@article{Abdul Majid Soomro_Awad Bin Naeem_Fridous Ayub_Biswaranjan Senapati_Ojas Prakashbhai Doshi_Nimra Bari_2023, title={ECG Models Predict AFib From 2012-2022: A Systematic Literature Review }, volume={4}, url={https://jcbi.org/index.php/Main/article/view/148}, abstractNote={<p>The most prevalent arrhythmia in the world is atrial fibrillation (AFib). Every year, 4.7 million individuals are diagnosed with atrial fibrillation, and it affects more than 33 million people globally. While symptoms vary by individual, the most prevalent ones are a fast heartbeat and chest discomfort. The heart rate might reach 101-175 beats per minute when atrial fibrillation develops, although the usual heart rate is 60-100 beats per minute. There are four kinds, two of which are difficult to identify using normal procedures such as an EKG (ECG). Nevertheless, as smart wearable devices have grown more commonplace, there are various techniques to identify and forecast the beginning of AF using merely ECG tests, making physicians’ diagnoses simpler. By searching several databases, this study reviewed articles published in the past decade (2012 to 2021), focusing on patients who used DL(DL) for AF prediction research. The results showed that only 23 studies were selected as systematic reviews, of which 4 applied Artificial Intelligence techniques (21%), 12 of which used DL methods (52%), and the other 7 focused on the application of the general Machine Learning Model (36%). All in all, this study shows that in the context of AI, AF prediction is still an untapped field and deep learning techniques are improving accuracy, but these applications are not as frequent as expected. In addition, since 2016, more than half of the selected studies have been published, which confirms that the topic is recent and has great potential for further research.</p>}, number={02}, journal={Journal of Computing & Biomedical Informatics}, author={Abdul Majid Soomro and Awad Bin Naeem and Fridous Ayub and Biswaranjan Senapati and Ojas Prakashbhai Doshi and Nimra Bari}, year={2023}, month={Mar.}, pages={186–203} }