Purpose:To develop and validate a multimodal recurrence-risk model integrating histology, genomic testing, and clinical variables. Methods:We developed AI-Path, a whole-slide image biomarker for recurrence prediction trained in CALGB 9344, and validated it in three independent cohorts: TAILORx, a multi-site Chicago cohort, and the MDX-BRCA cohort. We then integrated AI-Path with Oncotype DX Recurrence Score (RS), tumor size, and nodal status into a Cox model, PathClinRS, fit using 60% of cases from TAILORx, with the remaining 40% held out for validation. The primary end point was distant recurrence-free interval. Performance was assessed using Harrell's concordance index (C-index) and Kaplan-Meier analyses. Results:A total of 12,418 patients were included. In TAILORx, AI-Path outperformed RS for distant recurrence (C-index, 0.682 vs 0.647; P = .038), driven by superior prediction of late recurrence (0.656 vs 0.567; P < .001). In node-negative disease, PathClinRS outperformed RSClin in the TAILORx fitting (0.72 vs 0.70; P = .016) and validation sets (0.74 vs 0.70; P = .004). In node-positive disease, PathClinRS outperformed RSClinN+ in Chicago (0.94 vs 0.74; P < .001) and MDX-BRCA (0.71 vs 0.66; P = .004) cohorts. Compared with NATALEE eligibility, PathClinRS identified nearly twice as many high-risk node-negative patients while maintaining a comparable 10-year distant recurrence risk (16.7% vs 16.6% per NATALEE eligibility in TAILORx fitting; 21.0% vs 19.4% in TAILORx validation). PathClinRS identified 68% of intermediate risk premenopausal patients as low-risk with no evidence of chemotherapy benefit, compared to only 36% identified as low risk by standard clinicopathologic criteria. Conclusion:Digital histopathology provides prognostic information complementary to genomic assays and has the potential to personalize therapy beyond existing clinicogenomic tools.

Importance Many patients are diagnosed with atypical lesions or lobular carcinoma in situ (LCIS); however, evidence- and consensus-based guidelines for the management of many of these lesions are limited. Observations The American Society of Breast Surgeons, in collaboration with the Society of Breast Imaging and College of American Pathology, assembled a steering group to create guidelines for the management of atypical lesions and LCIS, inclusive of flat epithelial atypia (FEA), atypical ductal hyperplasia (ADH), atypical lobular hyperplasia (ALH), classic LCIS (C-LCIS), and the variant LCIS forms pleomorphic LCIS (P-LCIS) and florid LCIS (F-LCIS). The natural history of ADH, ALH, and C-LCIS suggests that these lesions are associated with an elevated future breast cancer risk; therefore, patients diagnosed with these lesions should be recommended to undergo comprehensive risk assessment and counseling about breast cancer risk-reducing strategies. The magnitude of future breast cancer risk associated with P-LCIS and F-LCIS remains uncertain, yet if these lesions are determined to be hormone receptor positive, risk-reducing medications should be considered. There is no evidence that FEA is associated with an elevated future breast cancer risk. A second pathology review confirmation is recommended for ADH, should be considered for FEA, and is not necessary for ALH or LCIS. Currently available evidence supports the need to diagnostically excise most ADH, P-LCIS, and F-LCIS cases identified on core biopsy, although some ADH cases fulfilling strict criteria and multidisciplinary consensus can be observed. P-LCIS and F-LCIS require a negative margin, but ADH does not. ALH and C-LCIS can be safely observed if the core biopsy diagnosis is concordant with imaging features (ie, radiographic-pathologic concordance is established). Provided radiologic-pathologic concordance is confirmed, diagnostic excision is generally not indicated after a diagnosis of FEA alone. Conclusions and Relevance These guidelines provide evidence-informed, consensus-based recommendations for the management of atypical lesions of the breast, including ADH, ALH, FEA, C-LCIS, P-LCIS, and F-LCIS. Practicing clinicians who treat patients with atypical breast lesions or LCIS should consider integrating these guidelines into clinical management.

