Development of Big Data Predictive Analytics Model for Disease Prediction using Machine learning Technique.

Area of Science:

• Health Informatics
• Machine Learning
• Big Data Analytics

Background:

• Heart disease is a leading cause of global mortality, necessitating advanced prediction methods.
• Big data analysis offers significant potential for improving health outcomes through predictive modeling.
• Machine learning techniques are increasingly vital for informed decision-making in healthcare.

Purpose of the Study:

• To develop and evaluate a Big Data Predictive Analytics Model for Disease Prediction using Naive Bayes (BPA-NB).
• To leverage machine learning for accurate heart disease prediction from health parameters.
• To demonstrate the utility of big data tools in healthcare for early disease detection.

Main Methods:

• Utilized the Naive Bayes classification technique, suitable for large datasets.
• Trained the BPA-NB model on heart disease data from the UCI machine learning repository.
• Employed Hadoop-Spark as the big data computing tool for efficient analysis.

Main Results:

• The BPA-NB model achieved a high prediction accuracy of 97.12% for heart disease.
• The model effectively classified patient data, demonstrating its predictive capabilities.
• Experiments confirmed the model's ability to predict future patient health conditions.

Conclusions:

• The BPA-NB model provides a highly accurate and efficient approach to heart disease prediction.
• Big data analytics, powered by tools like Hadoop-Spark, can yield significant insights in healthcare.
• Early disease detection through predictive modeling can lead to better patient outcomes.