Search Results (2,517)

Background: While basal-like markers (BMs), particularly cytokeratin 5/6 (CK5/6) and epidermal growth factor receptor (EGFR), are traditionally associated with triple-negative breast cancer, their expression in HR+/HER2- tumors defines a clinically distinct subgroup with unique therapeutic vulnerabilities. We comprehensively characterized the clinicopathological features, immune microenvironment, and neoadjuvant immunotherapy response of BM-positive HR+/HER2- breast cancer. Methods: We analyzed 150 basal marker-positive (BM+) and 180 BM-negative HR+/HER2- breast cancer patients. Clinicopathological data and survival outcomes were assessed using Kaplan–Meier and Cox regression analyses. The immune microenvironment was characterized by stromal tumor-infiltrating lymphocytes (sTILs) and immunohistochemistry for immune markers (CD3, CD8, FOXP3, CXCL13, CD68, PD-1, PD-L1). An independent cohort of 53 BM+ patients receiving neoadjuvant chemotherapy with anti-PD-1/PD-L1 immunotherapy was evaluated for pathological complete response (pCR). Results: BM+ patients exhibited significantly more aggressive features: younger age at diagnosis, higher histological grade, increased necrosis, and lower hormone receptor expression. BM+ status independently predicted worse disease-free survival (HR = 1.96, p = 0.034) and overall survival (HR = 2.93, p = 0.037), with CK5/6 expression emerging as an independent prognostic factor for both endpoints. These tumors displayed an activated immune microenvironment with significantly higher sTILs, enhanced cytotoxic T-cell infiltration, and elevated PD-L1 expression. Remarkably, the neoadjuvant immunotherapy cohort achieved a pCR rate of 49.1%, comparable to triple-negative breast cancer rates and substantially exceeding historical HR+/HER2- benchmarks. Conclusions: The basal-like phenotype identifies a clinically aggressive subset of HR+/HER2- breast cancer with distinct immune-activated characteristics and remarkable immunotherapy response rates. These findings suggest that the BM status, particularly CK5/6 expression, may serve as a basis for clinicians to decide whether to administer immunotherapy to patients with HR+/HER2-breast cancer. Full article

Surface-Enhanced Raman Spectroscopy (SERS) has emerged as a powerful analytical platform for breast cancer (BC) detection, offering ultrasensitive, multiplexed, and label-free molecular recognition. However, despite the rapid expansion of the field, no prior study has combined quantitative bibliometric mapping with a cluster-validated technical and translational synthesis, limiting a comprehensive understanding of the field’s structure, evolution and clinical projection. In this review, a PRISMA-guided bibliometric analysis was conducted; 199 articles on SERS-based BC detection (2016–2025) were retrieved from SCOPUS, Web of Science and Google Scholar, mapping publication trends, keyword co-occurrence networks (VOSviewer), and Multiple Correspondence Analysis (MCA) with hierarchical clustering on principal components. The results reveal sustained growth in scientific output, led by Asia, North America, and Europe. The 20 most-cited articles (271 citations maximum) showed a shift from substrate optimization toward AI-assisted liquid biopsy platforms. MCA identified five clusters, corroborated by the co-occurrence network: (1) nanostructured platforms for diagnosis; (2) biofunctionalization strategies; (3) liquid biopsy approaches targeting exosomes, circulating tumor cells, and alternative biofluids; (4) diagnostic interpretation based on chemometrics, machine learning (ML) and artificial intelligence (AI); and (5) translational achievements in preclinical and clinical studies. Each cluster was anchored by a technical sub-analysis of its landmark studies, an integration largely absent from prior SERS reviews. This framework clarifies the field’s trajectory and positions SERS as a key technology for non-invasive, personalized diagnostics in precision oncology. Full article

