Early life body size and puberty markers as predictors of breast cancer risk later in life: A neural network analysis.

BACKGROUND: The early life factors of birthweight, child weight, height, body mass index (BMI) and pubertal timing are associated with risks of breast cancer. However, the predictive value of these factors in relation to breast cancer is largely unknown. Therefore, using a machine learning approach, we examined whether birthweight, childhood weights, heights, BMIs, and pubertal timing individually and in combination were predictive of breast cancer. METHODS: We used information on birthweight, childhood height and weight, and pubertal timing assessed by the onset of the growth spurt (OGS) from 164,216 girls born 1930-1996 from the Copenhagen School Health Records Register. Of these, 10,002 women were diagnosed with breast cancer during 1977-2019 according to a nationwide breast cancer database. We developed a feed-forward neural network, which was trained and tested on early life body size measures individually and in various combinations. Evaluation metrics were examined to identify the best performing model. RESULTS: The highest area under the receiver operating curve (AUC) was achieved in a model that included birthweight, childhood heights, weights and age at OGS (AUC = 0.600). A model based on childhood heights and weights had a comparable AUC value (AUC = 0.598), whereas a model including only childhood heights had the lowest AUC value (AUC = 0.572). The sensitivity of the models ranged from 0.698 to 0.760 while the precision ranged from 0.071 to 0.076. CONCLUSION: We found that the best performing network was based on birthweight, childhood weights, heights and age at OGS as the input features. Nonetheless, this performance was only slightly better than the model including childhood heights and weights. Further, although the performance of our networks was relatively low, it was similar to those from previous studies including well-established risk factors. As such, our results suggest that childhood body size may add additional value to breast cancer prediction models.

Trajectories of body mass index across the lifecourse and associations with post-menopausal breast cancer by estrogen receptor status.

BACKGROUND: Associations between a high body mass index (BMI) at single timepoints during child- and adulthood and risks of post-menopausal breast cancer are well-established, but associations with BMI across the lifecourse remains largely unknown. Therefore, we examined whether lifecourse BMI trajectories were associated with risks of post-menopausal breast cancer overall and by estrogen receptor (ER) status. METHODS: We included 6698 Danish women born 1930-1946. Information on BMI at ages 6-15 years came from the Copenhagen School Health Records Register, and information on BMI at ages 20, 30, 40, 50 and/or 50-64 years came from the Diet, Cancer and Health cohort. Breast cancer cases (n = 577) were identified in the Danish Breast Cancer Cooperative Group database. Six BMI trajectories were identified using latent class trajectory modelling. Hazard ratios (HR) and 95% confidence intervals (CI) were estimated using Cox regression models. RESULTS: Compared to women with a trajectory characterized by an average BMI gain across life, women with the two trajectories with steep increases in BMI during childhood and adolescence that thereafter largely stabilized, had lower risks of post-menopausal breast cancer and ER-positive tumors. The adjusted HRs for ER-positive tumors were 0.67 (95% CI: 0.47-0.95) and 0.68 (95% CI: 0.46-1.01), respectively. In contrast, women with a trajectory with a low gain in BMI during childhood and adolescence followed by a subsequent steep increase during adulthood, had higher risks of post-menopausal breast cancer and ER-positive tumors when compared to women with an average BMI gain. The adjusted HR for ER-positive tumors was 1.28 (95% CI: 0.98-1.67). CONCLUSIONS: Our findings suggest that the timing of excess gain in BMI across the lifecourse impacts subsequent post-menopausal breast cancer risks. Thus, the BMI development across life is likely useful in the identification of women at increased risks of post-menopausal breast cancer.

Epigenetic Profiles of Triple-Negative Breast Cancers of African American and White Females.

