scholarly journals Analyzing artificial intelligence systems for the prediction of atrial fibrillation from sinus-rhythm ECGs including demographics and feature visualization

2021 ◽  
Vol 11 (1) ◽  
Author(s):  
Pietro Melzi ◽  
Ruben Tolosana ◽  
Alberto Cecconi ◽  
Ancor Sanz-Garcia ◽  
Guillermo J. Ortega ◽  
...  
Keyword(s):  
Atrial Fibrillation ◽  
Sinus Rhythm ◽  
Normal Sinus Rhythm ◽  
Area Under The Curve ◽  
Heart Rhythm ◽  
Demographic Groups ◽  
Ecg Signals ◽  
Normal Sinus ◽  
Visualization Techniques ◽  
Feature Visualization

AbstractAtrial fibrillation (AF) is an abnormal heart rhythm, asymptomatic in many cases, that causes several health problems and mortality in population. This retrospective study evaluates the ability of different AI-based models to predict future episodes of AF from electrocardiograms (ECGs) recorded during normal sinus rhythm. Patients are divided into two classes according to AF occurrence or sinus rhythm permanence along their several ECGs registry. In the constrained scenario of balancing the age distributions between classes, our best AI model predicts future episodes of AF with area under the curve (AUC) 0.79 (0.72–0.86). Multiple scenarios and age-sex-specific groups of patients are considered, achieving best performance of prediction for males older than 70 years. These results point out the importance of considering different demographic groups in the analysis of AF prediction, showing considerable performance gaps among them. In addition to the demographic analysis, we apply feature visualization techniques to identify the most important portions of the ECG signals in the task of AF prediction, improving this way the interpretability and understanding of the AI models. These results and the simplicity of recording ECGs during check-ups add feasibility to clinical applications of AI-based models.

Detection of Atrial Fibrillation and Normal Sinus Rhythm Using Multiple Machine Learning Classifiers

2021 ◽  
Vol 11 (5) ◽  
pp. 1453-1462
Author(s):  
Fiaz Majeed ◽  
Muhammad Asim ◽  
Syed Ali Abbas ◽  
Abdul Jaleel ◽  
Abdul Majid ◽  
...  
Keyword(s):  
Atrial Fibrillation ◽  
Sinus Rhythm ◽  
Predictive Value ◽  
Normal Sinus Rhythm ◽  
Area Under The Curve ◽  
High Ratio ◽  
Classification Model ◽  
False Alarms ◽  
Normal Sinus ◽  
Statistical Measures

In this era of eHealth, healthcare data has gained a significant importance due to having human survival information. Detection of the atrial fibrillation (AF) from electrocardiogram (ECG) rhythm is a promising area of research because of its critical impact on mortality ratio in all over the world. Although, most of the studies have shown more than 90% results accuracy in terms of specificity (Sp) and sensitivity (Se), yet this accuracy is not sufficient and cannot be considered reliable for AF continuous monitoring due to high ratio of false alarms. Existing works scarcely compare the accuracy of the results generated by a classifier with those of other robust classifiers. Further, the results are needed to be verified with more statistical measures. In this paper, a multiple classifiers-based model is proposed in which the transition between normal sinus rhythm (NSR) and AF are performed on the basis of ventricle activities of the heart. The proposed scheme first extracts several features that are pertinent to AF diagnosis from the ECG data. Later, the classification model categorizes rhythms into classes using statistical techniques. The experimental evaluation is performed on five datasets which include AF Challenge 2017 database, NSR database (NSRDB), NSR RR interval database (NSRDB-2), AF database (AFDB) and long-term AF database (LTAFDB). Based on verification of results using different measures, the proposed scheme outperforms in comparison to the existing systems in terms of area under the curve (AUC), Se, Sp, positive predictive value (PPV), accuracy (ACC), and negative predictive value (NPV) for all datasets. Specifically, the decision tree (DT) obtains 99% AUC, 92% Se and 98% Sp for the AF Challenge 2017 database, which are improved than parallel systems.

Classification of Paroxysmal Atrial Fibrillation using Second Order System

2014 ◽  
Vol 67 (3) ◽  
Author(s):  
Nurul Ashikin Abdul-Kadir ◽  
Norlaili Mat Safri ◽  
Mohd Afzan Othman
Keyword(s):  
Atrial Fibrillation ◽  
Sinus Rhythm ◽  
Normal Sinus Rhythm ◽  
Atrial Fibrillation Patient ◽  
Heart Rhythm ◽  
Second Order ◽  
Order System ◽  
Normal Sinus ◽  
Specificity And Sensitivity ◽  
Significant Difference

