A retrained Stacked Denoising Autoencoder using blockchain achieved classification accuracies of 99.15% for ventricular ectopic beats and 98.55% for supraventricular ectopic beats.
Does retraining Stacked Denoising Autoencoders with blockchain access control improve arrhythmia classification accuracy compared to non-retrained deep networks?
A retrained deep learning architecture using blockchain for secure data access achieves high accuracy in patient-specific arrhythmia classification.
Stacked Denoising Autoencoders (SDA) are deep networks which have gained popularity owing to their superior performance in image classification applications, but they haven't been used much in healthcare applications. SDA can be efficiently retrained to adapt to large streams of data, and this property is used in this work to develop a technique for classification of arrhythmias in a patient-specific manner. This approach is particularly useful in continuous remote systems because they gather large amounts of data for longer periods of time. Blockchain is a decentralized distributed ledger which secures transactions with cryptography. It is proposed as an access control manager to securely store and access data required by the classifier during retraining in real-time from an external data storage. This work uses MIT-BIH Arrhythmia database and the results show an increased accuracy for Ventricular Ectopic Beats (VEB) (99.15%) and Supraventricular Ectopic Beats (SVEB) (98.55%), which is higher than the published results of deep networks that are not retrained.
Juneja et al. (Thu,) conducted a other in Arrhythmia. Retrained Stacked Denoising Autoencoders (SDA) with blockchain vs. Deep networks that are not retrained was evaluated on Classification accuracy for Ventricular Ectopic Beats (VEB) and Supraventricular Ectopic Beats (SVEB). A retrained Stacked Denoising Autoencoder using blockchain achieved classification accuracies of 99.15% for ventricular ectopic beats and 98.55% for supraventricular ectopic beats.