Framework for Privacy-Preserving Wearable Health Data Analysis: Proof-of-Concept Study for Atrial Fibrillation Detection

Anamaria Vizitiu,Cosmin-Ioan Nita,Lucian Mihai Itu,Constantin Suciu,Tudor Suditu,Radu Miron Toev

doi:10.3390/app11199049

Anamaria Vizitiu, Cosmin-Ioan Nita + Show 4 more

Open Access

https://doi.org/10.3390/app11199049

Copy DOI

Abstract

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.

Highlights

Wearable medical devices provide remote solutions for patients to monitor their wellbeing and vital signs
To address potential privacy issues in wearable devices, we propose a cloud-based framework that relies on homomorphic encryption as a mechanism to guarantee the privacy and integrity of a person’s personal health information when wearable devices are used for remote health monitoring
The main objective of the evaluation is to assess the practical feasibility of the proposed pipeline and to determine the performance impact of using privacy-preserving analysis of wearable sensor data compared to plaintext analysis

Summary

Introduction

Wearable medical devices provide remote solutions for patients to monitor their wellbeing and vital signs. These devices are designed to capture and collect various types of health data and, in recent years, coupled with data analytics, cloud computing, and artificial intelligence, even allow for early disease detection [1]. Many popular developments are related to the cardiology field, e.g., monitoring of the heart rate, and of the electrical activity of the heart through electrocardiograms (ECG). Such heart monitors are useful in detecting signs of atrial fibrillation, the most common type of cardiac arrhythmia. An ECG can be used to detect irregularities in the heartbeat, atrial fibrillation is more difficult to trace because of the episodic nature of the symptoms

Objectives

Methods

Results

Discussion

Conclusion