An efficient fuzzy logic and artificial intelligence based optimization strategy for bigdata healthcare system

Digital health has revolutionized patient care by integrating big data analytics for predictive diagnostics, personalized treatment, and real-time health monitoring. However, the rapid generation of healthcare data from IoT devices, electronic health records, and medical imaging poses challenges such as high dimensionality, noise, and real-time processing. Existing methodologies struggle to balance accuracy and efficiency, making them limited for real-time healthcare applications. This paper proposes an optimization technique for big data-based healthcare systems incorporating fuzzy logic and artificial intelligence for predictive decision-making. This framework considers IoT-collected health data, which in itself brings forth problems of high dimensionality, noise, and real-time analytics. An intelligent preprocessing stage encompasses noise reduction and data integration, providing consistency and reliability for the dataset, which uses a fuzzy logic system. For optimal feature selection, an advanced AI model combines Lion optimization with heap-based feature estimation, thus reducing dimensionality while conserving health-relevant information. The optimized features are classified using a Hybrid Golden Eagle-Self-constructing Neural Fuzzy (HGE-SNF) algorithm, which dynamically tunes the weights and biases toward optimal classification performance. This hybrid approach improves predictive accuracy in disease detection and patient management issues and enhances computational efficiency for real-time healthcare applications. Experimental results indicate that it performs better than traditional methods and has great potential to revolutionize big data analytics in health systems.