A wrapper-based learning framework for papillary thyroid carcinoma diagnosis using optimized feature selection

Puntos clave

• Enhanced feature selection significantly improves diagnosis accuracy for papillary thyroid carcinoma, showing a potential increase in computational efficiency.
• The model achieved an accuracy of 92% during testing with optimized algorithms for feature selection, illustrating strong predictive capabilities.
• Wrapper-based learning approach in combination with optimized feature selection was employed to enhance diagnostic performance effectively.
• These findings highlight the need for advanced computational techniques to improve clinical diagnostics, suggesting further validation in diverse populations.