Real-World Evidence of the Impact of CanAssist Breast on Physician’s Decision About the Use of Adjuvant Chemotherapy in Early Breast Cancer
Bibliographic record
Abstract
Background Clinicians use prognostic biomarker/multi-gene-based tests for predicting recurrence in hormone receptor-positive/HER2-negative (HR+/HER2-) early-stage breast cancer (EBC). CanAssist Beast (CAB) uses the expression of five protein biomarkers in combination with tumor-specific parameters such as tumor size, histopathological grade, and lymph node status to predict the risk of distant recurrence within five years of diagnosis for patients with HR+/HER2-, EBC. The current study aimed to evaluate the impact of prognostic tests on adjuvant chemotherapy decisions by assessing the agreement between clinical and CAB risk stratification as low-risk (LR) or high-risk (HR) for distant recurrence. Methods The primary study group included 300 patients with HR+/HER2-, EBC diagnosed between 2016 and 2021. The clinical risk assessment and recommended treatment plan were captured before and after receiving the results for CAB. The risk stratification of patients into CAB LR and HR was obtained. Finally, compliance with CAB was analyzed by assessing the concordance of treatment prescribed with the CAB risk category. Results Before performing the CanAssist Breast test, patients were stratified based on clinicopathological features, with 52% of patients as LR, 21% as HR, and 27% of patients distributed as uncertain/intermediate risk (IR) category. CAB re-stratified the same cohort of patients, 67% as LR and 33% as HR, which was 15% higher than that of clinical LR assessment. The clinical IR category was re-stratified by CAB as 51% LR and 49% HR. Changes in treatment recommendations were seen in both clinical HR and clinical LR groups, which were 87% and 85%, respectively. Conclusions CAB has a significant impact on chemotherapy decisions. CAB provides definite treatment recommendations for patients with clinical intermediate risk. Overall, CAB has changed treatment recommendations in 23% of the cohort and for 88% of clinical IR patients helped physicians make a treatment decision.
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 | 0.049 | 0.291 |
| Meta-epidemiology (narrow) | 0.000 | 0.000 |
| Meta-epidemiology (broad) | 0.000 | 0.001 |
| Bibliometrics | 0.002 | 0.003 |
| Science and technology studies | 0.000 | 0.002 |
| Scholarly communication | 0.003 | 0.002 |
| Open science | 0.001 | 0.001 |
| Research integrity | 0.001 | 0.001 |
| Insufficient payload (model declined to judge) | 0.005 | 0.001 |
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".