Background: Triple-negative breast cancer (TNBC) is a highly aggressive subtype of breast cancer characterized by significant treatment challenges and poor prognosis. Traditional therapies such as surgical resection, radiotherapy, and chemotherapy often suffer from limitations including insufficient therapeutic specificity, potential damage to normal tissues, and limited imaging capability. The integrated diag{Pareja, 2018 #13}nosis-treatment platform combines diagnostic and therapeutic functions, offering a novel approach for real-time tumor monitoring and precision therapy. Methods: Accordingly, this study designed and developed an integrated diagnostic and therapeutic platform called A₂S-TT NPs, utilizing self-assembled nanoparticles incorporating organic conjugated molecules for precise photodynamic therapy (PDT) guided by dual modalities of Near-infrared II (NIR-II) fluorescence imaging and photoacoustic imaging (PA). Results: Under 808 nm laser excitation, A₂S-TT NPs efficiently generated reactive oxygen species (ROS) at the tumor site, inducing mitochondrial membrane potential disruption and DNA damage to activate apoptosis. In vitro experiments demonstrated that A₂S-TT NPs exhibited intense NIR-II fluorescence and photoacoustic signals, showcasing excellent dual-modal imaging potential. Moreover, it demonstrated minimal cytotoxicity in the absence of light exposure but significantly enhanced tumor cell killing under laser irradiation, demonstrating superior biosafety and photodynamic efficacy. In vivo studies further confirmed that A₂S-TT NPs effectively accumulated at tumor sites, enabling visualization-based monitoring through its mediated NIR-II and PA dual-modal imaging. Additionally, A₂S-TT NPs-mediated PDT exhibited remarkable tumor-suppressive effects while avoiding significant damage to normal tissues. Discussion: This study constructs a novel PA/NIR-II dual-modal imaging-guided PDT platform based on donor–acceptor conjugated polymer A₂S-TT NPs for integrated TNBC theranostics. PA provides high-resolution deep-tissue imaging, while NIR-II fluorescence offers high sensitivity and deep penetration; their complementary strengths support precise tumor localization and real-time therapeutic monitoring. Under dual-modal guidance, A₂S-TT NPs enrich in tumors and generate abundant ROS upon 808 nm laser irradiation to boost PDT efficacy. In vitro and in vivo biosafety tests confirm its favorable biocompatibility with minimal systemic toxicity at therapeutic doses. Conclusions: In conclusion, A₂S-TT NPs achieved precise, efficient, safe, and controllable PDT through dual-mode imaging using NIR-II and PA, providing a novel strategy with clinical translation potential for the integrated diagnosis and treatment of TNBC. Full article

Early and accurate cancer detection from medical imaging remains challenging because clinically relevant evidence is distributed across local image appearance, structural relationships between suspicious regions, and ordered imaging context. This study proposes a graph-aware and sequence-aware deep learning framework that combines a convolutional neural network (CNN) backbone for spatial feature extraction, a Graph Attention Network (GAT) for lesion-structure modelling, and a Bidirectional Long Short-Term Memory (BiLSTM) module for ordered-view or slice-sequence representation learning. Cross-attention-based multimodal fusion is evaluated exclusively for the RSNA mammography task, where the metadata branch is restricted to patient age and implant status, both available before diagnosis. In contrast, the primary LIDC-IDRI experiment is conducted as an image-only analysis because radiologist malignancy scores and semantic nodule attributes are annotation-derived variables and are not treated as independent clinical predictors. The framework is evaluated on the RSNA Breast Cancer Detection dataset and the LIDC-IDRI lung CT dataset using accuracy, precision, recall, F1-score, specificity, and area under the receiver operating characteristic curve (AUC). Additional ablation experiments assess the contribution of graph learning, sequence-aware modelling, and leakage-safe RSNA metadata fusion, while SHAP analysis quantifies the influence of the included RSNA metadata variables on multimodal predictions. For the RSNA multimodal experiment, the best held-out run achieved 95.2% accuracy and an AUC of 0.978, while three repeated runs yielded 94.0 ± 0.3% accuracy and an AUC of 0.970 ± 0.007 under the internal patient-wise benchmark protocol. These results should be interpreted as public-dataset benchmark outcomes rather than evidence of real-world clinical performance; external multi-centre and prospective validation is required before clinical deployment. Full article

Breast cancer-related lymphedema (BCRL) is a chronic disease that stems from damage to the lymphatic system due to breast cancer treatment leading to interstitial fluid buildup in the affected extremity. Patients with axillary lymph node dissection in combination with radiation therapy are at the highest risk of developing lymphedema. The mainstay non-surgical treatment involves participation in complete decongestive therapy with certified lymphedema therapists, daily compression garment usage, at-home pump treatments, and diligent skin care. Surgical treatments options can help alleviate symptoms associated with the disease by improving lymphatic drainage and removing fibrofatty tissue. Immediate lymphatic reconstruction (ILR) involves reconstructing cut lymphatics prophylactically at the time of axillary dissection with lymphovenous bypass (LVB) to decrease the risk of developing lymphedema. Delayed reconstruction addresses clinically diagnosed lymphedema and is divided into physiologic and debulking surgical techniques. Physiologic surgeries include lymphovenous bypass and vascularized lymph node transplantation (VLNT) aimed to treat fluid buildup. Debulking surgeries include lymphatic sparing liposuction or direct excision of fibrofatty tissues in the affected extremity to treat excess fibrofatty tissue secondary to lymphedema. This review discusses the pathophysiology of BCRL, diagnosis and staging of the disease, as well as provides an algorithmic overview on delayed lymphatic reconstruction options for BCRL. Full article

