McLaughlin, Sarah A.

ABSTRACT Background Evaluating fairness in artificial intelligence (AI) is essential before clinical implementation to prevent unintended harm across diverse patient populations. This study assesses performance differences of an image-based surgical site infection (SSI) detection model across age, gender, geography, race, and skin color. Methods Model development/validation study using retrospective, multicenter data across surgical subspecialties from adults who submitted an image of their incision via the electronic health record within 30 days of their procedure between 2019-2024. Area under receiver operating curve (AUROC) was compared by age (<55 vs. ≥55 years old), gender (male vs. female), geography (Rochester, Minnesota vs. Jacksonville, Florida vs. Scottsdale, Arizona vs. regional Minnesota/Wisconsin areas), race (White/Caucasian vs. non-White/Caucasian), and skin color (Fitpatrick I-III vs. IV-VI and Monk A-E vs. F-J). Results Training data contained 13,702 images from 4,274 patients between 2019-2022 (50.1% ≥55 years old; 63.2% female; 91.6% White/Caucasian; 58.5% Rochester, 17.3% Florida, 10.5% Arizona; 96.3% light skin tone), of which 1,348 images (9.8%) had an SSI. No differences in SSI detection existed for age, gender, race, or skin color (AUROC 0.83-0.87, p>0.09), however geographical differences were significant: lowest AUROC 0.83 (95% CI 0.77-0.88) vs. highest AUROC 0.87 (95% CI 0.84-0.89, p=0.01). Temporal validation using 4,242 images from 1,353 patients between 2022-2023 showed intact fairness across subgroups (ΔAUROC ≤0.06) except geography (ΔAUROC ≤0.16). Conclusions The model behaved fairly across age, gender, race, and skin color, however geographical differences persisted. These findings have practical implications underscoring the importance of evaluating bias in clinical AI before deployment.

ABSTRACT The normal adult male breast has not been characterized at single-cell resolution, leaving the cellular basis of male breast cancer (MBC) biology undefined. Here we present an integrated single-cell RNA sequencing atlas of the adult human breast comprising 174,471 cells from 17 donors (3 male, 14 female), including 18,117 male-derived cells. This revealed that the male breast retains all three epithelial populations, basal (BC), luminal progenitor (LP), and luminal committed cells (LC), but with an increase in LC at the expense of BC and LP across all three male donors. Male LC were distinguished from female by elevated ESR1 and PGR mRNA, enrichment of RNA processing and ribosome biogenesis programs, reduced inflammatory cytokine and growth factor signaling, elevated estradiol gene set enrichment scores, and higher inferred activity of developmental patterning transcription factors. This pattern was observed across differential expression, gene ontology, ligand profiling, and regulon-based analyses, and was not restricted to sex chromosome-linked gene expression. This is consistent with the near-universal estrogen receptor (ER) positivity that characterizes MBC clinically. This atlas provides the first cellular and transcriptional reference for the normal male breast and a resource for investigating sex differences in mammary biology, germline susceptibility variant interpretation, and modeling breast malignancies.

Background Breast cancer-related lymphedema (BCRL) is a common and life-long adverse event affecting ~20% of breast cancer survivors. As existing non-pharmacologic management is burdensome, expensive, and variably effective, this systematic scoping review aims to identify pharmacologic and herbal agents for prevention and treatment for BCRL. Methods PubMED, Embase, Web of Science Core collection, and the Cumulative Index to Nursing and Allied Health Literature were searched for studies published in English between 1993 and 2025 that investigated the preventative or therapeutic effect of pharmacologic or herbal agents on BCRL among adult stage I-III breast cancer patients. Studies describing interventions with systemically absorbed anti-inflammatories, anti-thrombotics, anti-coagulants, and blood product components were included. Systematic reviews, protocols for ongoing clinical trials, preclinical and non-human studies, editorials, and studies not exclusive to BCRL were excluded. Three reviewers screened and extracted data between June and August 2025. The primary outcomes of interest were reduction in BCRL incidence or severity. Results Of the 217 articles screened, 37 were included in the final review. After full text review, 13 were excluded for repetitive data, non-English language, or irrelevant outcomes. The 24 studies included in the analysis investigated anti-diabetic, herbal, anti-inflammatory, anti-hypertensive, immunomodulatory, and microbiome modifying agents, and venoactive flavinoid derivates. Three studies explored the role of pharmacologic/herbal agents in BCRL prevention. While thiazolidinediones, anti-hypertensives, and non-steroidal anti-inflammatory drugs (NSAIDs) had no effect on BCRL incidence, glucagon-like peptide-1 receptor agonists (GLP-1 RA) were associated with BCRL prevention. In the 21 studies that assessed the effect of pharmacologic/herbal agents in BCRL treatment, NSAIDs/steroids, anti-hypertensives, microbiome/synbiotic supplements, and doxycycline showed no benefit and data for flavonoid-derived venoactive agents and herbal products were inconsistent. Immune-modulating therapies were associated with improved BCRL signs/symptoms in three studies. Conclusion This systematic scoping review found limited evidence suggesting that GLP-1 RAs may reduce the risk of BCRL and that immunomodulatory agents may improve signs/symptoms of BCRL. Rigorous prospective trials using standardized limb volume/edema, quality-of-life (QoL), and symptom measures and longer follow-up are needed to inform clinical practice aimed at preventing and treating BCRL. Systematic review registration https://www.crd.york.ac.uk/PROSPERO/ , identifier CRD420251055134.

