Empowering Patient-Centric Healthcare with AI-Driven Predictive Analytics in Blockchain

Abstract

This paper proposes a novel approach integrating Multilayer Perceptron (MLP) with Gated Recurrent Unit (GRU) for predictive analytics within blockchain-based health records systems. In contrast to conventional models, the suggested method combines the power of GRUs to identify temporal correlations in sequential data with the strengths of MLPs in extracting complex patterns from organized health data. More precise and dynamic predictions are made possible by this hybrid model, which is designed to comprehend complicated health trajectories. The proposed model combines the strengths of MLP in learning complex patterns from structured data with GRU's ability to capture temporal dependencies from sequential data. By integrating these components, the model achieves a comprehensive understanding of patients' health trajectories, enabling accurate predictions of future health outcomes. Key features of this approach include adaptive learning mechanisms to accommodate diverse patient populations and dynamic health conditions. Moreover, the model's architecture facilitates real-time analysis, allowing healthcare providers to proactively intervene and optimize treatment plans. The integration of MLP with GRU offers a scalable and versatile solution for extracting actionable insights from vast repositories of health data, ultimately improving patient outcomes and reducing healthcare costs. The proposed method is implemented in Python software and has an accuracy of about 93% which is higher than other existing methods like CNN-LSTM, CNN-GRU and MLP-LSTM.