Importance: Triple-negative breast cancer (TNBC) is the most aggressive breast cancer subtype and appears to have disproportionately higher incidence and worse outcomes among younger African American females. Objective: To investigate whether epigenetic differences exist in TNBCs of younger African American females that may explain clinical disparities seen in this patient group. Design, Setting, and Participants: This cross-sectional study used clinical, demographic, DNA methylation (HumanMethylation450; Illumina), and gene expression (RNA sequencing) data for US patient populations from publicly available data repositories (The Cancer Genome Atlas [TCGA], 2006-2012, and Gene Expression Omnibus [GEO], 2004-2013) accessed on April 13, 2021. White and African American females with TNBC identified in TCGA (69 patients) and a validation cohort of 210 African American patients from GEO (GSE142102) were included. Patients without available race or age data were excluded. Data were analyzed from September 2022 through April 2023. Main Outcomes and Measures: DNA methylation and gene expression profiles of TNBC tumors by race (self-reported) and age were assessed. Age was considered a dichotomous variable using age 50 years as the cutoff (younger [<50 years] vs older [≥50 years]). Results: A total of 69 female patients (34 African American [49.3%] and 35 White [50.7%]; mean [SD; range] age, 55.7 [11.6; 29-82] years) with TNBC were included in the DNA methylation analysis; these patients and 210 patients in the validation cohort were included in the gene expression analysis (279 patients). There were 1115 differentially methylated sites among younger African American females. The DNA methylation landscape on TNBC tumors in this population had increased odds of enrichment of hormone (odds ratio [OR], 1.82; 95% CI, 1.21 to 2.67; P = .003), muscle (OR, 1.85; 95% CI, 1.44 to 2.36; P < .001), and proliferation (OR, 3.14; 95% CI, 2.71 to 3.64; P < .001) pathways vs other groups (older African American females and all White females). Alterations in regulators of these molecular features in TNBCs of younger African American females were identified involving hormone modulation (downregulation of androgen receptor: fold change [FC] = -2.93; 95% CI, -4.76 to -2.11; P < .001) and upregulation of estrogen-related receptor α (FC = 0.86; 95% CI, 0.34 to 1.38; P = .002), muscle metabolism (upregulation of FOXC1: FC = 1.33; 95% CI, 0.62 to 2.03; P < .001), and proliferation mediators (upregulation of NOTCH1: FC = 0.71; 95% CI, 0.23 to 1.19; P = .004 and MYC (FC = 0.81; 95% CI, 0.18 to 1.45; P = .01). Conclusions and Relevance: These findings suggest that TNBC of younger African American females may represent a distinct epigenetic entity and offer novel insight into molecular alterations associated with TNBCs of this population. Understanding these epigenetic differences may lead to the development of more effective therapies for younger African American females, who have the highest incidence and worst outcomes from TNBC of any patient group.

NCCN Guidelines® Insights: Breast Cancer Screening and Diagnosis, Version 1.2023.

The NCCN Guidelines for Breast Cancer Screening and Diagnosis provide health care providers with a practical, consistent framework for screening and evaluating a spectrum of clinical presentations and breast lesions. The NCCN Breast Cancer Screening and Diagnosis Panel is composed of a multidisciplinary team of experts in the field, including representation from medical oncology, gynecologic oncology, surgical oncology, internal medicine, family practice, preventive medicine, pathology, diagnostic and interventional radiology, as well as patient advocacy. The NCCN Breast Cancer Screening and Diagnosis Panel meets at least annually to review emerging data and comments from reviewers within their institutions to guide updates to existing recommendations. These NCCN Guidelines Insights summarize the panel's decision-making and discussion surrounding the most recent updates to the guideline's screening recommendations.

Early childhood adversity and body mass index in childhood and adolescence: linking registry data on adversities with school health records of 53,401 children from Copenhagen.