The purpose of this study was to examine treatment patterns and overall survival (OS) for patients ≥ 80 years with triple negative breast cancer (TNBC). The National Cancer Data Base was queried for patients ≥ 80 years old diagnosed with TNBC from 2012 to 2022. Patients with T1a or Tis tumors or distant metastatic disease were excluded. Charlson–Deyo comorbidity scores were used to assess comorbidity burden. Treatment patterns of chemotherapy, radiation therapy, and surgery were examined. OS was estimated using Kaplan–Meier curves and multivariable Cox proportional hazards models evaluated factors associated with OS. In total, 10,767 patients met inclusion criteria: 5876 (54.5

Current genomic assays provide prognostic information and guide chemotherapy decisions in early-stage hormone receptor–positive/human epidermal growth factor receptor 2–negative (HR+/HER2−) breast cancer, but limited tissue sampling may incompletely capture tumor heterogeneity. We developed and validated an image-based artificial intelligence (AI) model integrating dynamic contrast-enhanced magnetic resonance imaging (DCE-MRI) and clinicopathologic features to predict recurrence risk in early-stage HR+/HER2 − breast cancer. In this retrospective multi-institutional study, the model was trained using pre-treatment imaging and clinicopathologic data from 522 patients and independently validated in 550 additional patients treated between 2010 and 2023. By analyzing spatial tumor characteristics, the model generated individualized recurrence risk scores that outperformed clinicopathologic features alone. In the validation cohort, median age was 53 years (range, 24–90), 15.6% of patients self-identified as African American, 89.7% had clinical T1–T2 disease, and 34.4% had 1–3 positive lymph nodes. Five-year recurrence-free survival was 93.8% (95% CI, 90.0–96.2%) among patients classified as low risk compared with 82.6% (95% CI, 74.8–88.1%) among those classified as high risk, corresponding to an adjusted hazard ratio of 2.28. Prognostic performance was maintained across clinically relevant subgroups, including age and nodal status. These findings support the potential of a noninvasive image-based AI approach for real-time prognostication and treatment personalization in early-stage HR+/HER2 − breast cancer.

PURPOSE:Genomic assays are commonly used to predict breast cancer recurrence but remain inaccessible in low-resource settings, often leading to unnecessary chemotherapy. We previously optimized a LASSO-penalized regression model incorporating quantitative clinicopathologic features to predict genomic risk. Here, we present validation and clinical utility in an international cohort. METHODS:We retrospectively analyzed patients with early-stage hormone receptor-positive/human epidermal growth factor receptor 2-negative breast cancer treated in Chicago and Rio de Janeiro. Model accuracy for predicting high Oncotype DX (ODX) scores was evaluated using area under the receiver operating characteristic curve (AUROC) in Chicago cohorts. Survival outcomes-disease-free interval (DFI), disease-free survival (DFS), and overall survival (OS)-were compared by Kaplan-Meier and Cox regression using a predefined threshold for high-risk disease. Adjusted models examined chemotherapy benefit by predicted risk. Estimated cost was compared between testing strategies and chemotherapy allocation in Brazil and the United States. The study was approved by the Brazilian Research Ethics Committee on October 24, 2024, under CAAE number 67993323.6.0000.5274. Due to the retrospective nature of the study, which involved only data collection from electronic medical records, the requirement for informed consent was waived by the Ethics Committee. Additionally, the study is covered under Institutional Review Board 22-0707 at the University of Chicago. RESULTS:We included 1,566 patients from Chicago and 296 from Rio de Janeiro. The estrogen receptor/progesterone receptor/Ki-67 model showed strong performance for ODX prediction (AUROC 0.81 and 0.91).Compared with high-risk patients, low-risk patients had superior 5-year DFI (98.0% v 81.6%, hazard ratio [HR], 11.89, P < .001), DFS (91.3% v 77.5%, HR, 3.41, P < .001), and OS (92.1% v 87.3%, HR, 2.47, P = .02). Chemotherapy provided no significant benefit in the low-risk group. CONCLUSION:Our model accurately predicted recurrence and outcomes across US and Brazilian cohorts, supporting treatment de-escalation in low-risk patients and promoting equitable care where genomic testing is limited.

