Multi-level reversible encryption for ECG signals using compressive sensing
This addresses privacy concerns in healthcare for data sharing with semi-authorized users, but it is incremental as it builds on existing compressive sensing techniques.
The paper tackles the problem of privacy-preserving ECG data collection by proposing a multi-level reversible encryption method using compressive sensing, which reduces heartbeat anomaly classification accuracy by up to 50% while maintaining high R-peak detection accuracy.
Privacy concerns in healthcare have gained interest recently via GDPR, with a rising need for privacy-preserving data collection methods that keep personal information hidden in otherwise usable data. Sometimes data needs to be encrypted for several authentication levels, where a semi-authorized user gains access to data stripped of personal or sensitive information, while a fully-authorized user can recover the full signal. In this paper, we propose a compressive sensing based multi-level encryption to ECG signals to mask possible heartbeat anomalies from semi-authorized users, while preserving the beat structure for heart rate monitoring. Masking is performed both in time and frequency domains. Masking effectiveness is validated using 1D convolutional neural networks for heartbeat anomaly classification, while masked signal usefulness is validated comparing heartbeat detection accuracy between masked and recovered signals. The proposed multi-level encryption method can decrease classification accuracy of heartbeat anomalies by up to 50%, while maintaining a fairly high R-peak detection accuracy.