Revolutionizing core muscle analysis in female sexual dysfunction based on machine learning.

Area of Science:

• Physiology
• Machine Learning
• Women's Health

Background:

• Female sexual dysfunction (FSD) is a prevalent condition affecting women across all age groups.
• Symptoms of FSD include decreased libido, difficulty with orgasm, and dyspareunia.
• The role of core muscles in FSD has been historically overlooked.

Purpose of the Study:

• To investigate the role of core muscles in the etiology of FSD.
• To develop predictive models for core muscle changes associated with FSD using machine and deep learning.
• To inform the creation of targeted rehabilitation strategies for FSD.

Main Methods:

• A comprehensive analysis of core muscle alterations in FSD was performed.
• Machine and deep learning models, including CNN and Random Forest Regressor, were evaluated.
• Model performance was assessed using Mean Squared Error (MSE), Mean Absolute Error (MAE), and R-squared (R²).

Main Results:

• Convolutional Neural Network (CNN) and Random Forest Regressor demonstrated high accuracy in predicting core muscle changes.
• CNN achieved an MSE of 0.002 and an R² score of 0.988.
• Random Forest Regressor yielded an MSE of 0.0021 and an R² score of 0.9905.

Conclusions:

• Machine and deep learning models effectively predict core muscle dynamics in FSD.
• Core muscles play a crucial, often neglected, role in FSD.
• Developing rehabilitation programs targeting core muscles is essential for improving sexual health in women with FSD.