Ensuring the security and usability of electronic health records (EHRs) is important in health information exchange (HIE) systems that handle healthcare records. This study addressed the need to balance privacy preserving and data usability in blockchain-based HIE systems. We propose a searchable blockchain-based HIE system that enhances privacy preserving while improving data usability. The proposed methodology includes users collecting healthcare information (HI) from various Internet of Medical Things (IoMT) devices and compiling this information into EHR blocks for sharing on a blockchain network. This approach allows participants to search and utilize specific health data within the blockchain effectively. The results demonstrate that the proposed system mitigates the issues of traditional HIE systems by providing secure and user-friendly access to EHRs. The proposed searchable blockchain-based HIE system resolves the trade-off dilemma in HIE by achieving a balance between security and the data usability of EHRs.

Recently, cybercrimes that exploit the anonymity of blockchain are increasing. They steal blockchain users’ assets, threaten the network’s reliability, and destabilize the blockchain network. Therefore, it is necessary to detect blockchain cybercriminal accounts to protect users’ assets and sustain the blockchain ecosystem. Many studies have been conducted to detect cybercriminal accounts in the blockchain network. They represented blockchain transaction records as homogeneous transaction graphs that have a multi-edge. They also adopted graph learning algorithms to analyze transaction graphs. However, most graph learning algorithms are not efficient in multi-edge graphs, and homogeneous graphs ignore the heterogeneity of the blockchain network. In this paper, we propose a novel heterogeneous graph structure called an account-transaction graph, ATGraph. ATGraph represents a multi-edge as single edges by considering transactions as nodes. It allows graph learning more efficiently by eliminating multi-edges. Moreover, we compare the performance of ATGraph with homogeneous transaction graphs in various graph learning algorithms. The experimental results demonstrate that the detection performance using ATGraph as input outperforms that using homogeneous graphs as the input by up to 0.2 AUROC.

Privacy-preserving record linkage (PPRL) technology, crucial for linking records across datasets while maintaining privacy, is susceptible to graph-based re-identification attacks. These attacks compromise privacy and pose significant risks, such as identity theft and financial fraud. This study proposes a zero-relationship encoding scheme that minimizes the linkage between source and encoded records to enhance PPRL systems’ resistance to re-identification attacks. Our method’s efficacy was validated through simulations on the Titanic and North Carolina Voter Records (NCVR) datasets, demonstrating a substantial reduction in re-identification rates. Security analysis confirms that our zero-relationship encoding effectively preserves privacy against graph-based re-identification threats, improving PPRL technology’s security.

(1) Background: Although numerous artificial intelligence (AI)-based air pollution prediction models have been proposed, research that links key pollution drivers, such as regional industrial facilities, to actionable policy recommendations is required. (2) Methods: This study employs the radial basis function (RBF) and spatial lag features to capture spatial interactions among regions, utilizing a transformer model for analysis. The model was trained on air quality and industrial data from South Korea (2010–2022) and Japan (2017–2020). (3) Results: The transformer model achieved a mean squared error of 0.045 for the Korean dataset and 0.166 for the Japanese dataset, outperforming benchmark models, including Support Vector Regression, neural networks, and the AutoRegressive Integrated Moving Average model. (4) Conclusions: By capturing complex spatial dynamics, the proposed model provides valuable insights that can assist policymakers in developing effective, data-driven strategies for air pollution reduction at the national and regional levels, thereby supporting the broader goals of sustainability through informed, equitable environmental interventions.

Blood tests are used to screen a risk group for hepatocellular carcinoma. Various studies have utilized artificial intelligence to diagnose hepatocellular carcinoma using blood test records. However, most studies suffer from performance degradation due to insufficient data. In this paper, we propose a novel graph convolutional network-based computer-aided diagnosis model to address the data insufficiency problem. The proposed method assists training by converting data into graphs representing the relationships among the features. As a result, our diagnosis model has improved 4% accuracy compared to existing approaches with 89.3% accuracy.