Objective: To develop an artificial intelligence–based pipeline to assess and triage patient-submitted postoperative wound images. Background: The rise of outpatient surgeries, remote monitoring, and patient-submitted wound images via online portals has contributed to a growing administrative workload on clinicians. Early identification of surgical site infection (SSI) is essential for reducing postoperative morbidity. Methods: Patients ≥18 years old who underwent surgery at 9 affiliated Mayo Clinic hospitals (2019-2022) and were captured by the National Surgical Quality Improvement Program (NSQIP) were included. Eligibility required submission of one image via the patient portal within 30 days after surgery. Images were independently screened in duplicate to determine the presence of an incision. SSI outcomes were obtained from NSQIP. The developed model consisted of 2 stages: incision detection and SSI detection in images with incisions. Four pretrained architectures were evaluated using 10-fold cross-validation, with upsampling and data augmentation to mitigate class imbalance. An end-to-end pipeline, image quality assessment and sensitivity analysis stratified by race were also performed. Results: Among 6060 patients, the median age was 54 years (interquartile range: 40–65), 61.4% (n=3805) were female, and 92.5% (n=5731) identified as White. SSIs were confirmed in 6.2% (n=386) images. Vision Transformer outperformed all others, achieving an incision detection accuracy of 0.94 (area under the curve=0.98) and an SSI detection accuracy of 0.73 (area under the curve=0.81). In addition, it demonstrated strong performance in assessing image quality. Sensitivity analysis revealed comparable performance across racial subgroups. Conclusion: This artificial intelligence pipeline demonstrates promising performance in automating wound image assessment and SSI detection, reducing clinical workload and improving postoperative care.

Abstract: Lymphedema is a prevalent, incurable, and morbid condition with the potential to degrade the health and quality of life of patients living with cancer and beyond cancer. Effective long term control requires coordination by an interdisciplinary team to ensure that lymphedema progression, complications, and related disablement are detected and appropriately addressed. This review provides an overview of lymphatic function and lymphedema pathogenesis with focused discussion of the unique characteristics of cancer related lymphedema (CRL) including natural history, clinical presentation, and risk factors for onset and progression. Surgical practice changes and supportive evidence for lymph node sparing and lymphatic reconstruction for CRL prevention are described. The review outlines evaluations to diagnose, stage, and monitor CRL, and characterizes evidence for current CRL prevention and management practices, including surgeries to restore lymphatic function. Multimodal management with complete decongestive therapy remains first line treatment for CRL, though patient-specific customization might be required to optimize patients’ clinical response and quality of life as outlined in the review.

