ObjectiveThis study is aimed at developing and evaluating a machine learning–based model for breast cancer classification using integrated clinical, demographic, reproductive, and lifestyle data.MethodsA retrospective machine learning framework was developed using data from a case–control study conducted in Tehran. The dataset included demographic, clinical, reproductive, lifestyle, and screening‐related variables. Data preprocessing was performed within machine learning pipelines to ensure data quality and prevent data leakage. Duplicate records and noninformative variables were removed. Missing values were imputed using median values for numerical variables and the most frequent value for categorical variables. Categorical features were encoded appropriately, and Min–Max normalization was applied where required. Feature selection was conducted using mutual information (MI) and analysis of variance (ANOVA) within a stratified cross‐validation framework. The data were split into training (80%) and test (20%) sets. Several supervised learning algorithms, including Gaussian Naive Bayes (GNB), K‐nearest neighbors (KNN), decision tree (DT), random forest (RF), support vector machine (SVM), logistic regression (LR), and artificial neural network (ANN), were trained and evaluated. Model performance was assessed using accuracy, precision, recall (sensitivity), F1‐score, and receiver operating characteristic–area under the curve (ROC‐AUC), with stratified 5‐fold cross‐validation and final evaluation on an independent test set.ResultsSignificant differences were observed between breast cancer patients and healthy controls across multiple demographic and clinical variables. Patients were generally older and more likely to be widowed, belong to higher socioeconomic classes, and be housewives, whereas higher education levels and employment were more frequent among healthy individuals (p < 0.001). Reproductive factors, including age at first marriage and breastfeeding duration, also showed significant differences. Feature selection reduced 414 initial variables to 40 key predictors. The most influential features included genetic factors (BRCA1/2 mutations and family history), reproductive and hormonal characteristics (age at menarche, menopause, and infertility), lifestyle behaviors (dietary patterns and physical activity), anthropometric measures (BMI and weight at age 30), and screening‐related variables (mammography, ultrasound, and biopsy). All models demonstrated strong and stable performance with minimal differences between cross‐validation and test results, indicating good generalization. RF achieved the highest performance (accuracy: 0.9897, precision: 0.9946, recall: 0.9840, F1‐score: 0.9892), followed by SVM and LR, whereas ANN showed the lowest overall performance.ConclusionMachine learning models can effectively classify breast cancer using multidimensional patient data. Ensemble methods, particularly RF, demonstrated superior accuracy and robustness, highlighting their ability to capture complex nonlinear relationships. The identified predictors are consistent with established clinical and epidemiological risk factors, supporting the validity of the proposed models. These findings suggest that machine learning approaches hold strong potential for personalized risk assessment and early detection of breast cancer; however, external validation across diverse populations is necessary to confirm generalizability.

Vitamin B12 deficiency is classically associated with anemia and neurological dysfunction. However, recent studies suggest that elevated plasma vitamin B12 may indicate increased short-term cancer risk. This association remains largely unexplored in Middle Eastern populations, including Jordan, where cancer rates are rising and diagnosis often occurs at advanced stages due to limited screening. This study is aimed at investigating the association between serum vitamin B12 levels and the risk of colorectal, breast, and lung cancers in a Jordanian population, evaluating differences by cancer type and stage. A retrospective case-control study was conducted at King Abdullah University Hospital, Jordan, from January 2018 to December 2022. The study enrolled 260 patients diagnosed with colorectal, breast, or lung cancer and 260 matched healthy controls. Data collected included sociodemographic factors, clinical characteristics, and serum vitamin B12 levels. Serum vitamin B12 levels were significantly higher in cancer patients compared with controls (579.23 ± 468.72 vs. 492.70 ± 174.36 pg/mL; p = 0.005). High vitamin B12 levels (> 800 pg/mL) occurred in 15.8% of cancer patients versus 1.5% of controls (p < 0.001). Vitamin B12 levels varied significantly by cancer type, being highest in lung cancer patients (669.53 ± 566.59 pg/mL) compared with breast (594.86 ± 468.9 pg/mL) and colorectal cancer patients (439.62 ± 291.89 pg/mL; p = 0.024). There was a strong positive correlation between vitamin B12 levels and cancer stage, peaking in Stage IV cancers, r = 0.629, p = 0.001. Elevated serum vitamin B12 levels are significantly associated with solid cancers in Jordanian patients, particularly pronounced in lung cancer and advanced stages. These findings do not imply a causal relationship, but rather suggest that serum vitamin B12 may function as a potential biomarker for cancer detection and disease monitoring in resource-limited settings.

