A privacy-preserving logistic regression-based diagnosis scheme for digital healthcare

In recent years, with the popularity of smart wearable devices, online diagnosis is becoming a promising medical technology and therefore promotes the progress of digital healthcare. Online diagnostic services relieve computing and storage requirements of wearable devices with the help of the cloud, while facilitating remote collaboration and data sharing, providing instant access to major diagnostics that patients can obtain the diagnosis within seconds, thereby saving a lot of time and economic costs. However, the frequent occurrence of security incidents based on wireless transmission of wearable devices further exacerbates the security risks of patient health data, and therefore the security of online diagnosis based on wearable devices should be taken seriously. This paper proposes privacy-preserving logistic regression based online disease diagnosis (LR-DDH), where the privacy of the medical data can be preserved with the use of homomorphic authenticated encryption. Theoretical analysis and experimental results demonstrate that the scheme LR-DDH proposed in this paper achieves efficient computation and communication under the premise of security. (c) 2023 Elsevier B.V. All rights reserved.

Automated summary

With the popularity of smart wearable devices, online diagnosis has become a promising medical technology, promoting the progress of digital healthcare. Online diagnostic services utilize the cloud to relieve computing and storage requirements of wearable devices, enabling remote collaboration and data sharing, providing instant access to diagnostics, and saving time and costs. However, the security risks posed by wireless transmission of wearable devices highlight the need for serious consideration of the security of online diagnosis. This paper proposes privacy-preserving logistic regression based online disease diagnosis (LR-DDH), achieving efficient computation and communication while preserving the privacy of medical data.