The prognostic performance of PREDICT+ in patients (pts) with HER2-positive (HER2+) early-stage breast cancer (EBC).
Bibliographic record
Abstract
524 Background: PREDICT+ is a widely used, free, online tool based on traditional clinico-pathological features, including HER2, developed to predict individual mortality of EBC pts and to aid clinical decision making for adjuvant therapy. However, its prognostic role in HER2+ EBC pts treated with chemotherapy (CT) and anti-HER2 therapies remains unclear. We aimed to investigate the prognostic performance of PREDICT+ in HER2+ EBC pts enrolled in the ALTTO trial. Methods: ALTTO is a phase III study evaluating adjuvant lapatinib (L) +/- trastuzumab (T) vs. T alone in pts with HER2+ EBC. Pts enrolled in the ALTTO trial and receiving T-based therapy started concurrently with CT were eligible for this analysis. We calculated PREDICT+ estimates using variables extracted from ALTTO database, blinded to pts outcomes. The prognostic performance of PREDICT+ was evaluated by assessing its calibration and discriminatory accuracy. For calibration, median predicted 5-year (5-yr) overall survival (OS) was compared to observed 5-yr OS. For discriminatory accuracy, the area under the receiver-operator characteristic (AUC under the ROC) curve and corresponding 95% confidence intervals (CI) for predicted 5-yr OS were calculated. Subgroup analyses were performed according to type of anti-HER2 therapy, type of CT, age, hormone receptor (HR) status, nodal status and tumor size. Results: This analysis included 2,794 pts. After a median follow-up of 6.0 years (IQR, 5.8-6.7), 182 deaths were observed. Overall, PREDICT+ underestimated 5-yr OS by 6.7% (95% CI, 5.8-7.6): observed 5-year OS was 94.7% vs. predicted 88.0%. The underestimation was consistent across all subgroups (Table). For discriminatory accuracy, AUC under the ROC curve was 73.7% (95%CI 69.7-77.8) in the overall population, ranging between 61.7% and 77.7% across the analysed subgroups. Conclusions: In HER2+ EBC pts enrolled in the ALTTO trial, the PREDICT+ score highly underestimated OS. The low performance of this prognostic tool was consistent across all pts subgroups. PREDICT+ should be used with caution to give prognostic estimation in HER2+ EBC pts treated in the modern era with effective chemotherapy and anti-HER2 targeted therapies.[Table: see text]
Fetched live from OpenAlex and de-inverted. Abstracts are not stored in this database: the inverted indexes are 8.6 GB of the frame’s 9.3 GB of text, and the host has 13 GB free.
How this classification was reachedexpand
Full frame machine prediction
Teacher imitationNot calibrated prevalence, not ground truth. Human validation pending. The Gemma side is a direct model label for every work in the frame, read from the title-only record. The Codex side is a classifier learned from the 10,348 direct Codex labels and calibrated to design-weighted sample rates; fields without enough sample support carry no Codex call. Candidate is the union of the two sides; consensus is their intersection. These outputs are machine_predicted_unvalidated and are not human labels.
Distilled classifier scores by category (both heads)
| Category | Codex | Gemma |
|---|---|---|
| Metaresearch | 0.002 | 0.005 |
| Meta-epidemiology (narrow) | 0.000 | 0.000 |
| Meta-epidemiology (broad) | 0.000 | 0.000 |
| Bibliometrics | 0.000 | 0.000 |
| Science and technology studies | 0.000 | 0.000 |
| Scholarly communication | 0.001 | 0.000 |
| Open science | 0.000 | 0.000 |
| Research integrity | 0.000 | 0.000 |
| Insufficient payload (model declined to judge) | 0.001 | 0.000 |
Machine scores (provisional)
The two teacher heads of the student model, read on this work. A score orders the frame for review; it never asserts a category, and the validation status ships verbatim with every row.
Baseline scores from an immature model (maturity gate not passed, 7 training rounds). Scores rank; they never assert a category.
score_only:v0-immature-baseline · verbatim from the scoring run: score_only means the number may rank works, and no category label ships from itClassification
machine, unvalidatedMachine predicted; a candidate call from one source (direct Gemma or distilled Codex), not a consensus.
How this classification was reached, model by model and score by score, is at the end of the page under "How this classification was reached".