<p>Healthcare Information Exchange (HIE) has becoming one of the fundamental operations in today healthcare systems. However, such operation is very crucial due to the sensitivity of the patient data as well as the exponential increasing of attack numbers and types when sharing the data between various healthcare facilities (HCFs). This has placed significant pressure on HCFs to effectively secure and detect risky transactions by adopting various technologies in the HIE operations. Among these technologies, blockchain and artificial intelligence have emerged as valuable techniques for monitoring medical transactions and detecting fraudulent transactions. Aiming to take advantages of both technologies, we propose BlockAI, a secure framework designed for analyzing patient transactions communicated between HCFs and removing untrusted ones. On one hand, BlockAI uses two types of blockchain to enhance the data security: a blockchain to store ordinary patient data, and an off-chain to store the sensitive patient’s data. Additionally, we create a link of signed and verified blockchain and hashed blocks to make the blockchain network more resistant to unauthorized integrity attacks that attempt to falsify sensitive medical data and its related transactions. On the other hand, BlockAI uses an advanced deep learning model called generative adversarial network (GAN) with two-folds: first, it enhances the training phase of the model by generating additional synthetic health data, then it uses a discriminator to accurately detect the risky transactions in the testing phases. We evaluated the performance of our framework based on real health data while the obtained results shows the efficiency of BlockAI in detecting risky transactions and enhancing HIE security.</p>