OBJECTIVE: We examined whether childhood adversity experienced in early childhood (0-5 years) is related to body mass index (BMI) in childhood (6-7 years) and adolescence (12-15 years). METHODS: This study combined data from the nationwide register-based DANLIFE study on childhood adversities with data on height and weight of school children in Copenhagen. Data were available for 53,401 children born in Denmark between 1980 and 1996. Children were divided into groups of early childhood adversity by applying group-based multi-trajectory modelling using their yearly count of childhood adversity in three dimensions (i.e., material deprivation, loss or threat of loss, and family dynamics) from 0-5 years. Direct and total associations between the early childhood adversity groups and BMI z-scores in childhood and adolescence were estimated using sex-stratified structural equation models. RESULTS: Five exclusive and exhaustive groups of early childhood adversity were identified, which were characterized by low adversity (51%), moderate material deprivation (30%), high material deprivation (14%), loss or threat of loss (3%) and high adversity (2%). Boys and girls exposed to moderate or high material deprivation and loss or threat of loss had a slightly higher BMI z-score, especially in adolescence, compared with those in the low adversity group, with the strongest association found for girls in the loss or threat of loss group (b (95% CI) = 0.18 (0.10, 0.26)). Additionally, boys in the high adversity group had a slightly lower BMI z-score in childhood than boys in the low adversity group (b (95% CI) = -0.12 (-0.22, -0.02)). CONCLUSIONS: Whereas associations with BMI were found for children and adolescents exposed to material deprivation, loss or threat of loss, and high adversity, the effect sizes were generally small. Contrary to prevailing hypotheses, weight changes in childhood is probably not a major explanatory mechanism linking early childhood adversity with later-life morbidity.

Construction and validation of a gene expression classifier to predict immunotherapy response in primary triple-negative breast cancer.

BACKGROUND: Immune checkpoint inhibitors (ICI) improve clinical outcomes in triple-negative breast cancer (TNBC) patients. However, a subset of patients does not respond to treatment. Biomarkers that show ICI predictive potential in other solid tumors, such as levels of PD-L1 and the tumor mutational burden, among others, show a modest predictive performance in patients with TNBC. METHODS: We built machine learning models based on pre-ICI treatment gene expression profiles to construct gene expression classifiers to identify primary TNBC ICI-responder patients. This study involved 188 ICI-naïve and 721 specimens treated with ICI plus chemotherapy, including TNBC tumors, HR+/HER2- breast tumors, and other solid non-breast tumors. RESULTS: The 37-gene TNBC ICI predictive (TNBC-ICI) classifier performs well in predicting pathological complete response (pCR) to ICI plus chemotherapy on an independent TNBC validation cohort (AUC = 0.86). The TNBC-ICI classifier shows better performance than other molecular signatures, including PD-1 (PDCD1) and PD-L1 (CD274) gene expression (AUC = 0.67). Integrating TNBC-ICI with molecular signatures does not improve the efficiency of the classifier (AUC = 0.75). TNBC-ICI displays a modest accuracy in predicting ICI response in two different cohorts of patients with HR + /HER2- breast cancer (AUC = 0.72 to pembrolizumab and AUC = 0.75 to durvalumab). Evaluation of six cohorts of patients with non-breast solid tumors treated with ICI plus chemotherapy shows overall poor performance (median AUC = 0.67). CONCLUSION: TNBC-ICI predicts pCR to ICI plus chemotherapy in patients with primary TNBC. The study provides a guide to implementing the TNBC-ICI classifier in clinical studies. Further validations will consolidate a novel predictive panel to improve the treatment decision-making for patients with TNBC.

Triple-Negative Breast Cancer (TNBC) is an aggressive type of breast cancer, responsible for a substantial burden of breast cancer-related deaths. In recent years, immunotherapy, a therapy that triggers the patient's immune system to attack the tumor, has arisen as a promising treatment in various cancers, including TNBC. However, a subset of patients with TNBC does not respond to this treatment. Here, we employed advanced computational techniques to predict response to immunotherapy plus chemotherapy in patients with primary TNBC. Our method is more accurate than using other existing markers, such as PD-L1, but is not very accurate in patients with non-TNBC breast cancers or non-breast cancers. This method could potentially be used to better select patients for immunotherapy, upfront, avoiding the side effects and costs of treating patients in which immunotherapy might not work.