e12615 Background: Breast MRI after completion of neoadjuvant chemotherapy (NAC) has demonstrated high sensitivity and positive predictive value in evaluating response to NAC. It is widely recognized as the most accurate imaging technique for assessing tumor response, outperforming mammography and ultrasound. However, there remains a knowledge gap in its potential as an early predictor of pathological response, when performed at the midpoint of NAC. Here, we investigated the correlation between MRI findings at the midpoint of NAC and subsequent pathological response at definitive surgery. Methods: A retrospective study was performed of patients with breast cancer who received NAC at Mayo Clinic, Florida and had at least 2 breast MRIs, one at midpoint and one either pre- or post-treatment. Patients with prior ipsilateral breast cancer were excluded. Participants were stratified into three molecular subtypes: hormone receptor-positive (HR+), HER2-positive (HER2+), and triple-negative breast cancer (TNBC). All MRIs were re-reviewed by dedicated breast radiologists, with tumor response classified as complete response (CR), partial response (PR), stable disease (SD), or progressive disease (PD) based on RECIST criteria. Pathological outcomes, including pathologic complete response (pCR) and residual cancer burden (RCB), were extracted from pathology reports and confirmed by a single breast pathologist, as indicated. pCR was defined as the absence of residual invasive tumor in both the breast and axillary lymph nodes. Results: A total of 154 patients met inclusion criteria from 2012 to 2022. Similar to previous studies, the positive predictive value for the post-treatment MRI was high at 82.4%, with 14 of 17 patients with imaging complete responses (iCR) achieving pCR. For the midpoint MRI, the positive predictive value for patients with iCR was 100%, with 8 out of 8 patients achieving pCR. Patients with certain subtypes of breast cancer with at least PR in both breast and axillary lymph nodes at midpoint MRI had numerically higher pCR rate, specifically HER2+ (22/37, 59.5%) and TNBC (8/13, 61.5%) but not HR+ tumors (12/45, 26.7%). In contrast, patients with less than PR in either breast or axillary lymph nodes showed numerically lower rate pCR in TNBC (7/18, 38.9%) and HR+ tumors (3/18, 16.7%). However, 15/23 (65.2%) patients with HER2+ tumors achieved pCR despite having less than PR at midpoint MRI. Conclusions: Midpoint breast MRI may serve as an early predictor of pathological response, particularly in patients with iCR. Patients with less than PR, especially those with HR+ and TNBC, have lower chances of achieving pCR. These findings highlight the importance of considering additional therapies for these subgroups of patients to improve the treatment outcomes, as they are less likely to achieve pCR with the current standard neoadjuvant chemotherapy regimen.

Abstract Purpose: Black women are disproportionately affected by aggressive breast cancers compared to white women, suggesting underlying biological differences in normal breast tissue. This study aims to identify molecular disparities in normal breast tissue between premenopausal Black and white women that may contribute to increased breast cancer risk. Experimental Procedures: Visium spatial transcriptomic analysis was performed on a pilot cohort of normal breast tissue samples from premenopausal Black and white women. Tissue sections were spatially profiled, and capture spots were classified based on predominant cell types: epithelial, stromal, or endothelial. Differential gene expression analysis between racial groups was conducted for each cell type classification. Multiplex immunofluorescence (mIF) was used to validate selected markers in the pilot cohort. Meta-analysis compared differentially expressed genes with published gene sets associated with breast cancer subtypes. Results: Significant racial differences in gene expression profiles were identified in both epithelial and stromal spots. In epithelial spots, genes upregulated in Black women significantly overlapped with over 20 published gene sets associated with estrogen receptor-negative (ER−) breast cancer, including key genes involved in Wnt signaling inhibition (e.g., WIF1) and basal epithelial markers (e.g., KRT14, KRT15). This suggests alterations in pathways linked to more aggressive breast cancer phenotypes. In stromal spots, differentially expressed genes related to extracellular matrix remodeling and fibroblast activation (e.g., PI16, DPT, EFEMP1) were observed, indicating potential differences in stromal-epithelial interactions. Ongoing deconvolution and spatial analyses are being performed to further elucidate these findings. Preliminary mIF validation confirmed increased expression of PI16 in samples from Black women. Validation of additional markers is underway in a larger cohort of premenopausal Black and white women. Conclusions: Spatial transcriptomic profiling of normal breast tissue reveals distinct molecular differences between Black and white women, particularly in pathways associated with aggressive breast cancer subtypes and stromal interactions. These findings suggest that inherent variations in the normal breast microenvironment may contribute to the increased risk and aggressiveness of breast cancer in Black women. Further validation and analysis may identify potential biomarkers for risk assessment and inform targeted prevention strategies. Citation Format: Camila Pacheco Erak, Nicole Cruz-Reyes, Pria Westerman, Joshua Ogony, Jean R. Clemenceau, Tae Hyun Hwang, Sarah McLaughlin, Derek Radisky. Spatial transcriptomic profiling of normal breast tissue reveals potential mechanisms underlying increased breast cancer risk in Black women [abstract]. In: Proceedings of the American Association for Cancer Research Annual Meeting 2025; Part 1 (Regular Abstracts); 2025 Apr 25-30; Chicago, IL. Philadelphia (PA): AACR; Cancer Res 2025;85(8_Suppl_1):Abstract nr 765.

