What is the minimum sample size required for ROC analysis assuming no prior study done to know sensitivity or specificity of a particular test?
Sensitivity, specificity, and ROC are not recommended in this (nor hardly in any other) context. See
- Statistical Thinking - Damage Caused by Classification Accuracy and Other Discontinuous Improper Accuracy Scoring Rules
- Statistical Thinking - Clinicians’ Misunderstanding of Probabilities Makes Them Like Backwards Probabilities Such As Sensitivity, Specificity, and Type I Error
- Statistical Thinking - Classification vs. Prediction