patient, in 28 weeks of pregnancy was admitted to the clinic due to her medical record. She did not have any subjective complaints. She had two surgeries to repair ToF. After the surgery, she had residual ventricular septal defect (VSD). She had her first surgery 20 years ago (she was 3 years old), and second 7 years ago (she was 16). She had regular check-ups since, and her heart condition was unchanged. Due to her heart surgeries and VSD, a cardiologist indicates that she should deliver by having a c-section when she is 36 weeks pregnant. The patient’s heart condition was stabilized and the patient was sent home. She was recommended to have her cardiologist check up on her as she leaves the hospital and to have a gynecological examination in 6 weeks.ConclusionIt can be concluded that team work and prenatal care, in most cases, lead to delivery without complication, both for mother and fetus.

Stethoscope is an acoustic medical device widely use by doctors to listen to the sound of the heartbeat. Based on the sound of the heartbeat, the doctor can analyze the patient's heart condition. Acoustic stethoscope has a weakness in low sensitivity of sound that can be heard and vulnerable to external noise interference. The Addition of an electronic circuits in acoustic stethoscope will strengthen the heart rate signal. The addition of electronic circuits in the acoustic stethoscope is often called an electronic stethoscope. Electronic stethoscope utilizes a microphone and amplifier and electronic circuit as modifiers of the acoustic signal into digital. Electronic stethoscopes can cover the shortage of the less sensitive acoustic stethoscope and can minimize error analysis of the state of the patient's heart. To analyze the state of the heart beat, the output produced by the electronic stethoscope can be visualized in the form of the spectrum and played repeatedly by doctors with an audio player application.

Introduction. Cardiovascular complications are the common in patients with Henoch-Schönlein purpura (HSP; IgA-vasculitis). Heart condition is strictly connected with gall bladder (GB) changes. However the heart condition in patients with HSP in dependence of gallbladder status was not studied before. Purpose. To reveal peculiarities of heart structure and function in patients with HSP in dependence of gall bladder condition. Material and methods. We analyzed data from 75 patients with active HSP, which underwent the treatment according to guidelines of Helsinki Declaration. Investigated patients included 57% females and 43% males, middle age – 47.7±4.3 years; middle body mass index (BMI) 27,9 kg/m2. Patients were divided into 6 groups: group 0 – normal intact GB (38.7%); group 1 – sludge, polyposis and cholesterosis of GB (14.7%); group 2 – bent GB body (10.1%); group 3 – GB neck deformations and signs of chronic cholecystitis (18.7%); group 4 – cholelithiasis (10.1%); group 5 – patients with removed GB (7.7%). Digital data was processed with the statistical methods, the quantitative variables are expressed as mean ± standard deviation. Values of р&lt;0.05 were considered statistically significant. Results. Patients with HSP significantly more often had some GB disorders than its intact status (61.3% vs 38.7%, р&lt;0.05). Group 1 with sludge, cholesterosis and polyposis of GB was characterized by the normal values of EchoCG parameters. Patients with bent GB body (group 2) had bigger arrhythmia frequency and heart rate close to the maximal value but the best EchoCG. Group 3 had the most often left axis deviation and quite rare arrhythmias. Group 4 of patients with HSP and cholelithiasis was characterized by the maximal frequency of arterial hypertension, the highest frequency of arrhythmias, the most often presence of both bundle branch block and the worst EchoCG parameters. Group 5 of patients with HSP and removed GB was characterized by the maximal frequency of presence of left ventricle hypertrophy, the highest heart rate and left axis deviation. Heart structure in these patients can be estimated as better than in patients with cholelithiasis. Conclusions. The heart and GB conditions in patients with HSP are tightly connected. The worsening of GB condition was accompanied by worsening of structural and functional heart parameters. Cholecystectomy can improve heart condition. Patients with HSP and GB disorders need more thorough examination and early correction of biliary diseases.

Design and realization of a wireless PC-based system for electrocardiography and data acquisition of a patient's heart condition is described in this paper. The system is designed and realized according to virtual instrumentation concept consisting of two subsystems: 1) The battery powered external compact and mobile wireless ECG acquisition hardware on the side of patient and USB connected communication wireless module on the PC side; 2) Standard personal computer with graphical user interface and database support. The USB port is selected to be the communication interface between the ECG acquisition hardware and the PC and also to supply power to the communication wireless module at the PC side. The Graphical User Interface (GUI) is designed in the traditional style of ECG paper plots and additional displays based on suggestions of cardiologists. Strict medical requirements are respected in the design of the system. Key words: ECG, virtual instrument, wireless, MCU.

