Scholarlink

<p>In the present scenario, Security breaches, inadequate organ matching, and ethical issues like organ trafficking are just some of the problems that previous studies have shown to be present in centralized organ donation systems. Critical, vital decisions in organ transplantation are impacted by a lack of trustworthy and transparent processes. In this paper, Artificial Intelligence (AI)-powered federated learning method that incorporates blockchain technology and Electronic Health Records (EHR). Federated learning enables model training without centralized data storage, which maintains privacy, while artificial intelligence improves the accuracy and speed of donor-recipient matching by employing full medical data from EHRs. With the help of AI, donor-recipient matching becomes more precise and efficient, and federated learning ensures data privacy by enabling collaborative model training without requiring centralized data storage. The combination of this framework with blockchain technology creates an ethical, transparent, and decentralized approach to handle private data about organ donations. To further improve matching accuracy and decrease waiting periods, EHRs incorporate personalized, real-time updates on the health status of the recipients and the donors. This research suggests blockchain technology with AI-driven federated learning (BCT-AI-FL) to address these problems. Artificial intelligence algorithms enhance the accuracy of organ matching and allocation, while federated learning allows local data processing across many healthcare facilities, preserving privacy. With smart contracts, blockchain technology automates crucial procedures like organ allocation in accordance with ethical standards, reducing off administrative delays and human error. This further ensures privacy and transparency. As a consequence of blockchain's public and auditable records, donor-recipient matching accuracy, efficiency, security, and trust have&#xa0;shown significant improvements, according to preliminary research. The proposed method achieves better accuracy, efficiency, security, and trust when compared to existing methods.</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

AI empowered federated learning approach with blockchain for secure and transparent EHR based organ donation network

  • 期刊论文

  • 发表日期：

    2025年11月20日

查看全文
  • Divyashree Duggegowda,
  • Umadevi Ramamoorthy

摘要

In the present scenario, Security breaches, inadequate organ matching, and ethical issues like organ trafficking are just some of the problems that previous studies have shown to be present in centralized organ donation systems. Critical, vital decisions in organ transplantation are impacted by a lack of trustworthy and transparent processes. In this paper, Artificial Intelligence (AI)-powered federated learning method that incorporates blockchain technology and Electronic Health Records (EHR). Federated learning enables model training without centralized data storage, which maintains privacy, while artificial intelligence improves the accuracy and speed of donor-recipient matching by employing full medical data from EHRs. With the help of AI, donor-recipient matching becomes more precise and efficient, and federated learning ensures data privacy by enabling collaborative model training without requiring centralized data storage. The combination of this framework with blockchain technology creates an ethical, transparent, and decentralized approach to handle private data about organ donations. To further improve matching accuracy and decrease waiting periods, EHRs incorporate personalized, real-time updates on the health status of the recipients and the donors. This research suggests blockchain technology with AI-driven federated learning (BCT-AI-FL) to address these problems. Artificial intelligence algorithms enhance the accuracy of organ matching and allocation, while federated learning allows local data processing across many healthcare facilities, preserving privacy. With smart contracts, blockchain technology automates crucial procedures like organ allocation in accordance with ethical standards, reducing off administrative delays and human error. This further ensures privacy and transparency. As a consequence of blockchain's public and auditable records, donor-recipient matching accuracy, efficiency, security, and trust have shown significant improvements, according to preliminary research. The proposed method achieves better accuracy, efficiency, security, and trust when compared to existing methods.