Background: Secondary acute promyelocytic leukemia (sAPL) is a very rare subtype of acute myeloid leukemia that develops following exposure to chemotherapy, radiotherapy, or immunosuppressive agents. The treatment results and survival outcomes of sAPL patients are still not precisely defined. Methods: A search of the Polish Adult Leukemia Group (PALG) database identified 29 cases of sAPL (median age 57 years; 62.1% female) among 437 APL patients (6.7%) diagnosed between 2006 and 2024. Each sAPL case was matched to a de novo APL patient by sex, age, year of diagnosis, and treatment protocol (LPA (Leucemia Promielocítica Aguda) 2005, LPA 2012, or LPA 2017). Results: All sAPL cases occurred following chemo- and/or radiotherapy, most commonly for breast cancer. The sAPL cases demonstrated higher CD15 expression than the de novo APL cases (median 27.6% vs. 7%, p = 0.04). The two groups exhibited comparable complete remission rates (82.8% sAPL vs. 75.9% de novo; p = 0.75) and early mortality rates (17.2% vs. 20.7%, p = 1.0). However, relapse-free survival was significantly shorter in sAPL (median 94.7 months vs. not reached; HR 7.23, 95% CI 1.63–32.02, p = 0.030), whereas overall survival did not differ significantly between groups. Multivariate analysis identified Eastern Cooperative Oncology Group performance status ≥3 and CD15 expression > 20% as independent predictors of inferior survival. Conclusions: These findings suggest that sAPL shares many clinical features with de novo APL but carries a higher risk of relapse, highlighting the need for further prospective studies and the potential implementation of tailored therapeutic strategies. Full article

Triple-negative breast cancer (TNBC) is an aggressive and clinically heterogeneous breast cancer subtype characterized by the absence of estrogen receptor, progesterone receptor, and HER2 overexpression, limited targeted treatment options, early relapse, and frequent development of therapy resistance. Although TNBC often shows initial sensitivity to chemotherapy, durable responses are commonly undermined by the emergence of adaptive resistant cell states rather than solely by fixed genetic mutations. This review synthesizes the role of epigenetic plasticity as a central mechanism that enables TNBC cells to dynamically reprogram transcriptional identity, survive therapeutic stress, and transition between epithelial, mesenchymal, stem-like, immune-evasive, and drug-tolerant persister phenotypes. Key epigenetic mechanisms include aberrant DNA methylation, histone acetylation and methylation, BET/BRD4-dependent transcriptional regulation, EZH2-mediated repression, SWI/SNF-dependent chromatin remodeling, non-coding RNA networks, and three-dimensional genome reorganization. These processes regulate tumor suppressor silencing, DNA-damage repair, epithelial–mesenchymal plasticity, cancer stem-cell maintenance, metabolic adaptation, immune-checkpoint regulation, and minimal residual disease. The review also highlights the translational relevance of epigenetic biomarkers, including DNA methylation signatures, circulating epigenetic markers, chromatin-accessibility profiles, and single-cell epigenomic approaches for diagnosis, prognosis, therapy prediction, and monitoring resistance evolution. Finally, therapeutic strategies targeting epigenetic plasticity are discussed, including DNMT, HDAC, BET, EZH2, KDM, and LSD1 inhibitors, with emphasis on rational combination approaches involving chemotherapy, PARP inhibitors, immunotherapy, and metabolic targeting. Overall, epigenetic plasticity represents both a major driver of TNBC resistance and a therapeutically exploitable vulnerability, provided those future strategies account for tumor heterogeneity, adaptive cell-state transitions, biomarker-guided patient selection, and combination-based treatment design. Full article

