Enhanced heart disease risk prediction using adaptive botox optimization based deep long-term recurrent convolutional network.

This article presents an advanced methodology for heart disease prediction using Internet of Things (IoT) sensor data, integrating sophisticated data preprocessing, feature selection, and deep learning techniques. The approach employs Clustering-based Data Imputation and Normalization (CDIN) and Robust Mahalanobis Distance-based Outlier Detection (RMDBOD) to enhance data quality, the Improved Binary Quantum-based Avian Navigation Optimization (IBQANO) algorithm for optimal feature selection, and a Deep Long-Term Recurrent Convolutional Network (DLRCN) fine-tuned via the Adaptive Botox Optimization Algorithm (ABOA) for classification. Evaluated on the Hungarian, University of California (UCI) Statlog, and Cleveland heart disease datasets, the proposed models achieved superior accuracy—99.72% on the Cleveland dataset and 99.41% on the UCI dataset—outperforming traditional machine learning and deep learning models across multiple metrics. The study underscores the potential of combining IoT data with advanced hybrid deep learning frameworks to improve remote healthcare monitoring and heart disease diagnosis, while noting the need for future clinical validation, integration with electronic health records, and enhancements in model interpretability and real-time application.