Method for Detecting Pathology of Internal Organs Using Bioelectrography

Area of Science:

• Medical diagnostics
• Computational biology
• Biomedical engineering

Background:

• Current bioelectrography methods lack automated detection for internal organ pathologies and combined diseases.
• There is a need for improved diagnostic tools to identify organ dysfunction and abnormalities efficiently.

Purpose of the Study:

• To develop an automated method for detecting internal organ pathology using bioelectrography.
• To create a software package for disease detection based on bioelectrography data.
• To evaluate the efficacy of various machine learning classifiers for this diagnostic task.

Main Methods:

• Bioelectrography data acquisition and analysis.
• Implementation and comparison of machine learning classifiers: logistic regression, decision tree, random forest, xgboost, KNN, SVM, and HyperTab.
• Development of a novel method and software for automated pathology detection.

Main Results:

• Machine learning classifiers significantly expand the scope of detectable pathologies.
• HyperTab, logistic regression, and xgboost demonstrated the best performance, achieving 60-70% f1-score.
• The developed method enables the identification of individual and combined pathologies.

Conclusions:

• The developed bioelectrography-based method with machine learning offers a promising approach for automated disease detection.
• Combining machine learning models can improve the accuracy of identifying specific and complex pathologies.
• This technology has the potential to reduce the burden on medical staff during screening and improve diagnostic efficiency.