Intelligent classification of cardiotocography based on a support vector machine and convolutional neural network:...

Area of Science:

• Medical Informatics
• Artificial Intelligence in Healthcare
• Fetal Monitoring

Background:

• Cardiotocography (CTG) is crucial for assessing fetal well-being during pregnancy.
• Accurate interpretation of CTG patterns is essential but can be challenging for clinicians.
• Automated systems can potentially improve the consistency and efficiency of CTG analysis.

Purpose of the Study:

• To develop and evaluate a computerized system for intelligent CTG assessment.
• To utilize multiscene analysis incorporating Support Vector Machine (SVM) and Convolutional Neural Network (CNN) algorithms.
• To enhance the accuracy and reliability of CTG data classification.

Main Methods:

• Retrospective collection of 2542 CTG records from singleton pregnancies.
• Categorization of CTG data into five scenes: baseline, variability, acceleration, deceleration, and normality.
• Application of dynamic threshold, SVM, and CNN algorithms for system training and optimization.

Main Results:

• The system achieved a global accuracy of 93.88%, sensitivity of 93.06%, and specificity of 94.33%.
• Optimal performance in acceleration and deceleration scenes was observed with a convolution kernel of 3.
• The multiscene analysis model demonstrated robust classification capabilities.

Conclusions:

• The proposed multiscene research model integrating SVM and CNN is an effective tool for intelligent CTG classification.
• This system shows potential to assist obstetricians in making informed decisions regarding fetal health.
• The findings support the use of AI-driven tools in modern obstetrics.