Eine Plattform für die Wissenschaft: Bauingenieurwesen, Architektur und Urbanistik
Eine Plattform für die Wissenschaft: Bauingenieurwesen, Architektur und Urbanistik
A Holistic Overview of Artificial Intelligence in Detection, Classification and Prediction of Atrial Fibrillation Using Electrocardiogram: A Systematic Review and Meta-analysis
Abstract Atrial Fibrillation (AF) is the most studied cardiac arrhythmias due to its increasing prevalence in today’s scenario. Application of Artificial Intelligence (AI) for early identification of AF and classification has been thoroughly scrutinized. This review aims to determine the performance of machine and deep learning models applied for AF detection, classification and prediction through systematic review and meta-analysis. PubMed, IEEE Xplore, science direct and google scholar were searched for the relevant articles for review based on the search strategy framed. Detection, classification and prediction of AF performed using a 12-lead Electrocardiogram (ECG) recording were studied for systematic review. Bivariate hierarchical random effects method for meta-analysis of diagnostic tests accuracies using Stata 17 was performed, and Hierarchical Summary Receiver Operating Characteristic (HSROC) curve was plotted. Further, Meta-DiSc 1.4 software was used for pooling sensitivity and specificity. The pooled sensitivity of 0.98 (95% C.I. 0.98–0.99) and specificity of 0.98 (95% C.I. 0.97–0.99) was achieved for detecting AF. Classification gave pooled sensitivity of 0.98 (95% C.I. 0.96–0.99) and specificity 0.99 (95% C.I. 0.98–0.99). Correlation between logit Sensitivity and logit Specificity for detection and classification were 0.05 and 0.13, respectively. However, information in prediction articles was limited to perform meta-analysis. Convolutional neural network gave the best accuracy output in detecting AF; and Support Vector Machine in classification followed by neural network. Prediction of AF in its early stages has the scope for AI in future along with devising new processing techniques for utilizing f waves as a potent feature.
A Holistic Overview of Artificial Intelligence in Detection, Classification and Prediction of Atrial Fibrillation Using Electrocardiogram: A Systematic Review and Meta-analysis
Abstract Atrial Fibrillation (AF) is the most studied cardiac arrhythmias due to its increasing prevalence in today’s scenario. Application of Artificial Intelligence (AI) for early identification of AF and classification has been thoroughly scrutinized. This review aims to determine the performance of machine and deep learning models applied for AF detection, classification and prediction through systematic review and meta-analysis. PubMed, IEEE Xplore, science direct and google scholar were searched for the relevant articles for review based on the search strategy framed. Detection, classification and prediction of AF performed using a 12-lead Electrocardiogram (ECG) recording were studied for systematic review. Bivariate hierarchical random effects method for meta-analysis of diagnostic tests accuracies using Stata 17 was performed, and Hierarchical Summary Receiver Operating Characteristic (HSROC) curve was plotted. Further, Meta-DiSc 1.4 software was used for pooling sensitivity and specificity. The pooled sensitivity of 0.98 (95% C.I. 0.98–0.99) and specificity of 0.98 (95% C.I. 0.97–0.99) was achieved for detecting AF. Classification gave pooled sensitivity of 0.98 (95% C.I. 0.96–0.99) and specificity 0.99 (95% C.I. 0.98–0.99). Correlation between logit Sensitivity and logit Specificity for detection and classification were 0.05 and 0.13, respectively. However, information in prediction articles was limited to perform meta-analysis. Convolutional neural network gave the best accuracy output in detecting AF; and Support Vector Machine in classification followed by neural network. Prediction of AF in its early stages has the scope for AI in future along with devising new processing techniques for utilizing f waves as a potent feature.
A Holistic Overview of Artificial Intelligence in Detection, Classification and Prediction of Atrial Fibrillation Using Electrocardiogram: A Systematic Review and Meta-analysis
Bhardwaj, Arya (Autor:in) / Budaraju, Dhananjay (Autor:in) / Venkatesh, Prasanna (Autor:in) / Chowdhury, Dibya (Autor:in) / Kumar, R. Pradeep (Autor:in) / Pal, Kunal (Autor:in) / Sivaraman, J. (Autor:in) / Neelapu, Bala Chakravarthy (Autor:in)
2023
Aufsatz (Zeitschrift)
Elektronische Ressource
Englisch
| Elsevier | 2025
Food Adulteration Detection using Artificial Intelligence: A Systematic Review
| Online Contents | 2021
Neuroimage analysis using artificial intelligence approaches: a systematic review
| Springer Verlag | 2024
Artificial intelligence techniques for pavement performance prediction: a systematic review
| Taylor & Francis Verlag | 2025