Inter-patient automated arrhythmia classification: A new approach of weight capsule and sequence to sequence...

We propose a new capsule network to compensate for the information loss in the deep convolutional networks in previous studies, and to improve the performance of arrhythmia classification.

We proposed the innovative weight capsule model which uses a weight capsule network combined with sequence-to-sequence (Seq2Seq) modeling to classify arrhythmia, and explored the performance of this approach.

Based on the MIT-BIH arrhythmia database, we obtained better results compared with previous studies without data enhancement and balance for the samples. The specific performance was as follows: accuracy (ACC) = 99.85%; Class N: sensitivity (SEN) = 99.66%, positive predictive value (PPV) = 99.97%, specificity (SPEC) = 99.72%; Class S: SEN = 99.56%, PPV = 92.23%, SPEC = 99.68%; Class V: SEN = 99.97%, PPV = 99.38%, PPV = 99.96%; Class F: SEN = 93.81%, PPV = 100.00%, SPEC = 100.00%. When only half of the training sample was used, the method showed that the average accuracy and sensitivity of Class V and F were 1.57%, 2.01%, and 1.55% higher, respectively, than the traditional machine learning algorithm using the whole training sample.

Applying a weight capsule network combined with a Seq2Seq model in the field of arrhythmia not only alleviates the problem of inter-category sample imbalance effectively, but also improves the arrhythmia classification.

Our study suggests a new idea for solving the problem of small sample sizes and inter-category sample imbalance in the medical field.