De-escalation of surgery for occult breast cancer with axillary metastasis.

Occult breast cancer presenting as axillary metastasis is rare and remains a diagnostic and therapeutic challenge. Evidence to guide clinical management is limited, and locoregional treatment remains nonstandardized and highly varied nationally. Historically, occult breast cancer was managed with modified radical mastectomy ± radiotherapy; however, equivalent local control and survival are observed with breast preservation and adjuvant whole breast radiotherapy. Axillary lymph node dissection remains the standard surgical approach to the axilla for occult breast cancer patients. De-escalating axillary surgery in a subset of occult breast cancer patients treated with neoadjuvant chemotherapy with good response to treatment may be appropriate, similar to the management of clinically node-positive patients in a known primary setting. As in other clinically node-positive breast cancer cases, thoughtful integration and tailoring of axillary surgery and regional nodal radiotherapy (for the varying extent of nodal burden) is an area of continued controversy and active investigation.

Advancing precision public health for obesity in children.

Worldwide, far too many children and adolescents are living with the disease of obesity. Despite decades of public health initiatives, rates are still rising in many countries. This raises the question of whether precision public health may be a more successful approach to preventing obesity in youth. In this review, the objective was to review the literature on precision public health in the context of childhood obesity prevention and to discuss how precision public health may advance the field of childhood obesity prevention. As precision public health is a concept that is still evolving and not fully identifiable in the literature, a lack of published studies precluded a formal review. Therefore, the approach of using a broad interpretation of precision public health was used and recent advances in childhood obesity research in the areas of surveillance and risk factor identification as well as intervention, evaluation and implementation using selected studies were summarized. Encouragingly, big data from a multitude of designed and organic sources are being used in new and innovative ways to provide more granular surveillance and risk factor identification in obesity in children. Challenges were identified in terms of data access, completeness, and integration, ensuring inclusion of all members of society, ethics, and translation to policy. As precision public health advances, it may yield novel insights that can contribute to strong policies acting in concert that ultimately lead to the prevention of obesity in children.

Birth weight, childhood body mass index, and risk of diverticular disease in adulthood.

OBJECTIVE: Adult overweight is associated with increased risk of diverticular disease (DD). We investigated associations between birthweight and childhood body mass index (BMI) and DD. METHODS: Cohort study of 346,586 persons born during 1930-1996 with records in the Copenhagen School Health Records Register. Data included birthweight, and height and weight from ages 7 through 13. We used Cox proportional hazard regression to examine associations between birthweight and BMI z-scores and DD registered in the Danish National Patient Registry. Due to non-proportionality, we followed participants from age 18-49 and from age 50. RESULTS: During follow-up, 5459 (3.2%) women and 4429 (2.5%) men had DD. For low and high BMI in childhood, we observed a higher risk of DD before age 50. Among women with z-scores <0 at age 13, the hazard ratio (HR) was 1.16 [95% confidence interval (CI): 0.98-1.39] per one-point lower z-score. For z-scores ≥0 at age 13, the HR was 1.30 (95% CI: 1.11-1.51) per one-point higher z-score. Among men with z-scores <0 at age 13, the HR was 1.02 (95% CI: 0.85-1.22). For z-scores ≥0 at age 13, the HR was 1.54 (95% CI: 1.34-1.78). Z-scores ≥0 were not associated with DD after age 50. Among women only, birthweight was inversely associated with DD before age 50 [HR = 0.90 (95% CI: 0.83-0.99) per 500 g higher birthweight]. CONCLUSION: BMI z-scores below and above zero in childhood were associated with higher risk of DD before age 50. In addition, we observed lower risk of DD among women, the higher their birthweight.