Purpose:To test whether histology-derived gene-expression signatures from routine hematoxylin and eosin slides are prognostic for recurrence and predictive of chemotherapy benefit in early breast cancer. Methods:We conducted a multi-cohort study including CALGB 9344 (anthracycline ± paclitaxel), CALGB 9741 (standard vs dose-dense chemotherapy), a pooled Chicago real-world cohort, and the American Cancer Society (ACS) Cancer Prevention Studies-II and -3. Whole-slide images were processed with a previously described pipeline to generate 61 histology-derived signatures per patient. The primary endpoint was distant recurrence-free interval (DRFI), except in ACS, where breast cancer-specific survival was used. Secondary endpoints include distant recurrence-free survival (DRFS) and overall survival. The most prognostic signature in CALGB 9344, selected by Harrell's C-index, was evaluated in additional cohorts. Signature-treatment interaction was assessed by likelihood-ratio tests. Multivariable Cox models incorporating age, tumor size, nodal status, estrogen/progesterone receptor status, and signature were fit in CALGB 9344 to improve risk stratification. Results:A total of 7,170 patients were included across four cohorts. The top histology-derived signature in CALGB 9344 showed strong prognostic performance for 5-year DRFI (C-index 0.63) and performed well across validation cohorts (C-index 0.60, 0.70, and 0.62 in CALGB 9741, Chicago, and ACS, respectively). The strongest predictive signal for treatment benefit was observed for DRFS. High-risk cases identified by the signature demonstrated greater benefit from taxane in CALGB 9344 (adjusted hazard ratio [aHR] 0.76 for DRFS, 95% CI 0.66-0.88; interaction p=0.028), from dose-dense chemotherapy in CALGB 9741 (aHR 0.69, 95% CI 0.56-0.85; interaction p=0.039), and differential chemotherapy benefit in the Chicago cohort (aHR 0.84, 95% CI 0.59-1.21; interaction p=0.009). Combined clinical-histology models improved risk stratification and identified low-risk groups with a 2%-10% risk of distant recurrence or breast cancer death. Conclusion:Histology-derived signatures from H&E images are broadly prognostic and, unlike clinical factors, may predict chemotherapy benefit.

We examined the impact of the COVID-19 consortium recommendations on the surgical management of breast cancer during the first year of the pandemic. Patients with newly diagnosed ER + DCIS, ER- DCIS, AJCC Stage cT1-2N0-1 ER + , HER2-, HER2 + , and triple negative breast cancer were identified from the National Cancer Database from 2018 to 2021. An interrupted time series design evaluated differences in surgical delay and use of neoadjuvant chemotherapy/immunotherapy (NAC) and endocrine therapy (NET) before and after the pandemic. A total of 895116 female patients were included in the study with a mean age of 61.7 years. Time to surgery decreased by an average 5.5 days from January 2020 to May 2020 for all breast cancer types, corresponding with a 62.2

To address the interval between biopsy and first treatment, the National Accreditation Program for Breast Centers (NAPBC) launched Patient-Reported Observations for Medical Procedure Timeliness (PROMPT), a quality collaborative. Participating PROMPT sites submitted data on the number of days from biopsy to first treatment (either surgery or neoadjuvant treatment (NAC)) before and after individual site-specific quality improvement (QI) projects using the American College of Surgeons Quality Framework. The study examined interventions of sites that reported successful projects and barriers for both successful and unsuccessful sites. Of 104 PROMPT sites, 62 (59.6

BACKGROUND:Surgical volumes have long been correlated with outcomes, but their relationship to quality measures (QMs) remains unclear. This study aimed to examine the association between surgeon volumes and American Society of Breast Surgeons QM performance. METHODS:The study analyzed 635,252 women in the National Cancer Database 18 years old or older with stage I, II, or III breast cancer who underwent surgery between 1 January 2018 and 31 December 2022. Surgeon volume was calculated as tertiles using National Provider Identifiers. Quality measures included treatment timeliness, axillary management, and multidisciplinary care. Adjusted multilevel logistic models, with hospital as a random effect, were used to investigate associations of volume with QM performance. RESULTS:Low-volume (LV), average-volume (AV), and high-volume (HV) surgeons annually performed a median of 33 (interquartile range [IQR], 17-48), 98 (IQR, 80-112), and 169 (IQR, 147-202) breast cancer surgeries, respectively. Low-volume surgeons cared for a higher proportion of older, non-white, and non-metropolitan patients and were more likely to provide timely surgery (odds ratio [OR], 1.12; 95 % confidence interval [CI], 1.09-1.14), but less likely to adhere to adjuvant radiotherapy (odds ratio [OR], 0.81; 95 % confidence interval [CI], 0.77-0.85), appropriate axillary management (OR, 0.65; 95 % CI, 0.57-0.74), and sentinel lymph node biopsy (SLNB) omission (OR, 0.69; 95 % CI, 0.65-0.73). For LV surgeons, breast center accreditation was associated with increased radiotherapy referral (OR, 1.28; 95 % CI, 1.14-1.44) and SLNB omission (OR, 1.47; 95 % CI, 1.23-1.76). CONCLUSION:Low-volume surgeons had greater variability in breast QM performance and may benefit from efforts, including education and strengthening multidisciplinary communication, to improve breast cancer care for vulnerable populations.

