Artificial Intelligence for Multiclass Rhythm Analysis for Out-of-Hospital Cardiac Arrest During Mechanical Cardiopulmonary Resuscitation

Load Distributing Band (LDB) mechanical chest compression (CC) device is used to treat out-of-hospital cardiac arrest (OHCA) patients. Mechanical CCs induce artifacts in the electrocardiogram (ECG) recorded by defibrillators, potentially leading to inaccurate cardiac rhythm analysis. A reliable analysis of the cardiac rhythm is essential for guiding resuscitation treatment and understanding retrospectively patients’ response to treatment. The aim of this study was to design an artificial intelligence (AI)-based framework for cardiac automatic multiclass rhythm classification in the presence of CC artifacts during OHCA. Concretely, an automatic multiclass cardiac rhythm classification is addressed to distinguish the following types of rhythms: shockable rhythms (Sh), asystole (AS) and organized rhythms (OR). A total of 15479 segments (2406 Sh, 5481 AS, 7592 OR) were extracted from 2058 patients during LDB CCs, whereof 9666 were used to train the algorithms and 5813 to assess the performance. The proposed architecture consisted of an adaptive filter for CC artifact suppression and a multiclass rhythm classifier. Three alternatives were considered for the multiclass classifier: a traditional machine learning algorithm and two deep-learning architectures based on convolutional neuronal networks and residual networks (ResNets). The unweighted mean of sensitivities, unweighted mean of bad hbox and the accuracy of the best method (ResNets) were 88.3%, 88.3% and 88.2%, respectively. These results highlight the potential of AI-based methods to provide accurate cardiac rhythm diagnoses without interrupting mechanical CC therapy.