A Novel Diabetes Healthcare Disease Prediction Framework Using Machine Learning Techniques.

Area of Science:

• Medical Informatics
• Computational Biology
• Data Science

Background:

• Diabetes mellitus is a global chronic metabolic disorder with severe health consequences.
• Accurate diabetes prediction remains challenging due to data limitations and methodological gaps.
• Big data analytics and machine learning (ML) offer promising approaches for healthcare predictive analytics.

Purpose of the Study:

• To investigate the application of big data analytics and ML techniques for diabetes prediction.
• To propose and evaluate an intelligent diabetes mellitus prediction framework (IDMPF).
• To develop and assess ML models for enhanced diabetes risk identification.

Main Methods:

• A comprehensive literature review of existing machine learning models for prediction.
• Development of an intelligent framework (IDMPF) based on the review.
• Implementation and evaluation of Decision Tree (DT), Random Forest (RF), and Support Vector Machine (SVM) models within the framework.

Main Results:

• The proposed ML-based framework achieved a notable score of 86%.
• The developed models demonstrated 83% accuracy in diabetes prediction with minimal error rates.
• The study successfully applied and evaluated widely used ML techniques for diabetes risk assessment.

Conclusions:

• The proposed intelligent framework and ML models provide a robust approach to diabetes prediction.
• Findings can aid health professionals, stakeholders, and researchers in developing preventative strategies.
• The study highlights the potential of ML in improving diabetes care and management.