Childhood body mass index trajectories, adult-onset type 2 diabetes, and obesity-related cancers.

BACKGROUND: Elevated childhood body mass index (BMI), commonly examined as a "once-only" value, increases the risk of cancer and type 2 diabetes (T2D) in adulthood. Continuous exposure to adiposity during childhood may further increase cancer risk. We examined whether longitudinal childhood BMI trajectories were associated with adult obesity-related cancer and the role of adult-onset T2D in these associations. METHODS: Five sex-specific latent class BMI trajectories were generated for 301 927 children (149 325 girls) aged 6-15 years from the Copenhagen School Health Records Register. Information on obesity-related cancers and T2D was obtained from national health registers. Incidence rate ratios (IRR), cumulative incidences, and confidence intervals (CI) were estimated using Poisson regressions. RESULTS: Compared with the average childhood BMI trajectory (containing approximately 40% of individuals), the rate of obesity-related cancer (excluding breast cancer) increased with higher childhood BMI trajectories among women. The highest rates occurred in the overweight (IRR = 1.27, 95% CI = 1.17 to 1.38) and obesity (IRR = 1.79, 95% CI = 1.53 to 2.08) BMI trajectories. Similar patterns were observed among men. In contrast, women with the obesity childhood BMI trajectory had the lowest rate of pre- and postmenopausal breast cancer (IRR = 0.59, 95% CI = 0.43 to 0.80, and IRR = 0.41, 95% CI = 0.30 to 0.57, respectively). For all trajectories, the cumulative risk of obesity-related cancer increased with adult-onset T2D. CONCLUSION: Consistent childhood overweight or obesity may increase the rates of adult obesity-related cancer and decrease the rates of breast cancer. Adult-onset T2D conferred additional risk for obesity-related cancer, but the effect did not differ across childhood BMI trajectories.

The associations of maternal and paternal obesity with latent patterns of offspring BMI development between 7 and 17 years of age: pooled analyses of cohorts born in 1958 and 2001 in the United Kingdom.

OBJECTIVE: We aimed to 1) describe how the UK obesity epidemic reflects a change over time in the proportion of the population demonstrating adverse latent patterns of BMI development and 2) investigate the potential roles of maternal and paternal BMI in this secular process. METHODS: We used serial BMI data between 7 and 17 years of age from 13220 boys and 12711 girls. Half the sample was born in 1958 and half in 2001. Sex-specific growth mixture models were developed. The relationships of maternal and paternal BMI and weight status with class membership were estimated using the 3-step BCH approach, with covariate adjustment. RESULTS: The selected models had five classes. For each sex, in addition to the two largest normal weight classes, there were "normal weight increasing to overweight" (17% of boys and 20% of girls), "overweight increasing to obesity" (8% and 6%), and "overweight decreasing to normal weight" (3% and 6%) classes. More than 1-in-10 children from the 2001 birth cohort were in the "overweight increasing to obesity" class, compared to less than 1-in-30 from the 1958 birth cohort. Approximately 75% of the mothers and fathers of this class had overweight or obesity. When considered together, both maternal and paternal BMI were associated with latent class membership, with evidence of negative departure from additivity (i.e., the combined effect of maternal and paternal BMI was smaller than the sum of the individual effects). The odds of a girl belonging to the "overweight increasing to obesity" class (compared to the largest normal weight class) was 13.11 (8.74, 19.66) times higher if both parents had overweight or obesity (compared to both parents having normal weight); the equivalent estimate for boys was 9.01 (6.37, 12.75). CONCLUSIONS: The increase in obesity rates in the UK over more than 40 years has been partly driven by the growth of a sub-population demonstrating excess BMI gain during adolescence. Our results implicate both maternal and paternal BMI as correlates of this secular process.

Birthweight, childhood body size, and timing of puberty and risks of breast cancer by menopausal status and tumor receptor subtypes.

