Error Correction in Atrial Fibrillation Detection Using Viterbi Algorithm

Error correction in the results of atrial fibrillation (AF) detected with a convolutional neural network (CNN) classifier was investigated using the Viterbi algorithm. State transition probabilities were calculated using annotations of Holter ECG recordings obtained from 60 subjects. Errors in the detection results were corrected based on the Viterbi algorithm using the pre‐calculated state transition probabilities and the emission probabilities output by the CNN classifier. As a result, the detection results were appropriately corrected, and the detection performance was improved, demonstrating the effectiveness of the proposed method. © 2025 Institute of Electrical Engineers of Japan and Wiley Periodicals LLC.