Importance:Many patients are diagnosed with benign breast lesions; however, evidence- and consensus-based guidelines for the management of benign breast disease (BBD) are limited. Observations:The American Society of Breast Surgeons (ASBrS) and the Society of Breast Imaging (SBI) developed guidelines for the management of benign fibroepithelial lesions (FELs) using a modified Delphi consensus methodology and public comment. There was strong consensus that core biopsy-proven concordant fibroadenomas without atypia only require excision if they were symptomatic, patient preferred, attained a certain size, or demonstrated substantive growth over time on clinical examination. There was strong consensus that when removing a fibroadenoma, complete excision without transection of the mass is recommended and surgeons should consider aesthetics, sensation, and other factors when selecting incision placement. Patients with core biopsy-proven concordant fibroadenomas do not require imaging follow-up and may return to age-appropriate screening. Many benign phyllodes tumors (BPTs) present as an FEL on core biopsy, and these lesions along with any lesions with suspicion of or concern for phyllodes tumors (PTs) require surgical excisional biopsy with complete excision of the mass. Re-excision of a BPT is not required for patients with a positive margin for BPT, but a margin re-excision may be considered if the mass was transected or there is concern of residual disease after excisional biopsy. Patients with BPT who have undergone excision do not require follow-up imaging and may return to age-appropriate screening. Conclusions and Relevance:Evidence-informed, consensus and expert opinion-based guidelines for the management of benign FELs of the breast were developed. These guidelines provide clarification on the controversial management of benign FELs of the breast. Any practicing clinicians who treat patients with benign FELs should integrate these guidelines into treatment of their patients.

Since 2022, the Commission on Cancer (CoC) has developed three new breast cancer quality measures (QMs): time to surgery (BCSdx) and radiation (BCSRT) and the use of neoadjuvant therapy for triple negative and HER2/neu positive breast cancer (BneoCT). This study assesses CoC center historical performance for these measures and facility factors associated with low performance. We examined the median number of days for time to surgery and radiation, and the proportion of facilities that achieved an estimated performance rate (EPR) of 70

