Time ECG Monitoring Research Articles

Development of real time ECG monitoring and unsupervised learning classification framework for cardiovascular diagnosis

In this work, a novel meta-heuristic-based feature ranking and classification approach is developed on the real-time ECG data. Initially, the data is captured using AD8232 biopotential sensor and transmitted to Amazon Web Service (AWS) Internet of Things (IoT) core through ESP8266 gateway via Message Queuing and Telemetry Transport (MQTT) protocol. An improved inter quartile range (IIQR) based filtering is applied on each feature measure to find outliers in the data. A probability estimator-based feature ranking method is used to find the key features. With unsupervised clustering the essential key segments are calculated and used as class labels to train the classifier. Finally, the prediction rate of the model on the segmented classes is improved with the use of ensemble learning. The real-time ECG data of three different individuals are used to test the unsupervised ensemble learning model (Support Vector Machine (SVM) + Linear Regression (LR) + ORF (Optimized Random Forest) + (K-Nearest Neighbor (KNN) + Gradient Boost (XGBoost)) and obtains an overall accuracy of 99.63% (Person 1), 99.75% (Person 2) and 99.78% (Person 3) which significantly outperforms the base ensemble classifiers such as, (LR + SVM + XGBoost) with 94.2% accuracy, (LR + KNN + XGBoost) with 95.8% accuracy and (Random Forest (RF) + KNN + XGBoost) with 95.67% accuracy.

Vital sign monitoring during out-of-hospital pediatric advanced airway management.

ObjectiveTo evaluate physiologic monitoring in pediatric patients undergoing out‐of‐hospital advanced airway management.MethodsRetrospective case series of pediatric patients (<18 years) with advanced airways placed in the out‐of‐hospital setting. Patients given cardiopulmonary resuscitation (CPR) or defibrillation before the first advanced airway attempt were excluded. Reviewers abstracted physiologic data from the patient monitor files and patient care reports. The primary outcome was the proportion of time pulse oximetry was in place during airway management. Other outcomes included the proportion of time ECG monitoring and waveform end‐tidal capnography were in place as well as the incidence of oxygen desaturation events.ResultsWe evaluated 23 pediatric patients with a mean age of 10.7 years (SD 6.5). Eleven of 18 (61%) children with medication‐facilitated intubation had pulse oximetry in place when the first medication was documented as given. Eight of 18 (44%) had ECG monitoring, 12 of 18 (66%) had waveform capnography, and 5 of 18 (28%) had a blood pressure check within the 3 minutes before receiving the first medication. In the 3‐minute preoxygenation phase, pulse oximetry was in place for an average of 1.4 minutes (47%, SD 0.37) and a visible photoplethysmogram (PPG) waveform obtained from the pulse oximeter was present for 0.6 minutes (20%, SD 0.34). During airway device placement, pulse oximetry was in place 73% (SD 0.39) of the time and 30% (SD 0.41) of the time there was a visible PPG waveform.ConclusionsPediatric patients had critical deficits in physiologic monitoring during advanced airway management.

Diagnosis of Obstructive Sleep Apnoea in Patients Presenting with Nocturnal Pauses May Prevent the Unnecessary Insertion of Permanent Pacemakers

Introduction: Obstructive sleep apnoea (OSA) is a common medical condition with an estimated prevalence of around 7% worldwide. Patients with OSA have an increased risk of cardiovascular morbidity and mortality. Previous studies have shown a higher incidence of cardiac arrhythmias in OSA. Case Report: We report a 37-year-old male who presented with a significant syncope episode while driving a motor vehicle. His cardiac risk factors include obesity (BMI = 54.1 kg/m2), diabetes and tobacco consumption. He reported two similar syncopal episodes over the last twenty years. Transthoracic echocardiogram and baseline ECG were unremarkable for structural heart disease and conduction disorder. Twenty-four hour Holter monitor however, revealed significant nocturnal pauses lasting up to 7.56 seconds. He had a loop recorder (Medtronic Reveal LINQ LNQ 11) confirming episodes of significant nocturnal pauses which diminished after commencing CPAP for the co-diagnosis of severe sleep apnoea as part of the investigation of his symptoms. Conclusion: The use of a loop recorder has gained extensive role for discovering high degree AV block as primary cause of syncope by providing real time ECG monitoring up to 3-4 years. In this particular case, by discovering reversible organic cause of nocturnal pause, we avoid longitudinal potential side effects or complications related to PPM implant including infections, limitation in certain work activities like arc welding and the need for future surgeries related to generator replacement in an otherwise young patient.

