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

Area of Science:

• Cardiovascular Health
• Artificial Intelligence in Medicine
• Internet of Things (IoT)

Background:

• Heart disease remains the leading global cause of mortality.
• Accurate prediction is challenging, necessitating advanced techniques.
• IoT sensor data offers potential for improved illness prediction.

Purpose of the Study:

• To develop an integrated methodology for heart disease classification using IoT sensor data.
• To enhance prediction accuracy through advanced data preprocessing, feature selection, and deep learning.
• To provide a reliable tool for remote healthcare monitoring, particularly for conditions like high blood pressure.

Main Methods:

• Data preprocessing using Clustering-based Data Imputation and Normalization (CDIN) and Robust Mahalanobis Distance-based Outlier Detection (RMDBOD).
• Feature selection via the Improved Binary Quantum-based Avian Navigation Optimization (IBQANO) algorithm.
• Classification using a Deep Long-Term Recurrent Convolutional Network (DLRCN), optimized by the Adaptive Botox Optimization Algorithm (ABOA).

Main Results:

• The proposed methodology demonstrated superior performance on Hungarian, UCI, and Cleveland heart disease datasets.
• Achieved high accuracy rates: 99.72% on the Cleveland dataset and 99.41% on the UCI dataset.
• Significant improvements over existing heart disease prediction methods were observed.

Conclusions:

• The developed methodology represents a substantial advancement in remote healthcare and cardiovascular disease prediction.
• Offers a reliable and accurate solution for managing conditions like high blood pressure, especially in older adults.
• Highlights the potential of integrated IoT, AI, and deep learning for proactive health management.