A Blockchain-Secured IoT Framework for Real-Time Heart Failure Risk Stratification Using Temporal-Ensemble Fusion Learning

A Blockchain-Secured IoT Framework for Real-Time Heart Failure Risk Stratification Using Temporal-Ensemble Fusion Learning presents a secure, intelligent, and scalable healthcare monitoring framework that integrates Internet of Things (IoT), permissioned blockchain technology, and temporal-ensemble machine learning for continuous heart failure (HF) risk assessment. The framework collects multimodal physiological signals, including electrocardiogram (ECG), photoplethysmography (PPG), blood pressure, body weight, and physical activity, through IoT-enabled wearable devices and performs edge-based preprocessing to minimize latency and communication overhead. A permissioned blockchain with smart contract–based access control ensures data integrity, provenance, traceability, and resistance to unauthorized modification before the health records are analyzed. The proposed Temporal-Ensemble Fusion Learning model combines temporal feature extraction with gradient-boosted ensemble decision learning to capture complex physiological trends and generate accurate real-time HF risk predictions. Designed for deployment on resource-constrained edge devices, the framework enhances predictive performance while preserving patient privacy, reducing computational overhead, and enabling trustworthy decentralized healthcare monitoring. By unifying secure blockchain-enabled data management with low-latency intelligent risk stratification, the proposed architecture addresses the limitations of existing IoT-based heart failure monitoring systems and provides a reliable foundation for next-generation smart healthcare applications, while supporting future clinical validation, regulatory compliance, and large-scale deployment.