In this paper, we monitored and analyzed the characteristics of atrial fibrillation in patient using second order approach. Atrial fibrillation is a type of atria arrhythmias, disturbing the normal heart rhythm between the atria and lower ventricles of the heart. Heart disease and hypertension increase risk of stroke from atrial fibrillation. This study used electrocardiogram (ECG) signals from Physiobank, namely MIT-BIH Atrial Fibrillation Dataset and MIT-BIH Normal Sinus Rhythm Dataset. In total, 865 episodes for each type of ECG signal were classified, specifically normal sinus rhythm (NSR) of human without arrhythmia, normal sinus rhythm of atrial fibrillation patient (N) and atrial fibrillation (AF). Extracted parameters (forcing input, natural frequency and damping coefficient) from second order system were characterized and analyzed. Their ratios, time derivatives, and differential derivatives were also observed. Altogether, 12 parameters were extracted and analysed from the approach. The results show significant difference between the three ECGs of forcing input, and derivative of forcing input. Overall system performance gives specificity and sensitivity of 84.9 % and 85.5 %, respectively.

scholarly journals Holter monitoring for assessment of possible paroxysmal atrial fibrillation as a cause in otherwise normal sinus rhythm patients with acute ischemic stroke: a hospital based study

2021 ◽  
Vol 10 (2) ◽  
pp. 63-66
Author(s):  
Navaraj Paudel ◽  
Namrata Thapa ◽  
Ramchandra Kafle ◽  
Subash Sapkota ◽  
Abhishek Maskey
Keyword(s):  
Risk Factors ◽  
Atrial Fibrillation ◽  
Sinus Rhythm ◽  
Paroxysmal Atrial Fibrillation ◽  
Normal Sinus Rhythm ◽  
Heart Rhythm ◽  
Female Ratio ◽  
Mortality And Morbidity ◽  
Cerebrovascular Accidents ◽  
Normal Sinus

Background: Stroke/ cerebrovascular accidents are common and among the major causes of mortality and morbidity. Thromboembolism are also among the causes of ischemic strokes. Diagnosis of atrial fibrillation makes the difference in the management of ischemic strokes for long term as anticoagulation are given in these cases for prevention of further embolic events. Methods: A prospective observational study was done from july 2019 to june 2021 for patients admitted for ischemic strokes who were otherwise found to have normal sinus rhythm. A 24 hour holter monitor was connected and analyzed for possible paroxysmal atrial fibrillation. Baseline investigations including trans-thoracic echocardiography was done. Data were analyzed and results were sought. Results: Out of 212 patients admitted for stroke, only 116 were eligible for the study. Male female ratio was 2:1. Ninety-four percent of patients had at least one or more risk factors: Smokers (74%) followed by Hypertensives (70%), Dyslipidemics (54%) and Diabetics (20%). Twenty-two percent of patients were found to have paroxysmal atrial fibrillation. There was no gender difference between the occurrences of paroxysmal atrial fibrillation. Among the risk factors, smoking and hypertension were significantly associated with the occurrence of paroxysmal atrial fibrillation (P: 0.001 and 0.002 respectively) while other risk factors like diabetes and dyslipidemia had no significant association. There was significant association of paroxysmal atrial fibrillation with mortality (P: 0.0013). Conclusion: Patients who are in otherwise normal sinus rhythm in electrocardiography with ischemic cerebrovascular accidents may have paroxysmal atrial fibrillation as cause of event. Smoking and hypertensive patients are significantly associated with occurrence of paroxysmal atrial fibrillation and stroke and these patients are more likely to die than the patients having normal heart rhythm. Management of these patients definitely defer in terms of possible use of anticoagulants. 

scholarly journals An Atrial Fibrillation with Normal Limits using Signal Processing- A Review

2018 ◽  
Vol 7 (2.24) ◽  
pp. 453
Author(s):  
S. Sathish ◽  
K Mohanasundaram
Keyword(s):  
Atrial Fibrillation ◽  
Sinus Rhythm ◽  
Normal Sinus Rhythm ◽  
P Wave ◽  
Wave Duration ◽  
Normal Limits ◽  
Normal Sinus ◽  
P Wave Duration ◽  
Standard Lead ◽  
Wave Morphology

Atrial fibrillation is an irregular heartbeat (arrhythmia) that can lead to the stroke, blood clots, heart failure and other heart related complications. This causes the symptoms like rapid and irregular heartbeat, fluttering, shortness of breath etc. In India for every around 4000 people eight of them are suffering from Atrial Fibrillation. P-wave Morphology.  Abnormality of P-wave (Atrial ECG components) seen during sinus rhythm are associated with Atrial fibrillation. P-wave duration is the best predictor of preoperative atrial fibrillation. but the small amplitudes of atrial ECG and its gradual increase from isometric line create difficulties in defining the onset of P wave in the Standard Lead Limb system (SLL).Studies shows that prolonged P-wave have duration in patients (PAF) In this Study, a Modified Lead Limb (MLL) which solves the practical difficulties in analyzing the P-ta interval for both in healthy subjects and Atrial Fibrillation patients. P-Ta wave interval and P-wave duration can be estimated with following proposed steps which is applicable for both filtered and unfiltered atrial ECG components which follows as the clinical database trials. For the same the p-wave fibrillated signals that escalates the diagnosis follows by providing minimal energy to recurrent into a normal sinus rhythm.  

Sign in / Sign up

Export Citation Format

Share Document