Diagnosis of several diseases by using combined kernels with Support Vector Machine

Area of Science:

• Biomedical research
• Computational biology
• Machine learning

Background:

• Machine learning (ML) is crucial for analyzing large biomedical datasets.
• Support Vector Machines (SVM) are effective classifiers in various fields.
• Improving SVM classification efficiency through combined methods is an active research area.

Purpose of the Study:

• To propose a novel Support Vector Machine (SVM) classification method using combined kernel functions.
• To evaluate the performance of the new method for influential classification in biomedical applications.
• To compare the developed non-linear classifier against the standard SVM method.

Main Methods:

• Development of a new Support Vector Machine (SVM) classification technique.
• Integration of combined kernel functions within the SVM framework.
• Application and comparison of the developed method on seven diverse medical disease datasets.

Main Results:

• The proposed combined kernel SVM method demonstrated significant improvements in classification performance.
• The new method showed a notable increase in probability excess compared to the standard SVM.
• The enhanced SVM approach proved effective across multiple medical disease datasets.

Conclusions:

• The novel combined kernel Support Vector Machine (SVM) method offers superior classification performance for medical diseases.
• This approach represents a significant advancement in applying machine learning to complex biomedical problems.
• The developed technique holds promise for improving diagnostic accuracy and patient outcomes.