Abstract Background: Postpartum breast cancer (PPBC) is associated with increased morbidity and mortality among women within 5 to 10 years following childbirth. The postpartum breast undergoes involution, involving tissue remodeling and immune cell infiltration, potentially creating a pro-tumorigenic microenvironment. The molecular mechanisms underlying this elevated risk remain poorly understood. In this study, we compared normal breast tissue samples and human mammary epithelial cells (HMECs) from postpartum women to those from age- and BMI-matched nulliparous women to elucidate potential molecular contributors to PPBC risk. Methods: Transcriptomic profiling was performed on RNA extracted from FFPE normal breast tissues using the NanoString IO 360 and BC 360 platforms to examine gene expression in nulliparous and postpartum women under 45 years of age. HMECs were isolated from organoids derived from breast tissue samples and used for next-generation sequencing and knockdown experiments targeting STAT1 and GBP1. Gene set enrichment analysis (GSEA) was applied to NanoString and RNA-seq datasets to identify differentially enriched genes between postpartum and nulliparous women. Results: Transcriptomic analysis revealed significant upregulation of interferon-stimulated genes, including STAT1 and GBP1, in postpartum breast tissues, consistent with increased immune responses during involution. NanoString data showed that markers of cell proliferation, such as Ki67, STAT1, and GBP1, were significantly higher in samples from parous compared to nulliparous women (p &lt; 0.05). GSEA revealed that cell cycle-promoting genes (GBP1, cyclins, CDKs) were upregulated, while cyclin-dependent kinase inhibitors (CDKNs) were downregulated in postpartum breast tissues. Immunohistochemistry confirmed significantly higher expression of Ki67, STAT1, and GBP1 in postpartum versus nulliparous breast tissues (p &lt; 0.0001). Silencing STAT1 and GBP1 in HMECs resulted in decreased cell proliferation, G1 cell cycle arrest, and increased expression of CDKN1A and CDKN1C. Conclusion: These findings suggest that STAT1 and GBP1 promote proliferation in postpartum breast epithelial cells by downregulating cyclin-dependent kinase inhibitors, potentially contributing to the increased risk of PPBC. Targeting these pathways may offer novel strategies for mitigating postpartum breast cancer risk. Citation Format: Joshua Ogony, Melody Stallings-Mann, Sarah McLaughlin, Mark Sherman, Derek C. Radisky. STAT1 and GBP1 promote proliferation in postpartum breast epithelium by downregulating cyclin-dependent kinase inhibitors: implications for increased postpartum breast cancer risk [abstract]. In: Proceedings of the American Association for Cancer Research Annual Meeting 2025; Part 1 (Regular Abstracts); 2025 Apr 25-30; Chicago, IL. Philadelphia (PA): AACR; Cancer Res 2025;85(8_Suppl_1):Abstract nr 187.

Background: Immediate lymphatic reconstruction (ILR) via lymphovenous anastomosis is performed in patients undergoing axillary lymph node dissection (ALND) to minimize the risk of lymphedema. Following ALND, drains are placed to prevent seromas, while prolonged drain days are associated with increased risk of infection. The study aim was to determine the impact of ILR on the number of drain days following ALND in patients with breast cancer. Methods: We report a post-hoc analysis of a prospective trial (April 2018-January 2023) comparing patients with breast cancer who underwent ALND with ILR (intervention arm) vs ALND without ILR (control arm). Wilcoxon rank sum test and chi-squared or Fisher’s exact tests compared continuous and categorical variables, respectively. Multivariable quantile regression models evaluated the difference in drain days and days until drain removal criteria were met with covariates adjusted. Results: Data from 214 patients were analyzed (n = 115 interventional arm, n = 99 control arm). The intervention arm had a median of 15 axillary drain days compared to 11 days in the control arm ( P = .001). There was no significant difference between groups when measuring drain days based on the date the drain met removal criteria, rather than actual drain removal date. Seroma incidence was lower in the intervention arm (3.5%) vs the control arm (12.1%) ( P = .017) without a statistical difference in incidence of infection. Conclusion: ALND with ILR does not decrease the number of drain days compared to ALND without ILR in patients with breast cancer, although we found the incidence of seromas to be lower without increase in incidence of infection.