With 50% of post-operative biochemical failure, efficient predictive models are needed to guide post-operative management. Radiomic features are quantitative features extracted from medical imaging, supposed to be correlated with tumor heterogeneity. We aim to build and test three predictive models (clinical, radiomic and combined models).
Study Type
OBSERVATIONAL
Enrollment
195
CHRU de Brest
Brest, Brittany Region, France
Centre Hospitalier de Cornouaille
Quimper, Brittany Region, France
Prediction of biochemical failure
Comparison of AUCs between each predictive model
Time frame: From the date of surgery until data collection (up to 100 months)
Prediction of survival without biochemical failure
Survival analysis: comparison of Kaplan-Meier curves
Time frame: From the date of surgery until data collection (up to 100 months)
This platform is for informational purposes only and does not constitute medical advice. Always consult a qualified healthcare professional.