BACKGROUND: Associations of birthweight, childhood body size and pubertal timing with breast cancer risks by menopausal status and tumor receptor subtypes are inconclusive. Thus, we investigated these associations in a population-based cohort of Danish women. METHODS: We studied 162,419 women born between 1930 and 1996 from the Copenhagen School Health Records Register. The register includes information on birthweight, measured childhood weights and heights at the age of 7-13 years, and computed ages at the onset of the growth spurt (OGS) and at peak height velocity (PHV). The Danish Breast Cancer Cooperative Group database provided information on breast cancer (n = 7510), including estrogen receptor (ER), human epidermal growth factor receptor 2 (HER2) and menopausal status. Hormone replacement therapy use came from the Danish National Prescription Registry. Hazard ratios (HR) and 95% confidence intervals (CI) were estimated by Cox regression. RESULTS: We found that birthweight was not associated with any breast cancer subtypes. While childhood BMI was not statistically significantly associated with ER+ tumors nor consistently with ER- tumors among pre-menopausal women, consistent inverse associations were found among postmenopausal women. At the age of 7 years, the HRs for postmenopausal ER+ and ER- tumors were 0.90 (95% CI 0.87-0.93) and 0.84 (95% CI 0.79-0.91) per BMI z-score, respectively. Similarly, childhood BMI was inversely associated with pre- and postmenopausal HER2- tumors, but not with HER2+ tumors. Childhood height was positively associated with both pre- and postmenopausal ER+ tumors, but not with ER- tumors. At the age of 7 years, the HRs for postmenopausal ER+ and ER- tumors were 1.09 (95% CI 1.06-1.12) and 1.02 (95% CI 0.96-1.09) per height z-score, respectively. In general, childhood height was positively associated with HER2+ and HER2- tumors among pre- and postmenopausal women. Ages at OGS and PHV were not associated with any breast cancer subtypes. CONCLUSIONS: We showed that a high BMI and short stature in childhood are associated with reduced risks of certain breast cancer subtypes. Thus, childhood body composition may play a role in the development of breast cancer.

Childhood body mass index trajectories and associations with adult-onset chronic kidney disease in Denmark: A population-based cohort study.

BACKGROUND: Although excess adult adiposity is a strong risk factor for chronic kidney disease (CKD), evidence for associations with early life body size is limited. We investigated whether childhood body mass index (BMI) trajectories are associated with adult-onset CKD and end-stage kidney disease (ESKD) using a population-based cohort. Further, we examined the role of adult-onset type 2 diabetes (T2D) in these associations. METHODS AND FINDINGS: We included 151,506 boys and 148,590 girls from the Copenhagen School Health Records Register, born 1930 to 1987 with information on measured weights and heights at ages 6 to 15 years. Five sex-specific childhood BMI trajectories were analyzed. Information on the main outcomes CKD and ESKD, as well as T2D, came from national health registers. Incidence rate ratios (IRRs) and 95% confidence intervals (CIs) were estimated using Poisson regression adjusted for year of birth. During a median of 30.8 person-years of follow-up, 5,968 men and 3,903 women developed CKD and 977 men and 543 women developed ESKD. For both sexes, the rates of CKD and ESKD increased significantly with higher child BMI trajectories in comparison with the average BMI trajectory (40% to 43% of individuals) and the below-average BMI trajectory (21% to 23% of individuals) had the lowest rates. When including T2D, most associations were significant and men (IRR = 1.39, 95% CI: 1.13 to 1.72) and women (IRR = 1.54, 95% CI: 1.28 to 1.86) with the obese childhood BMI trajectory (2% of individuals) had significantly higher CKD rates than the average BMI trajectory, whereas for ESKD, the associations were positive, but nonsignificant, for men (IRR = 1.38, 95% CI: 0.83 to 2.31) but significant for women (IRR = 1.97, 95% CI: 1.25 to 3.11) with the obese BMI trajectory. A main study limitation is the use of only hospital-based CKD diagnoses. CONCLUSIONS: Individuals with childhood BMI trajectories above average had higher rates of CKD and ESKD than those with an average childhood BMI trajectory. When including T2D, most associations were significant, particularly with CKD, emphasizing the potential information that the early appearance of above-average BMI growth patterns provide in relation to adult-onset CKD beyond the information provided by T2D development.

