China
Africa
Explore chapters and articles related to this topic
Diseases Prediction and Diagnosis System for Healthcare Using IoT and Machine Learning
Published in Meenu Gupta, Gopal Chaudhary, Victor Hugo C. de Albuquerque, Smart Healthcare Monitoring Using IoT with 5G, 2021
Shweta Agarwal, Chander Prabha
Several causes of arrhythmia are there, such as irregular heartbeat, blood potassium or sodium deficiency, heart muscle changes, various coronary disorder, post-operative healing processes, etc. Irregular ECG is crucial in arrhythmia prediction. If not diagnosed, then the sudden condition can cause cardiac arrest [56]. Supraventricular tachycardia, atrial fibrillation, atrial flutter, and ventricular tachycardia are the ECG-based classifications for retrospective data analysis of resuscitation cardiac rhythms [57]. An automatic arrhythmia categorization will save many patients lives [58]. A random forest classifier is intended for the diagnosis of arrhythmias in 16 types [59]. The efficiency of the classifier may be affected by excessive datasets and several feature choices. To overcome this problem, SRS (simple random sampling) and CFS (correlation-based feature selection) classification methods are used. CFS filtering method [60] conducts the most suitable feature selection, and the data collection is re-sampled by SRS to obtain a uniformly distributed class data set. This work employs ML method for classifying the arrhythmia data set is used in this work to create a real-time arrhythmia monitoring system using sensors and IoT devices.
Cardiovascular system
Published in A Stewart Whitley, Jan Dodgeon, Angela Meadows, Jane Cullingworth, Ken Holmes, Marcus Jackson, Graham Hoadley, Randeep Kumar Kulshrestha, Clark’s Procedures in Diagnostic Imaging: A System-Based Approach, 2020
A Stewart Whitley, Jan Dodgeon, Angela Meadows, Jane Cullingworth, Ken Holmes, Marcus Jackson, Graham Hoadley, Randeep Kumar Kulshrestha
Some patients suffer from ‘palpitations’. These are, in fact, cardiac arrhythmias. Some examples of these are atrial flutter, atrial fibrillation and supraventricular tachycardia. To treat these, the cardiologists places electrodes within the heart and ‘burns’ away the errant pathway using a radiofrequency generator. These electrodes (known as catheters) are introduced through the femoral vein and guided under fluoroscopic control into appropriate positions. The most common projections are 45° RAO and 40° LAO. Some centres use bi-plane equipment to enable speedy changes of view. Occasionally, in order to allow high ablation power to be used, the catheter tip is cooled during burning by passing room temperature saline through it. The procedure is terminated when the arrhythmia has ceased.
The Promise of Artificial Intelligence and Machine Learning
Published in Paul Cerrato, John Halamka, Reinventing Clinical Decision Support, 2020
Differences in the risk criteria recommended in the current screening guidelines and the risk criteria used to create the deep learning algorithms explain why the ML approach was so much more effective. Currently, clinicians are advised to consider a diagnosis of FH if LDL-cholesterol levels rise above 190 mg/dl and the patient has a family history of early-onset atherosclerotic disease. But in light of the fact that less than 5% of adults with LDL levels above 190 actually have the mutation causing FH, and the fact that an adequate family history is very often lacking, these criteria are not very helpful. The algorithm designed by Banda et al.33 mined patients’ structured and unstructured EHR data to extract a long list of relevant variables, including lab tests, text mention, diagnosis codes, and medication prescriptions. For instance, among the top 20 features were a prescription for atorvastatin, ezetimibe, rosuvastatin, metoprolol, or rosuvastatin; mention of red meat; triglycerides; a visit to a cardiology clinic; the word high as a describer for cholesterol value in serum or plasma; very high triglycerides in serum or plasma; “other and unspecified hyperlipidemia”; or “a diagnosis code of paroxysmal supraventricular tachycardia” in structured data.
A review of arrhythmia detection based on electrocardiogram with artificial intelligence
Published in Expert Review of Medical Devices, 2022
Jinlei Liu, Zhiyuan Li, Yanrui Jin, Yunqing Liu, Chengliang Liu, Liqun Zhao, Xiaojun Chen
According to the American Heart Association statistics, cardiovascular diseases (CVDs) have become the primary cause of death in the world [1]. Due to irregular and unhealthy lifestyles, patients with CVDs tend to become younger. The early symptoms of most CVDs are irregular heartbeats, also known as arrhythmia. Arrhythmia is generated by the disordered electrical activity of the heart, and some arrhythmia such as ventricular tachycardia (VT) and ventricular fibrillation (VF) can be life-threatening [2]. In addition, atrial fibrillation (AF), atrial flutter (AFL), premature ventricular contraction (PVC), premature atrial contraction (PAC), paroxysmal supraventricular tachycardia (PSVT), and bradycardia are also common types of arrhythmia [3]. Therefore, rapid detection and accurate diagnosis of cardiac arrhythmia are particularly essential.
Subcutaneous cardiac rhythm monitors: state of the art review
Published in Expert Review of Medical Devices, 2021
Anish Nadkarni, Jasneet Devgun, Shakeel M. Jamal, Delores Bardales, Julie Mease, Faisal Matto, Toshimasa Okabe, Emile G. Daoud, Muhammad R. Afzal
Overall, the programming characteristics of various SCRMs are similar with minor exceptions. Every SCRM allows the programmer to adjust, tachycardia threshold, bradycardia threshold, minimum duration of episode (for both tachy and brady), pause duration and AT/AF detection. Additionally, they all have a parameter to adjust the sensitivity of AF detection to some sort of low, medium, or high sensitivity setting. LINQ IITM and BioMonitor IIITM have ectopy rejection parameters via detection of short then long R-R intervals. This can be turned ‘on’ or ‘off’ based on the indication for SCRM placement. For tachycardia, LINQ IITM and Confirm also have a programmable ‘sudden onset’ feature which can be turned on or off. Supraventricular tachycardia and ventricular tachycardia usually are abrupt onset tachyarrhythmias while sinus tachycardia tends to be slower onset. LINQ II and Confirm RxTM implement this ‘sudden onset’ feature to distinguish between the two. Confirm RxTM also has an additional parameter called ‘Delta Onset’ where the degree of sudden onset needed for a detection can be programmed.
Fire service instructors' working practices: A UK survey
Published in Archives of Environmental & Occupational Health, 2019
Emily R. Watkins, Mark Hayes, Peter Watt, Alan J. Richardson
FSI also reported experiencing heart palpitations, which although usually benign, can be caused by arrhythmias, which include supraventricular tachycardia, ventricular extrasystoles, or atrial fibrillation.49,50 Suffering from an arrhythmia can increase the risk of sudden cardiac death (relative risk 3.2, 95% CI 2.0–5.3).49 Atrial fibrillation is also a predictor of cardiovascular events (rate ratio 1.8, 95% CI 1.3–2.5), with 66% of men with atrial fibrillation experiencing an event over a 20 year period, compared to 45% of asymptomatic men.51 The possibly life threatening consequences of sleep deprivation and heart palpitations reported by FSI suggest that further investigation into the health of FSI is warranted, with determining methods and guidelines to reduce the incidence of these new symptoms of paramount importance.