Blockchain-enabled smart contracts for Alzheimer’s healthcare payments: Fraud reduction, efficiency enhancement, and personalized treatment adjustments with machine learning

Alzheimer’s disease management requires effective healthcare systems capable of offering secure information processing, fraud prevention, and personalized treatment. Current healthcare systems lack data breaches, fraud, and nonpersonalized treatments. This research fills these fault lines by integrating blockchain technology with machine learning (ML) algorithms in Alzheimer’s healthcare management. The study proposes a model that incorporates blockchain-aided smart contracts and ML-based fraud detection, efficient payment handling, and patient-tailored treatment plans within Alzheimer’s healthcare networks. The platform employs elliptic curve cryptography (ECC) for encrypting patient information securely and offering robust protection with low computing costs. Blockchain is employed for secure, open, and tamper-evident transactions and automated payments via smart contracts. A random forest classifier is used for fraud detection, while treatment recommendations are made based on a K-nearest neighbors (KNN) model. Within the integrated workflow, patient data are first encrypted using ECC before being processed. Healthcare transactions are evaluated by the random forest model for fraud detection, and the prediction results are automatically enforced through blockchain smart contracts. Concurrently, the KNN model leverages secured patient data to generate personalized treatment recommendations, ensuring coordinated security, fraud prevention, and clinical personalization within a unified framework. The Kaggle Alzheimer’s Disease Dataset is used as the training and testing platform for the proposed models. The framework described was 98.5% accurate in fraud detection, with a 98.5% accuracy rate, 97.1% recall, and 98.8% F1-score. The blockchain network recorded a transaction success rate of 99.3% and throughput of [Formula: see text]250 transactions per second (TPS), demonstrating high scalability and efficiency in handling healthcare transactions. ECC encryption took 256[Formula: see text]ms to encrypt and 198[Formula: see text]ms to decrypt, thereby providing timely and secure data processing. The proposed system demonstrates a secure, efficient, and scalable way for processing Alzheimer’s healthcare payments, fraud detection, and personalized care. Its blend of blockchain and ML brings sweeping enhancements to data security, fraud protection, and treatment customization for both healthcare providers and patients.