Now-a-days, heart disease has the greatest impact in the cause of mortality. Although people's lives can be saved through accurate prediction of heart disease, it may also lead to death if the prediction is inaccurate. Heart disease prediction at an earlier stage is a very difficult task. The earlier prediction provides information about the patient's heart condition so that treatment can be made effectively. To solve problems which are complex and nonlinear, machine learning (ML) algorithms can be used. In order to enhance the accuracy of classification and prediction, different machine learning (ML) algorithms can be utilized together (ensemble models). K-Nearest Neighbor, Random Forest, Decision Tree are the various ML techniques that have been employed for ensemble models. The majority voting technique is utilized by the ensemble model for the prediction.

The electrocardiogram (ECG) is a non-invasive test that records the electrical activity of the heart and is important in the investigation of cardiac abnormalities. Each portion of the ECG waveform carries various types of information for the cardiologists analyzing patient's heart condition. ECG interpretation at the present time remains dependent manually in time domain. It is difficult for the cardiologists to make a correct diagnosis of cardiac disorder. A computerized interpretation of ECG is needed in order to make the diagnosis more efficient. This paper discusses the use of digital signal processing approach for the detection of heart blocks in ECG signals. Signal analysis techniques such as the periodogram power spectrum and spectrogram time-frequency analysis are employed to analyze ECG variations. Seven subjects are identified: normal, first degree heart block, second degree heart block type I, second degree heart block type II, Third degree heart block, right bundle branch block and left bundle branch block. Analysis results revealed that normal ECG subject is able to maintain higher peak frequency range (8 Hz), while heart block subjects revealed a significant low peak frequency range (< 4 Hz). The results revealed that the periodogram power spectrum can be used to differentiate between normal and heart block subjects, while the spectogram time-frequency analysis is used to give better characterization of ECG parameters. These analyses can be used to construct ECG monitoring and analyzing system for heart blocks detection.

Auscultation that defined as listening to heart sound is the most practical and comfortable method to monitor patient's heart condition. Despite that, the complexity of murmur that exist in the heart sounds often provide misleading in diagnosis. This work proposed an auto-diagnosis system for heart disease by classifying the pathological heart sounds. Mitral valve stenosis and bicuspid aortic valve stenosis are two focused diseases due to the fatal effect. The analysis stage involved the transformation of heart sound signal into envelope signal in order to assist the location of the first and second heart sound. Moreover, power spectrum and Mel Frequency Cepstral Coefficient (MFCC) are extracted to classify the diseases where Fine Gaussian SVM is found to perform the best classifier model with 86.1% of accuracy. Later, the testing stage of the classification process has yielded the 86% of accuracy in detecting the true disease with 93% of average F1-score. Finally, a pre-develop prototype is constructed using GUI system that able to automatically diagnose the type of heart disease. The system, in future, has high potential to provide a better diagnosis system with less time-diagnose and operator-independent.

Heart-lung machines can effectively oxygenate blood, but their prolonged use causes difficulties not directly related to the patient's heart condition or the specific procedures used to correct it. In extreme cases a patient may be seriously affected and may develop thromboses, abnormal permeability of the vascular system (particularly in the lungs), blood clots, and occasionally brain damage (1, 2). The results of several studies (3-6) suggest that denaturation of blood proteins at blood-gas interfaces in the heart-lung machine may be responsible for some of the postoperative difficulties. We have found no specific studies of the effects of the gas/liquid interfaces in the heart-lung machine on individual blood proteins. Therefore, we undertook an investigation of the denaturation of gamma globulin, albumin, and their mixtures in the disc oxygenator. The advantage of studying individual blood proteins is that the results can be interpreted more easily than studies with whole blood. However, data obtained in this simple model system can, at best, tell only part of the story regarding the medical complications of open-heart surgery. We chose to work with gamma globulin because of its instability at the gas/liquid interface. This instability is easily demonstrated. If a stream of air is passed through a clear solution of gamma globulin, a precipitate of the aggregated protein rapidly forms. Albumin was selected for study because it is one of the principal components of whole blood and because it is often added to solutions of labile proteins as a stabilizer. The Complement System and Denatured Gamma Globulin. The complement system can be activated by interaction with antigen–antibody complexes or by interaction with heat denatured, aggregated gamma globulin. Activation is known to increase capillary permeability, to enhance phagocytosis, to initiate chemotactic migration of leucocytes, and to damage membranes (7, 8).