Early diagnosis of breast cancer (BC) remains challenging. The limited sensitivity and specificity of existing serum tumor markers for reliable clinical application highlight the need to develop a more accurate and efficient screening workflow. This study analyzed serum samples from 255 breast cancer patients and 300 healthy controls using matrix-assisted laser desorption/ionization time-of-flight (MALDI-TOF) mass spectrometry, identifying 58 differentially expressed peptides (37 upregulated, 21 downregulated). Combined with machine learning, peptide identification, and external validation, a complete standardized workflow was established. Nine machine learning (ML) algorithms were employed and compared, including SVM, LightGBM, XGBoost, etc. The models were interpreted using SHAP and LIME to identify key features. Peptides of interest were sequenced via mass spectrometry. Their expression and potential prognostic value were further validated in breast cancer transcriptomic datasets. Nine machine learning algorithms showed favorable discriminatory ability in the study cohort. The LightGBM model achieved an AUC of 0.97 internally and maintained an AUC of 0.88, an accuracy of 0.8543, and a precision of 0.9799 externally. However, after correcting for the markedly elevated prevalence (80.3%) in the external cohort, the positive predictive value (PPV) decreased substantially under real-world screening scenarios, warranting prospective validation in true screening populations. Model interpretation and subsequent sequencing identified six core biomarker peptides: Apolipoprotein A-IV (APOA4), Serum Deprivation Response Protein (SDPR), Alpha-1-Antitrypsin (SERPINA1), Ezrin (EZR), Serglycin (SRGN), and Fibrinogen Alpha Chain (FGA). Transcriptomic corroboration suggested that these molecules were significantly dysregulated in breast cancer tissues and showed univariate prognostic associations with patient survival. These findings demonstrated the potential of a proteomics-driven integrated machine learning pipeline as a proof-of-concept auxiliary risk-stratification tool for enhancing early breast cancer diagnosis, warranting further prospective validation in real-world screening cohorts before clinical translation. Full article

Background/Objectives: Breast MRI is the most sensitive modality for breast cancer detection, but long examination times, high costs, and limited availability restrict its use. Abbreviated breast MRI (AB-MRI) aims to preserve clinically relevant information while reducing acquisition and interpretation times. This narrative review summarizes evidence through 2026 on AB-MRI protocols, diagnostic performance, clinical applications, limitations, and emerging developments. Methods: Clinical studies, reviews, guidelines, implementation studies, and technical investigations of AB-MRI for screening, surveillance, preoperative assessment, neoadjuvant chemotherapy response, postoperative imaging, ultrafast MRI, diffusion-weighted imaging, artificial intelligence, and patient experience were reviewed. Results: AB-MRI can achieve diagnostic performance comparable to full-protocol MRI in selected screening and surveillance settings while substantially reducing scan and reading times. Multireader data in women with extremely dense breasts showed no significant differences in sensitivity or specificity versus full MRI. However, performance depends on protocol composition and clinical setting; T2-weighted imaging and DWI may improve specificity or diagnostic performance in selected applications. Recent studies also support sequential screening, surveillance after breast cancer, and neoadjuvant response assessment, while limitations remain for invasive lobular carcinoma, small lesions, non-mass enhancement, and disease extent. Emerging strategies include ultrafast MRI, adaptive AI-based imaging, AI-generated gadolinium-free contrast enhancement, and DWI-based protocol optimization. Conclusions: AB-MRI is best viewed as a flexible, indication-specific strategy rather than a single universal protocol. It is particularly promising for supplemental screening and surveillance, but prospective multicenter validation and protocol standardization remain necessary. Full article

Background: South Asian Americans (SAAs) represent the fastest-growing U.S. immigrant group but remain underrepresented in breast cancer research. This study utilizes the National Cancer Database (NCDB) to evaluate differences in tumor characteristics, treatment patterns, and survival outcomes between SAAs and non-Hispanic Whites (NHWs). Materials and Methods: A retrospective cohort analysis was conducted using NCDB data from 2004–2021. Women with breast cancer were stratified by race/ethnicity (SAA vs. NHW), and demographic, clinical, and treatment variables were compared. Outcomes assessed were overall survival (OS) and treatment delays, defined as initiation of surgery, chemotherapy, or radiation therapy > 60 days after diagnosis. Multivariable Cox proportional hazards models assessed OS. Results: Among 2,363,627 patients, 20,561 (0.9%) were SAAs and 2,343,066 (99.1%) NHWs. SAAs were younger at diagnosis, with 37.6% aged 20–49 vs. 20.6% of NHWs (p < 0.001). Insurance coverage differed, with SAAs more likely privately insured (63.0% vs. 54.2%, p < 0.001), less likely on Medicare (17.2% vs. 37.9%), and more often uninsured (4.5% vs. 1.2%). Time to first treatment was longer for SAAs (39.55 vs. 37.17 days, p < 0.001). Surgical delays >60 days increased mortality by 59%, while chemotherapy delays raised it by 44%. SAAs demonstrated higher survival at 5, 10, and 15 years (93%, 87%, 81%) vs. NHWs (87%, 76%, 64%). Median survival was 225.8 months but not estimable for SAAs. SAAs presented with aggressive subtypes: triple-negative and HER2-positive tumors. Conclusions: SAAs present younger with aggressive subtypes and treatment delays yet maintain survival advantages; reducing care barriers and clarifying tumor biology are vital to improving outcomes. Full article