Abstract Background: The Oncotype DX (ODX) test is a 21-gene expression assay widely used for the prediction of risk recurrence in early-stage breast cancer, but it may be possible to identify patients who can forgo testing using only clinicopathologic variables. In 2018, the National Cancer Database (NCDB) began reporting quantitative histologic parameters for estrogen receptor (ER), progesterone receptor (PR), and Ki-67 expression in breast cancer patients. Inclusion of these variables may improve the development of nationally applicable models to predict ODX results using clinicopathologic variables alone. Methods: Using a cohort of patients from the NCDB diagnosed from 2018–2020 with hormone receptor (HR)-positive, HER2-negative, Stage I-III breast cancer, we trained machine learning models to predict high-risk (26-100) ODX score. A subset comprising 80% of patients was used for model training, while the remaining data were set aside for internal validation. An external validation cohort was selected from the University of Chicago Medical Center (UCMC), including patients diagnosed from 2009–2021. Feature selection, model architecture selection, and hyperparameter tuning were performed using 10-fold cross-validation within the NCDB training set. We compared a model with quantitative ER, PR, and Ki-67; a model with only quantitative ER and PR, and a model without quantitative immunohistochemistry – to best reflect the likely data available in a variety of practice patterns. The primary endpoint was the area under the receiver operating characteristic curve (AUROC) for prediction of high-risk ODX results in the UCMC validation cohort. Models were also evaluated as rule-out tests to identify low-risk patients who did not require further ODX testing, using a high (90%) sensitivity threshold, fit in the NCDB training dataset. Results: We identified 53,346 patients from the NCDB cohort meeting the inclusion criteria; 7% had a high risk ODX score, with a median follow-up time of 28 months. The UCMC validation cohort included 896 patients, and was more diverse, with 30% non-Hispanic Black patients (versus 8% in NCDB), more high-risk patients (18% with high ODX), and a longer median follow-up time of 55 months. In the NCDB validation cohort, models incorporating quantitative ER/PR (AUROC 0.78, 95% CI 0.77–0.80) and quantitative ER/PR/Ki-67 (AUROC 0.81, 95% CI 0.80–0.83) both performed better than the non-quantitative model (AUROC 0.70, 95% CI 0.68–0.72). These results were preserved in the external UCMC cohort, where the ER/PR model (AUROC 0.86, 95% CI 0.80–0.92, p = 0.032) and the ER/PR/Ki-67 model (AUROC 0.87, 95% CI 0.81–0.93) outperformed the non-quantitative model (AUROC 0.80, 95% CI 0.73–0.87, p = 0.009). The high sensitivity rule-out threshold of the ER/PR model predicted that 30% of patients in the UCMC cohort would be low ODX, and the ER/PR/Ki-67 model predicted 44% as low risk – negative predictive value was over 96% for prediction of high ODX. Of the patients predicted to be low risk by the quantitative models, none had a documented high ODX score, and recurrence was < 3% at 5 years. The hazard ratio for recurrence free interval, adjusted for age and comorbidity score, of patients predicted to be high risk by this threshold was 2.96 (95% CI 1.02–8.58) for the ER/PR model and 3.84 (95% CI 1.48–9.97) for the ER/PR/Ki-67 model. Conclusions: We present externally validated and nationally applicable models that identify approximately half of HR-positive/HER2-negative breast cancer patients who are unlikely to have high ODX results using widely available quantitative clinicopathologic variables. Patients identified as low risk by these models have excellent long-term outcomes and may be able to forgo adjuvant chemotherapy without further genomic testing. Citation Format: Asim Dhungana, Augustin Vannier, Fangyuan Zhao, Jincong Freeman, Poornima Saha, Megan Sullivan, Katharine Yao, Elbio Flores, Olufunmilayo Olopade, Dezheng Huo, Alexander Pearson, Frederick Howard. Development and Validation of a Breast Cancer Recurrence Model Demonstrates Accurate Identification of Patients with Favorable Long-Term Outcomes [abstract]. In: Proceedings of the 2023 San Antonio Breast Cancer Symposium; 2023 Dec 5-9; San Antonio, TX. Philadelphia (PA): AACR; Cancer Res 2024;84(9 Suppl):Abstract nr PO1-01-11.

Abstract Introduction The objective of this study was to examine the impact of the early part of the COVID‐19 pandemic on the number of newly diagnosed breast cancer cases at Commission on Cancer (CoC)‐accredited facilities relative to the United States (U.S.) population. Methods We examined the incidence of breast cancer cases at CoC sites using the U.S. Census population as the denominator. Breast cancer incidence was stratified by patient age, race and ethnicity, and geographic location. Results A total of 1,499,806 patients with breast cancer were included. For females, breast cancer cases per 100,000 individuals went from 188 in 2015 to 203 in 2019 and then dropped to 176 in 2020 with a 15.7% decrease from 2019 to 2020. Breast cancer cases per 100,000 males went from 1.7 in 2015 to 1.8 in 2019 and then declined to 1.5 in 2020 with a 21.8% decrease from 2019 to 2020. For both females and males, cases per 100,000 individuals decreased from 2019 to 2020 for almost all age groups. For females, rates dropped from 2019 to 2020 for all races and ethnicities and geographic locations. The largest percent change was seen among Hispanic patients (−18.4%) and patients in the Middle Atlantic division (−18.6%). The stage distribution (0–IV) for female and male patients remained stable from 2018 to 2020. Conclusion The first year of the COVID‐19 pandemic was associated with a decreased number of newly diagnosed breast cancer cases at Commission on Cancer sites.