Speaker: Miguel González Rodríguez.
Abstract:
The Physionet Challenge 2021 is presented. The goal is to classify 27 types of cardiac anomalies from electrocardiograms using convolutional neural networks (CNN). The challenge database consists of over 30,000 patient records, making it one of the largest collections of its kind in the world. The evaluation metrics used in the challenge are described, such as accuracy, sensitivity, and specificity, the top two winners of the competition are presented. Also, deep learning technology, such as CNN, and how it can be used to effectively classify cardiac anomalies, are discussed. Finally, different approaches and models used to classify cardiac anomalies are presented, sharing their preliminary results and the challenges faced when working with such a large and complex database.