CPS + EG and Neo-Bioscore predict individual outcomes but not trial results after neoadjuvant therapy for early breast cancer.

CPS + EG and Neo-Bioscore are significantly associated with long-term outcomes at the patient level in 8,359 early breast cancer patients, but show weak trial-level surrogacy.

• Why it matters: Surrogacy is needed to predict long-term benefit from neoadjuvant trials, but it is unclear whether these prognostic scores translate to trial-level outcome prediction.
• What they did: Using data from nine German Breast Group (GBG) and AGO-B neoadjuvant randomized trials, the study evaluated patient-level and trial-level surrogacy for DDFS, iDFS, and OS.
• The result: Trial-level associations were weak for both scores (R² = 0.03 to 0.24 with wide confidence intervals), suggesting they are not reliable surrogate endpoints, though they estimate residual individual risk.