Accelerometry-based classification of circulatory states during out-of-hospital cardiac arrest

Objective: During cardiac arrest treatment, a reliable detection of spontaneous circulation, usually performed by manual pulse checks, is both vital for patient survival and practically challenging. Methods: We developed a machine learning algorithm to automatically predict the circulatory state during cardiac arrest treatment from 4-second-long snippets of accelerometry and electrocardiogram data from real-world defibrillator records. The algorithm was trained based on 917 cases from the German Resuscitation Registry, for which ground truth labels were created by a manual annotation of physicians. It uses a kernelized Support Vector Machine classifier based on 14 features, which partially reflect the correlation between accelerometry and electrocardiogram data. Results: On a test data set, the proposed algorithm exhibits an accuracy of 94.4 (93.6, 95.2)%, a sensitivity of 95.0 (93.9, 96.1)%, and a specificity of 93.9 (92.7, 95.1)%. Conclusion and significance: In application, the algorithm may be used to simplify retrospective annotation for quality management and, moreover, to support clinicians to assess circulatory state during cardiac arrest treatment.