Recent surveys suggest that the majority of the world's population is unconcerned with their health. Aside from a hectic lifestyle, research reveals that stress is also a component in the development of many diseases. Sudden cardiac arrest and death (SCD) is a major public health concern that jeopardizes patient safety. As a result, detecting such illnesses only by ECG is difficult. The Bayesian Dirichlet equivalence score, AIC (akaike information criterion), and MDL (maximum description length) scores make up the variable-order Bayesian network (VOBN). On the basis of HRV (heart rate variability) acquired from ECG and using a hybrid classifier to identify SCD patients from normal patients, this study predicts sudden cardiac arrest before it occurs within 30 minutes. The validity of the suggested study is checked using the physionet database of cardiac patients and normal people, as well as the Cleveland dataset. The proposed method achieves 97.1% accuracy, 96.2% precision, 89.8% recall, 84.82% F1-score, 54.66% AUC, and 45.92% ROC, according to the results.
TopIntroduction
Heart failure (HF) has become a major public health issue in both Asia and the West, with an increasing prevalence. In Asia, the prevalence of heart failure ranges from 1.2 percent to 6.7 percent, depending on the population. HF with a low ejection fraction is a frequent disease with a bad prognosis. It’s still difficult to accurately identify people with ischemic heart disease as well as idiopathic dilated cardiomyopathy who are at risk of SCD (sudden cardiac death). Current suggestions for ICD (implantable cardioverter-defibrillators) in these circumstances are nearly completely based on LVEF (left ventricular ejection fraction). This constraint is insufficient. Using myocardial deformation on echocardiography and MRI, noninvasive imaging has recently given insight into the process behind SCD (Kammoun et al., 2021). However, the function of these biomarkers in predicting arrhythmic mortality has not been studied in isolation.
The goal of this study is to see if biomarkers CT-proET-1, MR-proANP, and MR-proADM are linked to an elevated risk of arrhythmic death as well as all-cause mortality in HFrEF patients with ischemic and non-ischaemic dilated cardiomyopathy. Despite advancements in the survival rate of AMI (acute myocardial infarction), AMI-related OHCA (out-of-hospital cardiac arrest) remains a fatal condition.TIMI(Thrombolysis in myocardial infarction) evaluation is utilized to categorize coronary reperfusion following PCI (percutaneous coronary intervention), although it's uncertain if TIMI evaluation after emergent PCI is linked to short-term mortality in patients with AMI who had OHCA (Otaki et al., 2021).
SCD should be identified as the major endpoint whenever possible, even though determining the cause of death is not always straightforward. The so-called “grey zone fibrosis” mass, which is defined as the standard deviation from maximum signal intensity LGE, has recently been found to be more significantly related to SCD and VAs than LVEF (Zegard et al., 2021).
Figure 1. Generalized steps in machine learning
Figure 1 depicts steps involved in developing a predictive model utilizing machine learning which consists of raw data s input, machine learning process as processing unit, and model as output There are other machine learning algorithms available; however, logistic regression is the most basic type of machine learning method that we are familiar with. However, its inability to analyze data like a machine learning technique may limit its use in big data and difficult data analysis. There are 3 ML techniques such as supervised, unsupervised, and reinforcement learning.
The most common causes of arrhythmic SCD are ischemic heart disease and non-ischemic dilated cardiomyopathy. Antiarrhythmic medications' role is restricted to symptom alleviation, while ICD therapy is the only method that helps avoid SCD in high-risk individuals. Current guidelines propose choosing ICD candidates based on aetiology, heart failure symptoms, and a profoundly decreased LVEF, although these criteria are neither sensitive nor specific. The review looks at mechanisms of SCD in patients with ischemia or non-ischemic HF, as well as risk assessment and preventative measures in clinical practice (Corrado et al., 2020).
Several multivariate prognostic methods for chronic HF patients are proposed in the recent decade. These models, on the other hand, are ineffective at identifying ICD candidates with a high risk of SCD in HF patients with poor LVEF. The majority of the prognosis scores shown above were derived from trial databases and individuals included diverse kinds of heart failure. There is no specific research on the prognosis of people with poor LVEF. Moreover, despite the fact that all of the scores are “not parsimonious,” some critical factors are left out of prognostic methods, such as medications, which are included in the I-PRESERVE, MAGGIC, and CC-HF.
Examine whether patients in our study waited too long to call 911. During the early pandemic period, the author found a sharp countrywide drop in hospital-treated acute coronary disease, possibly representing that fewer people are seeking care for cardiac symptoms (Solomon et al., 2020).