Data prediction for cases of incorrect data in multi-node electrocardiogram monitoring

The development of a mesh topology in multi-node electrocardiogram (ECG) monitoring based on the ZigBee protocol still has limitations. When more than one active ECG node sends a data stream, there will be incorrect data or damage due to a failure of synchronization. The incorrect data will affect signal interpretation. Therefore, a mechanism is needed to correct or predict the damaged data. In this study, the method of expectation-maximization (EM) and regression imputation (RI) was proposed to overcome these problems. Real data from previous studies are the main modalities used in this study. The ECG signal data that has been predicted is then compared with the actual ECG data stored in the main controller memory. Root mean square error (RMSE) is calculated to measure system performance. The simulation was performed on 13 ECG waves, each of them has 1000 samples. The simulation results show that the EM method has a lower predictive error value than the RI method. The average RMSE for the EM and RI methods is 4.77 and 6.63, respectively. The proposed method is expected to be used in the case of multi-node ECG monitoring, especially in the ZigBee application to minimize errors.

Prenatal Abdominal Electrocardiogram Monitoring System using IoT in Cloud Environment: A MIMO approach

<p>The application of Internet of Things (IoT) for acquiring, analyzing and transmission of medical data is increasing in recent years. Especially in abdominal ECG processing the need is more. Since the fetal movements are random in the abdomen, a single electrode can’t be able to acquire the fetal ECG. So multi-electrodes are used to record the same. At the same time all electrodes will not provide continuous ECG signal due to the fetal movements. The temperature, pressure and heart rate of the mother also monitored for effective diagnosis. This options makes the design a multi-input structure. In existing methods, Multi-input multi-output options are not available. In addition to that the complexity increases if number of input increases. In conventional methods, the complete machine is available in the patient room. But here in this work the product is divided into three units, bedside unit, doctors unit and main server. The bedside unit is an ECG acquisition device developed using a multi-lead heart rate monitor, sensors and microcontroller. Zigbee is used to transmit the information from the patient bedside to doctors unit which makes it wireless. During the movement of the patient also the data can be viewed. The Multi-output data corresponds to fetal ECG, maternal ECG, heart rate, temperature, pressure. The IoT using raspberry pi module connects the doctors unit with the main server. The machine learning algorithms analyze the ECG data of all electrodes and sensor outputs. The multi-outputs are viewed in a Graphical User Interface (GUI). The integration of the system is conducted to construct a complete IoT-based ECG monitoring system and diagnosis in Cloud environment. </p>

Prenatal Abdominal Electrocardiogram Monitoring System using IoT in Cloud Environment: A MIMO approach

<p>The application of Internet of Things (IoT) for acquiring, analyzing and transmission of medical data is increasing in recent years. Especially in abdominal ECG processing the need is more. Since the fetal movements are random in the abdomen, a single electrode can’t be able to acquire the fetal ECG. So multi-electrodes are used to record the same. At the same time all electrodes will not provide continuous ECG signal due to the fetal movements. The temperature, pressure and heart rate of the mother also monitored for effective diagnosis. This options makes the design a multi-input structure. In existing methods, Multi-input multi-output options are not available. In addition to that the complexity increases if number of input increases. In conventional methods, the complete machine is available in the patient room. But here in this work the product is divided into three units, bedside unit, doctors unit and main server. The bedside unit is an ECG acquisition device developed using a multi-lead heart rate monitor, sensors and microcontroller. Zigbee is used to transmit the information from the patient bedside to doctors unit which makes it wireless. During the movement of the patient also the data can be viewed. The Multi-output data corresponds to fetal ECG, maternal ECG, heart rate, temperature, pressure. The IoT using raspberry pi module connects the doctors unit with the main server. The machine learning algorithms analyze the ECG data of all electrodes and sensor outputs. The multi-outputs are viewed in a Graphical User Interface (GUI). The integration of the system is conducted to construct a complete IoT-based ECG monitoring system and diagnosis in Cloud environment. </p>

Poisoning due to consumption of horse chestnut seed

Horse chestnut (Aesculus hippocastanum) is a common tree found on roads and parks. The shape of the fruit is very similar to that of the edible Korean chestnut (Castanea crenata); thus, people can eat it by mistake. However, reports of the side effects and toxicity from ingestion are very rare. A 46-year-old male who had no unusual findings in the past had eaten horse chestnut seed which he had mistaken to be Korean chestnut. He visited the emergency department (ED) with complaints of epigastric pain, nausea, and sweating. Blood tests showed a slight increase in the levels of liver enzymes, serum amylase, and pancreatic amylase. During the monitoring, he complained of palpitations, and electrocardiogram showed atrial fibrillation. On the following day after conservative treatment, blood testing and electrocardiogram showed normal findings. He was discharged from the ED as he did not complain of any further symptoms. When a patient who has eaten horse chestnut visits the ED, blood examination and electrocardiogram monitoring are needed, and conservative treatment is required.

