Scholarlink

<p>Electronic Health Records (EHRs) face significant privacy challenges, particularly when stored and shared across distributed healthcare systems. Centralized systems are vulnerable to data breaches and internal threats. Conventional systems often lack robust encryption and secure sharing mechanisms. To address these challenges, a blockchain-based privacy framework, is proposed to ensure secure, scalable, and decentralized e-health management. A new approach known as Enhanced Recursive Quantum Graph Hash Encryption (ERQGHE) provides segment-wise encryption utilizing high-entropy keys produced by the Black-Winged Kite Optimization Algorithm (BWKOA). The key approach imitates the adaptive behavior of birds in order to stop both brute-force and statistical attacks. Besides, a quantum signature verification scheme increases data integrity by authenticating encrypted records with quantum-safe digital signatures. Encrypted EHRs are kept on an unchangeable blockchain ledger, which not only ensures secure but also clear access by the approved staff through BWKOA-based decryption. When decrypted, the records are subjected to disease diagnosis via the dual-path convolutional pyramid bluefin trevally autoencoder mutual attention network for accurate classification. For disease diagnosis, decrypted records undergo classification using the Dual Path Convolutional Pyramid Autoencoder Mutual attention Network (DPC-PAMNet), which leverages multi-resolution attention fusion to capture both global and local semantic features for accurate detection of diseases. ERQGHE achieves a low latency of 150&#xa0;ms for encryption and 130&#xa0;ms for decryption of 1000 records. Accuracy results show 96.2% on Synthea, 93.6% on heart disease, and 91.3% on Pima datasets. Through secure handling of EHRs and precise health condition classification, the approach assists physicians in timely and confident diagnosis, enhancing decision-making across decentralized healthcare infrastructures.</p>

错误：搜索内容不能为空，请输入英文关键词
错误：关键词超出字数限制，请精简
高级检索

Blockchain-Enabled Privacy-Preserving Framework for Secure Electronic Health Records Sharing and Diagnosis in Internet of Medical Things

  • 期刊论文

  • 发表日期：

    2026年2月11日

查看全文
  • S. A. Megha,
  • J. Ranjith,
  • B. V. Abhinand,
  • K. M. Veeresh,
  • V. Kiran Kumar

摘要

Electronic Health Records (EHRs) face significant privacy challenges, particularly when stored and shared across distributed healthcare systems. Centralized systems are vulnerable to data breaches and internal threats. Conventional systems often lack robust encryption and secure sharing mechanisms. To address these challenges, a blockchain-based privacy framework, is proposed to ensure secure, scalable, and decentralized e-health management. A new approach known as Enhanced Recursive Quantum Graph Hash Encryption (ERQGHE) provides segment-wise encryption utilizing high-entropy keys produced by the Black-Winged Kite Optimization Algorithm (BWKOA). The key approach imitates the adaptive behavior of birds in order to stop both brute-force and statistical attacks. Besides, a quantum signature verification scheme increases data integrity by authenticating encrypted records with quantum-safe digital signatures. Encrypted EHRs are kept on an unchangeable blockchain ledger, which not only ensures secure but also clear access by the approved staff through BWKOA-based decryption. When decrypted, the records are subjected to disease diagnosis via the dual-path convolutional pyramid bluefin trevally autoencoder mutual attention network for accurate classification. For disease diagnosis, decrypted records undergo classification using the Dual Path Convolutional Pyramid Autoencoder Mutual attention Network (DPC-PAMNet), which leverages multi-resolution attention fusion to capture both global and local semantic features for accurate detection of diseases. ERQGHE achieves a low latency of 150 ms for encryption and 130 ms for decryption of 1000 records. Accuracy results show 96.2% on Synthea, 93.6% on heart disease, and 91.3% on Pima datasets. Through secure handling of EHRs and precise health condition classification, the approach assists physicians in timely and confident diagnosis, enhancing decision-making across decentralized healthcare infrastructures.