Breast cancer imaging is central to screening, diagnosis, staging, treatment monitoring, and post-treatment surveillance, but image interpretation remains limited by variable image quality, interobserver variability, false-positive findings and heterogeneous tumor biology. This narrative review summarizes current applications of deep learning in multimodal breast cancer imaging, with emphasis on image reconstruction, image enhancement, lesion detection, segmentation, classification, biomarker prediction, treatment response assessment, prognosis and clinical implementation. A structured literature search was performed across major biomedical and technical databases, focusing on studies involving mammography, digital breast tomosynthesis, ultrasound, MRI, PET/CT, digital pathology and multimodal fusion approaches. Current evidence indicates that deep learning can support image denoising; super-resolution, low-dose, and accelerated reconstruction; lesion localization; tumor segmentation; benign–malignant classification; and molecular or biomarker-related prediction. Multimodal models integrating radiological imaging, histopathology, clinical variables, and molecular markers show particular promise for treatment response prediction, recurrence risk estimation, and personalized decision support. However, clinical translation remains limited by retrospective study designs, small and imbalanced datasets, domain shift, inconsistent annotations, limited explainability, bias, lack of prospective validation, and regulatory challenges. Deep learning should therefore be viewed as a decision-support framework that may improve breast cancer imaging workflows if validated in diverse, prospective, and clinically representative settings. Full article

Background/Objectives: Male breast cancer (MBC) is a rare malignancy accounting for less than 1% of all breast cancers, and current treatment recommendations are largely extrapolated from studies in women. We aimed to evaluate the clinicopathological characteristics, treatment patterns, survival outcomes, and prognostic factors of male breast cancer patients treated at a tertiary referral center. Methods: We retrospectively reviewed 45 patients with histopathologically confirmed MBC treated between January 2015 and July 2025. Demographic, clinicopathological, treatment, and follow-up data were collected from institutional records. Overall survival (OS) and disease-free survival (DFS) were estimated using the Kaplan–Meier method, and potential prognostic factors were analyzed using univariate Cox proportional hazards regression. Results: The median age at diagnosis was 60 years, and invasive ductal carcinoma was the predominant histological subtype (95.6%). Estrogen and progesterone receptor positivity were observed in 93.0% and 95.2% of patients, respectively, while HER2 positivity was identified in 26.8%. Modified radical mastectomy was performed in 95.6% of patients, adjuvant endocrine therapy in 88.9%, chemotherapy in 73.3%, and radiotherapy in 64.4%. After a median follow-up of 84 months (range, 1–125 months), the estimated 5-year OS and DFS rates were 85.3% and 68.4%, respectively. No locoregional recurrence was observed in the entire cohort; all recurrences were distant metastases. None of the evaluated clinicopathological variables demonstrated a statistically significant association with OS or DFS. Conclusions: This single-center experience demonstrates favorable long-term survival and no observed locoregional recurrence in a contemporary cohort of patients with male breast cancer. These real-world findings are consistent with current treatment strategies and provide additional evidence regarding the management of this rare disease. Larger multicenter collaborative studies are needed to establish robust prognostic models and generate male-specific evidence to further optimize clinical management. Full article

