A privacy-preserving machine learning framework using homomorphically encrypted ECG data achieved atrial fibrillation detection performance similar to state-of-the-art plaintext models.
Does a privacy-preserving machine learning framework using homomorphically encrypted data accurately detect atrial fibrillation from wearable ECGs compared to plaintext data?
A novel privacy-preserving machine learning framework using homomorphically encrypted data can detect atrial fibrillation from wearable ECGs with performance comparable to standard plaintext methods.
Medical wearable devices monitor health data and, coupled with data analytics, cloud computing, and artificial intelligence (AI), enable early detection of disease. Privacy issues arise when personal health information is sent or processed outside the device. We propose a framework that ensures the privacy and integrity of personal medical data while performing AI-based homomorphically encrypted data analytics in the cloud. The main contributions are: (i) a privacy-preserving cloud-based machine learning framework for wearable devices, (ii) CipherML—a library for fast implementation and deployment of deep learning-based solutions on homomorphically encrypted data, and (iii) a proof-of-concept study for atrial fibrillation (AF) detection from electrocardiograms recorded on a wearable device. In the context of AF detection, two approaches are considered: a multi-layer perceptron (MLP) which receives as input the ECG features computed and encrypted on the wearable device, and an end-to-end deep convolutional neural network (1D-CNN), which receives as input the encrypted raw ECG data. The CNN model achieves a lower mean F1-score than the hand-crafted feature-based model. This illustrates the benefit of hand-crafted features over deep convolutional neural networks, especially in a setting with a small training data. Compared to state-of-the-art results, the two privacy-preserving approaches lead, with reasonable computational overhead, to slightly lower, but still similar results: the small performance drop is caused by limitations related to the use of homomorphically encrypted data instead of plaintext data. The findings highlight the potential of the proposed framework to enhance the functionality of wearables through privacy-preserving AI, by providing, within a reasonable amount of time, results equivalent to those achieved without privacy enhancing mechanisms. While the chosen homomorphic encryption scheme prioritizes performance and utility, certain security shortcomings remain open for future development.
Vizitiu et al. (Tue,) conducted a other in Atrial Fibrillation. Privacy-preserving machine learning framework (CipherML) vs. State-of-the-art plaintext models was evaluated on Atrial fibrillation detection (mean F1-score). A privacy-preserving machine learning framework using homomorphically encrypted ECG data achieved atrial fibrillation detection performance similar to state-of-the-art plaintext models.