Newly Constructed Real Time ECG Monitoring System Using LabView

This paper deals with the removal of noise and base wander in the transfer of ECG data from the patients to the doctor. The process of the project is receiving ECG signals from the patient and reading the data in PC using an Arduino (an open-source electronics prototyping platform based on flexible, easy-to-use hardware and software) board, and then the signal is subjected to the removal of noise and base wander by amplification circuits in LabView (a system design software) software. Thus obtained ECG signal is sent to the doctors using an Ethernet cable or LAN connection. This enables the doctors to monitor any number of patients more accurately by sitting in a single room.

QRS Detection Based on an Advanced Multilevel Algorithm

This paper presents an advanced multilevel algorithm used for the QRS complex detection. This method is based on three levels. The first permits the extraction of higher peaks using an adaptive thresholding technique. The second allows the QRS region detection. The last level permits the detection of Q, R and S waves. The proposed algorithm shows interesting results compared to recently published methods. The perspective of this work is the implementation of this method on an embedded system for a real time ECG monitoring system.

Cloud-ECG for real time ECG monitoring and analysis

Recent advances in mobile technology and cloud computing have inspired numerous designs of cloud-based health care services and devices. Within the cloud system, medical data can be collected and transmitted automatically to medical professionals from anywhere and feedback can be returned to patients through the network. In this article, we developed a cloud-based system for clients with mobile devices or web browsers. Specially, we aim to address the issues regarding the usefulness of the ECG data collected from patients themselves. Algorithms for ECG enhancement, ECG quality evaluation and ECG parameters extraction were implemented in the system. The system was demonstrated by a use case, in which ECG data was uploaded to the web server from a mobile phone at a certain frequency and analysis was performed in real time using the server. The system has been proven to be functional, accurate and efficient.

Droperidol: past present and future

I am pleased to see that droperidol is to reappear amongst anaesthetists’ armamentarium; its loss was deeply felt [1]. Professor Sneyd discussed its antiemetic properties but only mentioned its original use in anaesthesia as a neuroleptic agent. In about 1970 the late Dr Peter Basket introduced me to the use of droperidol at a dose of 0.25–0.3 mg.kg−1. At this dose, marked alpha blocking effects were present and 500–1000 ml of colloid was required to restore blood pressure. At this dose, presumably derived from psychiatry, droperidol had the reputation of causing the sensation of ‘invisible chains’. The patient would lie serenely smiling for 6 h or more, but later questioning would reveal that they were in terrible pain or having terrible thoughts or worries. In my own practice, I gradually reduced the dose to 2.5 mg, and at this dose I could detect no clinical difference to a plain opioid plus N2O:O2 regimen. This dose resulted in smooth anaesthesia and good postoperative conditions (including day-cases). The neuroleptic technique was to administer then titrate an opioid, initially phenoperidine and later fentanyl. Top-ups were given to maintain the respiratory rate > 8 min−1. Accidental overdose was common; rates of three breaths.min−1 were not infrequently encountered. At that time ECG monitoring was rare; my department only owned one 8-cm ‘bouncing ball’ monitor and oxygen saturation monitoring relied on skin colour. The addition of 60% nitrous oxide rendered the patient anaesthetised without recall as long as the nitrous concentration was maintained and supplementary opioid given, using respiratory rate and pulse rate as a guide and patient movement as an imperative. Neuroleptanaesthesia was revelation in comparison to the standard O2:N2O:halothane combination, with rapid patient recovery and a clear head for the anaesthetist compared with working in an atmosphere of un-scavenged volatile anaesthetics. When ECG monitoring finally became routine I never detected changes related to the use of droperidol. Neuroleptanalgesia was eventually superseded by midazolam and patient controlled propofol sedation, but I found neuroleptanaesthesia difficult to replace after droperidol was withdrawn. With the advent of proper scavenging systems, sevoflurane and total intravenous anaesthesia I could replicate, if somewhat more expensively, the peri-operative conditions of neuroleptanaesthesia. Perhaps the time of neuroleptanaesthesia has passed in the affluent world but elsewhere it may still have a place.

Multitask coronary care unit—a distributed processing approach

Automated analysis of abnormal cardiac rhythms for use in the real time ECG monitoring in intensive coronary care units (ICUs) has gained widespread recognition. As more and more tasks are being assigned to these units, the system's throughput requirements are increasing. Microprocessors with adequate computational power and intelligence have invaded the ICUs and are finding greater application. To meet the high throughput requirement, it is possible to integrate two or more microprocessors to work in parallel. One such approach as proposed and implemented is reported in this paper. The various tasks as assigned to the ICU are divided into two groups. The more basic task of continuous real time ECG monitoring is entrusted to the master processor of the master-slave configuration. The other jobs are then assigned to the slave. This approach helps to serve better the needs of the unibed coronary care. A major problem to which most researchers in this area have addressed themselves is the high rate of false positives (FPs) and false negatives (FNs) in the detection of QRS-complex of the ECG. Efforts are made here to design an algorithm for detecting QRS-complex with reduced FPs and FNs in the presence of noise and in spite of wide variations in the ECG.