Body mass index trajectories in childhood and incidence rates of type 2 diabetes and coronary heart disease in adulthood: A cohort study.

AIMS: We examined associations between five body mass index (BMI) trajectories from ages 6-15 years and register-based adult-onset type 2 diabetes mellitus (T2D) and coronary heart disease (CHD) with and without adjustment for adult BMI. METHODS: Child and adult BMI came from two Danish cohorts and 13,205 and 13,438 individuals were included in T2D and CHD analyses, respectively. Trajectories were estimated by latent class modelling. Incidence rate ratios (IRRs) were estimated with Poisson regression. RESULTS: In models without adult BMI, compared to the lowest trajectory, among men the T2D IRRs were 0.92 (95 %CI:0.77-1.09) for the second lowest trajectory and 1.51 (95 %CI:0.71-3.20) for the highest trajectory. The corresponding IRRs in women were 0.92 (95 %CI:0.74-1.16) and 3.58 (95 %CI:2.30-5.57). In models including adult BMI, compared to the lowest trajectory, T2D IRRs in men were 0.57 (95 %CI:0.47-0.68) for the second lowest trajectory and 0.26 (95 %CI:0.12-0.56) for the highest trajectory. The corresponding IRRs in women were 0.60 (95 %CI:0.48-0.75) and 0.59 (95 %CI:0.36-0.96). The associations were similar in direction, but not statistically significant, for CHD. CONCLUSIONS: Incidence rates of adult-onset T2D were greater for a high child BMI trajectory than a low child BMI trajectory, but not in models that included adult BMI.

Machine Learning-Based Epigenetic Classifiers for Axillary Staging of Patients with ER-Positive Early-Stage Breast Cancer.

BACKGROUND: In the era of molecular stratification and effective multimodality therapies, surgical staging of the axilla is becoming less relevant for patients with estrogen receptor (ER)-positive early-stage breast cancer (EBC). Therefore, a nonsurgical method for accurately predicting lymph node disease is the next step in the de-escalation of axillary surgery. This study sought to identify epigenetic signatures in the primary tumor that accurately predict lymph node status. PATIENTS AND METHODS: We selected a cohort of patients in The Cancer Genome Atlas (TCGA) with ER-positive, HER2-negative invasive ductal carcinomas, and clinically-negative axillae (n = 127). Clinicopathological nomograms from the Memorial Sloan Kettering Cancer Center (MSKCC) and the MD Anderson Cancer Center (MDACC) were calculated. DNA methylation (DNAm) patterns from primary tumor specimens were compared between patients with pN0 and those with > pN0. The cohort was divided into training (n = 85) and validation (n = 42) sets. Random forest was employed to obtain the combinations of DNAm features with the highest accuracy for stratifying patients with > pN0. The most efficient combinations were selected according to the area under the curve (AUC). RESULTS: Clinicopathological models displayed a modest predictive potential for identifying > pN0 disease (MSKCC AUC 0.76, MDACC AUC 0.69, p = 0.15). Differentially methylated sites (DMS) between patients with pN0 and those with > pN0 were identified (n = 1656). DMS showed a similar performance to the MSKCC model (AUC = 0.76, p = 0.83). Machine learning approaches generated five epigenetic classifiers, which showed higher discriminative potential than the clinicopathological variables tested (AUC > 0.88, p < 0.05). CONCLUSIONS: Epigenetic classifiers based on primary tumor characteristics can efficiently stratify patients with no lymph node involvement from those with axillary lymph node disease, thereby providing an accurate method of staging the axilla.