Atrial fibrillation detection in outpatient electrocardiogram monitoring: An algorithmic crowdsourcing approach

Background Atrial fibrillation (AFib) is the most common cardiac arrhythmia associated with stroke, blood clots, heart failure, coronary artery disease, and/or death. Multiple methods have been proposed for AFib detection, with varying performances, but no single approach appears to be optimal. We hypothesized that each state-of-the-art algorithm is appropriate for different subsets of patients and provides some independent information. Therefore, a set of suitably chosen algorithms, combined in a weighted voting framework, will provide a superior performance to any single algorithm. Methods We investigate and modify 38 state-of-the-art AFib classification algorithms for a single-lead ambulatory electrocardiogram (ECG) monitoring device. All algorithms are ranked using a random forest classifier and an expert-labeled training dataset of 2,532 recordings. The seven top-ranked algorithms are combined by using an optimized weighting approach. Results The proposed fusion algorithm, when validated on a separate test dataset consisting of 4,644 recordings, resulted in an area under the receiver operating characteristic (ROC) curve of 0.99. The sensitivity, specificity, positive-predictive-value (PPV), negative-predictive-value (NPV), and F1-score of the proposed algorithm were 0.93, 0.97, 0.87, 0.99, and 0.90, respectively, which were all superior to any single algorithm or any previously published. Conclusion This study demonstrates how a set of well-chosen independent algorithms and a voting mechanism to fuse the outputs of the algorithms, outperforms any single state-of-the-art algorithm for AFib detection. The proposed framework is a case study for the general notion of crowdsourcing between open-source algorithms in healthcare applications. The extension of this framework to similar applications may significantly save time, effort, and resources, by combining readily existing algorithms. It is also a step toward the democratization of artificial intelligence and its application in healthcare.

Incidence of cardiac arrhythmias in patients with COVID-19 infection according to 24-hour electrocardiogram monitoring

Cardiac arrhythmias in patients with COVID-19 infection may be due to many pathophysiological factors. Further study on the structure of arrhythmias in this category of patients will reveal clinically significant arrhythmias and select the optimal management. The aim: to determine the features of arrhythmias in patients with and without concomitant cardiovascular disease who suffered from COVID-19 infection based on the results of 24-hour electrocardiogram (ECG) monitoring. Materials and methods. 84 patients (45 men – 53.5 %, 39 women – 46.5 %) who had COVID-19 infection over 12 weeks previously were examined. Patients were divided into 2 groups – with and without a history of concomitant cardiovascular disease. The patient groups did not differ in age (P = 0.33) and sex (P = 0.58, P = 0.64). 24-hour ECG monitoring was performed on a Cardiosens K device (XAI-MEDICA, Kharkiv) according to the standard method. Results. Comparison of 12-channel ECG data did not reveal a significant difference in the incidence of single atrial (P = 0.13) and ventricular extrasystoles (P = 0.37) between the two groups, but sinus tachycardia was significantly more common in patients without concomitant cardiovascular disease (P = 0.022). According to 24-hour ECG monitoring, a significantly higher total number of arrhythmias, in particular, supraventricular extrasystoles (P = 0.009), high gradations of ventricular arrhythmias: paired ventricular extrasystoles (P = 0.041), ventricular bigeminy (P = 0.005), ventricular trigeminy (P = 0.004), ventricular salvos (P = 0.017) were detected significantly more frequently in patients with concomitant cardiovascular disease after COVID-19 infection than those in the comparison group. The results of 24-hour ECG monitoring also showed that patients without cardiovascular disease were significantly more likely to have inappropriate sinus tachycardia (P = 0.03) and postural orthostatic tachycardia (P = 0.04). Paroxysmal arrhythmias were significantly more common in patients with concomitant cardiovascular pathology, namely unstable (P = 0.002) and stable paroxysms of atrial tachycardia (P = 0.014), unstable paroxysms of monomorphic ventricular tachycardia (8.3 %), paroxysms of atrial fibrillation (6.2 %). Conclusions. 24-hour ECG monitoring should be advised in patients with COVID-19 infection and concomitant cardiovascular disease in addition to recording a standard 12-channel ECG to detect prognostically unfavorable cardiac arrhythmias, possible arrhythmogenic manifestations of post-COVID-19 syndrome and choose management tactics for these patients.