PMHE: a wearable medical sensor assisted framework for health care based on blockchain and privacy computing

Jindong Zhao, Wenshuo Wang, Dan Wang, Xu An Wang, Chunxiao MuJournal of Cloud Computing Advances Systems and Applications 2022 · DOI

Abstract

Nowadays, smart medical cloud platforms have become a new direction in the industry. However, because the medical system involves personal physiological data, user privacy in data transmission and processing is also easy to leak in the smart medical cloud platform. This paper proposed a medical data privacy preserving framework named PMHE based on blockchain and fully homomorphic encryption technology. The framework receives personal physiological data from wearable devices on the client side, and uses blockchain as data storage to ensure that the data cannot be tampered with or forged; Besides, it uses fully homomorphic encryption method to design disease prediction models implemented by smart contracts. In PMHE, data is encoded and encrypted on the client side, and encrypted data is uploaded to the cloud platform via the public Internet, preventing privacy leakage caused by channel eavesdropping; smart contracts run on the blockchain platform for disease prediction, and the operators participating in computing are encrypted user data too. So, privacy and security issues caused by platform data leakage are avoided. The client-to-cloud interaction protocol is also designed to overcome the defect that fully homomorphic encryption only supports addition and multiplication by submitting tuples on the client side, to ensure that the prediction model can perform complex computing. In addition, the design of the smart contract is introduced in detail, and the performance of the system is analyzed. Finally, experiments are conducted to verify the operating effect of the system, ensuring that user privacy is not leaked without affecting the accuracy of the model, and realizing a smart medical cloud platform in which data can be used but cannot be borrowed.

Introduction

The rapid advancement of smart healthcare relies heavily on cloud platforms to process vast amounts of data from wearable sensors for real-time disease prediction. However, this digital transformation faces a critical bottleneck: privacy. Traditional encryption methods protect data during transmission, but the data must typically be decrypted on cloud servers to be processed by AI models. This leaves sensitive physiological information vulnerable to hackers or untrusted service providers. Furthermore, centralized medical databases are often susceptible to data tampering.

The PMHE (Privacy-preserving Medical framework based on Homomorphic Encryption) framework addresses these challenges by integrating Fully Homomorphic Encryption (FHE) with blockchain technology. This combination ensures that sensitive data remains encrypted throughout its entire lifecycle—during transmission, storage, and even during computation. This approach adheres to the core principle that "data can be used but cannot be borrowed," maintaining total user privacy even if the cloud platform is compromised.

System Architecture

The PMHE architecture is designed to bridge the gap between data utility and data privacy. It consists of four primary components: smart medical devices, a client application, a cloud server, and a blockchain network.

The architecture of the PMHE system, illustrating the flow of encrypted data from wearable devices to the cloud and blockchain.

In this framework, wearable sensors collect raw medical data, which is then encoded and encrypted on the user's client application (e.g., a smartphone). This encrypted data is uploaded to the cloud and stored on a consortium blockchain (Hyperledger Fabric), ensuring data integrity and decentralization. Disease prediction models, specifically Logistic Regression, are implemented as smart contracts (Chaincode) that run directly on the blockchain platform using encrypted operators.

Privacy-Preserving Computing with FHE

At the heart of PMHE is the CKKS (Cheon-Kim-Kim-Song) homomorphic encryption scheme. Unlike standard encryption, CKKS allows mathematical operations—specifically addition and multiplication—to be performed directly on ciphertexts. When the result is eventually decrypted by the user, it matches the outcome of the same operations performed on the original plaintext data.

Conceptual diagram of privacy homomorphic encryption, showing the relationship between plaintext operations and ciphertext evaluation.

A significant challenge with FHE is its computational complexity and its limitation to basic arithmetic. Complex non-linear functions, such as the sigmoid function required for logistic regression, are difficult to compute directly in the encrypted domain. PMHE overcomes this through a unique client-to-cloud interaction protocol. When a smart contract encounters a complex operation, it sends a tuple back to the client. The client performs the specific non-linear step, re-encrypts the result, and sends it back to the cloud to continue the calculation. This hybrid approach bypasses the "level" limits of standard FHE while maintaining end-to-end security.

Experimental Evaluation and Results

The framework was evaluated using five well-known public medical datasets: Low Birth Weight Study (LBW), Heart_UCI, Umaru Impact Study (UIS), Breast-Cancer-Wisconsin (BCW), and NhanesIII. The experiments focused on accuracy, error rates, and computational overhead.

  • High Accuracy: The CKKS-encrypted AI models achieved accuracy levels nearly identical to models running on plaintext. For example, on the NhanesIII dataset, the encrypted model achieved 99.40% accuracy, compared to 99.80% for the initial plaintext model.
  • Minimal Error: While CKKS uses approximate arithmetic, the cumulative "noise" error was found to be less than 0.4%, which is insufficient to affect the binary results of disease predictions.
  • Practical Overhead: Performance analysis shows that a modern smartphone can handle the encoding and encryption of 20 physiological features in less than 0.03 seconds. At a high frequency of one data upload per minute, the system requires a network speed of roughly 175kbps, making it highly viable for real-time wearable integration.

Conclusion

PMHE demonstrates a robust path forward for secure, smart healthcare. By leveraging the strengths of FHE for privacy and blockchain for integrity, the framework allows for sophisticated medical analysis without exposing sensitive user data. Future work will focus on scaling the system for massive deployments and optimizing the CKKS algorithm to support more complex deep learning architectures efficiently.

Summary updated

Abstract

Abstract Nowadays, smart medical cloud platforms have become a new direction in the industry. However, because the medical system involves personal physiological data, user privacy in data transmission and processing is also easy to leak in the smart medical cloud platform. This paper proposed a medical data privacy preserving framework named PMHE based on blockchain and fully homomorphic encryption technology. The framework receives personal physiological data from wearable devices on the client side, and uses blockchain as data storage to ensure that the data cannot be tampered with or forged; Besides, it uses fully homomorphic encryption method to design disease prediction models implemented by smart contracts. In PMHE, data is encoded and encrypted on the client side, and encrypted data is uploaded to the cloud platform via the public Internet, preventing privacy leakage caused by channel eavesdropping; smart contracts run on the blockchain platform for disease prediction, and the operators participating in computing are encrypted user data too. So, privacy and security issues caused by platform data leakage are avoided. The client-to-cloud interaction protocol is also designed to overcome the defect that fully homomorphic encryption only supports addition and multiplication by submitting tuples on the client side, to ensure that the prediction model can perform complex computing. In addition, the design of the smart contract is introduced in detail, and the performance of the system is analyzed. Finally, experiments are conducted to verify the operating effect of the system, ensuring that user privacy is not leaked without affecting the accuracy of the model, and realizing a smart medical cloud platform in which data can be used but cannot be borrowed.
BibTeX
@article{zhao2022pmhe,
  author = {Jindong Zhao and Wenshuo Wang and Dan Wang and Xu An Wang and Chunxiao Mu},
  title = {{PMHE: a wearable medical sensor assisted framework for health care based on blockchain and privacy computing}},
  journal = {Journal of Cloud Computing Advances Systems and Applications},
  year = {2022},
  doi = {10.1186/s13677-022-00373-8},
}
Figure