A New Fuzzy-Based Classification Method for Use in Smart/Precision Medicine

Area of Science:

• Medical Informatics
• Artificial Intelligence in Medicine
• Data Science

Background:

• Information technology advancements have spurred the evolution of Medicine 4.0, integrating AI-based medicine, telemedicine, and precision medicine.
• Each component of Medicine 4.0 generates unique data requiring simultaneous processing for a comprehensive patient health overview.
• Current data processing methods face challenges in handling the diverse and complex data streams inherent in smart medicine.

Purpose of the Study:

• To introduce a novel classification method for processing diverse medical data types.
• To address the need for integrated analysis of data from AI-based medicine, telemedicine, and precision medicine.
• To enhance the accuracy and efficiency of medical data classification.

Main Methods:

• Development of a new data classification method utilizing a fuzzy classifier.
• Application of a fuzzy decision tree as a specific fuzzy classifier for illustration.
• Comparative analysis of the proposed fuzzy classification method against crisp classifiers.

Main Results:

• The proposed fuzzy classification method demonstrates superior performance in processing a wide array of medical data types.
• Fuzzy decision trees, as an implementation, show enhanced accuracy in classifying medical data.
• The fuzzy classifier approach yields better classification outcomes compared to crisp classifiers.

Conclusions:

• The novel fuzzy classification method effectively integrates and processes diverse medical data for smart medicine applications.
• Fuzzy logic offers a robust framework for enhancing medical data analysis and improving diagnostic accuracy.
• This approach represents a significant advancement in handling the complexities of Medicine 4.0 data.