Artificial Intelligence Based Approach to Self-Sensitivity and Compassion Scores: Development of Prediction Models.

Area of Science:

• Psychology and Computer Science
• Investigates the intersection of artificial intelligence (AI) and psychosocial variables.

Background:

• Self-sensitivity and compassion are crucial for stress management.
• Accurate measurement of these psychosocial variables is essential for effective interventions.

Purpose of the Study:

• To develop and evaluate AI and machine learning models for predicting self-sensitivity and compassion.
• To compare the predictive performance of Gaussian Process Regression (GPR), Neural Network Regression (Net), and Support Vector Machine (SVM) models.

Main Methods:

• Utilized Gaussian Process Regression (GPR), Neural Network Regression (Net), and Support Vector Machine (SVM) models.
• Collected data using self-sensitivity and compassion scales.
• Evaluated model performance using metrics such as MAPE, MAE, SE, MSE, RMSE, R, and R².

Main Results:

• The Gaussian Process Regression (GPR) model achieved the highest prediction accuracy for both self-sensitivity and compassion.
• Neural Network Regression (Net) and Support Vector Machine (SVM) models also demonstrated effective predictive capabilities.
• GPR outperformed Net and SVM models in overall prediction accuracy.

Conclusions:

• AI and machine learning models are practical tools for predicting self-sensitivity and compassion scores.
• The GPR model shows significant potential due to its high prediction accuracy.
• Findings have important implications for nursing practice and the design of psychosocial interventions.