The integration of artificial intelligence (AI) into digital histopathology has the potential to improve the accuracy and efficiency of metastatic cancer diagnosis. We evaluated LYDIA (LYmph noDe assIstAnt), an AI-based decision-support system, for both standalone diagnostic performance and its impact on histopathologists’ workflow, diagnostic accuracy, and resource utilization. LYDIA was evaluated on a blinded dataset of 366 whole-slide images (WSIs) from breast, colorectal, lung, and skin cancers. Standalone performance demonstrated excellent discrimination, achieving ROC-AUC values of 0.995, 0.963, 0.973, and 0.983 for breast, colorectal, lung, and skin cancers, respectively. Clinical utility was further assessed in a multi-reader study involving four experienced histopathologists interpreting 105 WSIs with and without AI assistance. AI-assisted diagnosis significantly reduced time-to-diagnosis across all metastasis sizes, with a maximum 1.59-fold acceleration for micro-metastases, corresponding to a mean time saving of 26.5 s per WSI. LYDIA also improved diagnostic sensitivity from 77.3% to 87.3%. These findings demonstrate that LYDIA can enhance both the efficiency and accuracy of lymph node metastasis detection while reducing diagnostic workload and the need for ancillary testing. Beyond improving routine pathology workflows, the system’s rapid inference capabilities and human-expert level performance may support future intraoperative diagnostic applications, enabling timely and automatic or semi-automatic assessment of nodal status to inform surgical decision-making. The resulting reductions in diagnostic time and ancillary testing costs have the potential to improve healthcare resource utilization and patient care, mainly in soft tissue reconstruction and surgical repair decisions. Full article

Breast cancer remains one of the leading causes of cancer-related mortality among women worldwide, underscoring the importance of early and accurate diagnosis to improve patient outcomes. Magnetic resonance imaging (MRI) is a highly sensitive imaging modality for detecting breast malignancies, particularly in patients with dense breast tissue or those at high risk, where conventional imaging techniques may have limited sensitivity. Recent advances in deep learning (DL) have demonstrated considerable potential for improving the automated analysis of breast MRI, including tumour classification, prediction, and segmentation. This systematic review synthesises peer-reviewed studies published between 2014 and 2025 that exclusively applied DL techniques to breast MRI for cancer classification, prediction, or segmentation. The included studies were critically evaluated with respect to model architectures, dataset characteristics, image preprocessing methods, validation strategies, and reported performance metrics. The reviewed literature demonstrates that DL models consistently achieve high diagnostic performance and have the potential to enhance radiological workflows by supporting automated lesion detection and clinical decision-making. However, several challenges continue to limit their translation into routine clinical practice, including limited access to large, diverse, and well-annotated datasets, inadequate external validation, variability in MRI acquisition protocols, and concerns regarding model interpretability and generalisability. Future research should prioritise the development of robust, explainable, and clinically validated DL models trained on multicentre datasets using standardised evaluation frameworks. Addressing these challenges will be essential to improve the reliability, reproducibility, and clinical applicability of AI-assisted breast cancer diagnosis using MRI. Full article

Background and Aim: Approximately 10% of breast cancer patients present with distant organ metastases at initial diagnosis. This study aimed to evaluate the efficacy of immune-inflammatory markers and histopathological variables in identifying de novo metastatic breast cancer. Methods: Patients with breast cancer referred to a tertiary surgical oncology clinic between January 2020 and December 2022 were retrospectively screened. A total of 412 patients met the strict inclusion criteria. Laboratory parameters and radiological findings obtained during the initial diagnostic workup, prior to the initiation of any therapeutic intervention, were comprehensively evaluated. Results: Among the screened cohort, 56 patients presented with synchronous distant organ metastases at diagnosis. Significant differences (p < 0.05) were observed between the metastatic and non-metastatic groups in serum hemoglobin, albumin, and alkaline phosphatase (ALP) levels, lymphocyte and neutrophil counts, hemoglobin-albumin-lymphocyte-platelet score, prognostic nutritional index (PNI), systemic immune-inflammation index (SII), monocyte-to-lymphocyte ratio, platelet-to-lymphocyte ratio, neutrophil-to-lymphocyte ratio, and pan-immune-inflammation value. Multivariate logistic regression analysis identified Ki-67, T stage, N stage, ALP, SII, and PNI as independent predictors of metastasis (p < 0.05). In the receiver operating characteristic (ROC) analysis, the prognostic score formulated from this predictive model demonstrated an area under the curve (AUC) of 0.821 (95% CI: 0.781–0.857, p < 0.001, and Z-score = 9.34). At an optimal cut-off value of >0.233, the score yielded a sensitivity of 64.3% and a specificity of 92.1%. Furthermore, Decision Curve Analysis (DCA) confirmed a positive net clinical benefit across the decision-making threshold. Conclusions: The developed prognostic score may be a promising clinical tool for differentiating de novo metastatic breast cancer from non-metastatic disease at initial staging. This non-invasive approach may help clinicians risk-stratify patients, reduce diagnostic delays, and optimize early intervention strategies. Nonetheless, larger prospective multicenter studies are warranted for robust validation. Full article