Breast cancer is the most prevalent cancer among women, with a notably high mortality-to-incidence ratio, especially in rural areas. Limited awareness and inadequate access to healthcare are major contributors to the high breast cancer mortality rate in rural women, often resulting from insufficient screening, delayed diagnosis, and treatment. This study is aimed at evaluating the effectiveness of three distinct intervention strategies-medical personnel-led education, breast health volunteers, and mobile screening mammography van visits-in improving breast cancer awareness, increasing screening participation, and reducing associated stigmatization among rural women. A comparative, community-based interventional study was conducted in three villages in neighboring districts. Rural communities were randomly allocated to one of the three intervention strategies. Baseline and postintervention data were collected using validated structured questionnaires assessing breast cancer knowledge, screening practices, stigma, and perceived barriers. A total of 944 women aged 30-70 years were enrolled in the study. Overall, 63.7% of participants underwent screening. The mobile screening mammography van group achieved the highest screening uptake (68.7%) and the greatest increase in awareness scores, whereas the breast health volunteer-led group showed the most significant reduction in stigma. The medical personnel-led group, though cost-effective in raising awareness, recorded lower screening participation and reported higher perceived barriers to screening mammography (e.g., transport, time, and financial constraints). The findings demonstrate that integrated, culturally tailored interventions, particularly those combining community engagement with accessible on-site screening services, can effectively improve breast cancer awareness and screening uptake among rural women. Scaling up such multicomponent strategies may help overcome logistical and sociocultural barriers, ultimately contributing to earlier detection and reduced mortality.

Patients with advanced HR+/HER2− breast cancer often experience prolonged disease courses, with bone being a dominant site of metastasis. Bone-targeted agents (BTAs) are recommended to reduce the risk of skeletal-related events (SREs), yet most clinical trials report follow-up durations of less than 2 years. Here, we present two cases of patients with breast cancer and bone metastases who received continuous BTA therapy for 8 and 10 years, respectively, in the context of ongoing antitumor treatment. Neither patient developed SREs during follow-up. The two cases demonstrated good tolerabilit during long-term treatment, though broader conclusions regarding safety require further investigation.

BackgroundVirtual teleconsultation plays a pivotal role in managing diseases requiring long‐term communication between patients and treatment teams, such as breast diseases. The Ruban Virtual Breast Clinic in Iran offers teleconsultation services focusing on nonurgent chronic complaints through offline messaging. This study aimed to evaluate patient satisfaction with these teleconsultation services.MethodsA comprehensive questionnaire was designed with three sections: identifying the individual interacting with the clinic and prior teleconsultation use; collecting demographic data and reasons for consultation; and assessing satisfaction using 16 items rated on a Likert scale from 1 (poor) to 10 (excellent). The study included patients who received at least one consultation by a breast surgeon through the Ruban platform.ResultsOf 583 eligible cases, 367 (62.9%) consented to participate. The average satisfaction score was 91.6 out of 100, indicating a high level of patient satisfaction.ConclusionsThe high satisfaction rates suggest that telehealth services, particularly virtual consultations, are feasible and highly acceptable in meeting patients′ healthcare needs. These findings underscore telehealth′s potential to improve access to care, though further research is required to establish its clinical effectiveness.

Background: Breast cancer screening and effective neoadjuvant treatments have increased surgeries for nonpalpable tumors, often requiring preoperative localization. The wire-guided method, performed on the same day as surgery, has limitations, prompting interest in wire-free alternatives like magnetic seed devices.Methods: A retrospective single-center study (November 2020–March 2024) compared magnetic seed and wire-guided localization in 558 patients. The primary aim was to assess localization and retrieval success, resection margins, and reoperation rates. Secondary endpoints included the interval between localization and surgery, operative time, incision site selection, and volume excised.Results: Among 558 patients, 188 underwent magnetic seed and 370 wire-guided localizations. Both groups were similar in BMI, breast size, and lesion characteristics. Complications in the wire-guided group included device migration (0.5%) and hematoma (1.3%). Success rates were comparable (98.9% vs. 99.7%), as were positive margins (5.3% vs. 6.7%) and reoperation rates (6.9% vs. 7.8%). Excised volume was significantly lower in the magnetic seed group (24.2 [range 6.5–48.0 cm3] vs. 41.5 cm3 [range 16.0–68.0 cm3], p < 0.001). The magnetic seed group had an average localization-to-surgery interval of 1 day (range 0–160 days).Conclusions: Magnetic seed localization is as safe and effective as wire-guided localization, with comparable success rates and resection margins adequacy. Its primary advantage is scheduling flexibility, offering a longer interval between localization and surgery.

Purpose: The purpose was to investigate the impact of breast density notification on anxiety using the State and Trait Anxiety Inventory (STAI) tool in South Australian women undergoing breast cancer screening. Methods: A survey-based cross-sectional mixed method study was conducted in women attending breast cancer screening at the Queen Elizabeth Hospital Breast/Endocrine outpatient department (n = 100). The women had participated in a previous study assessing their general knowledge of breast density and had indicated they wanted to know their own breast density. Breast density was assessed using Volpara software, and the participants were notified by letter. The STAI tool was administered with an additional question asking how participants felt after being told their breast density. State and trait anxiety levels were compared between those receiving notification of dense breasts and those notified of nondense breasts. Results: State anxiety scores were not different between women notified they had dense breasts (n = 34, mean state anxiety ± SD; 36.65 ± 13.03) and those who had nondense breasts (n = 66, 35.17 ± 13.60, p = 0.51). Severe trait anxiety was observed in 8 of 34 (23%) and 13 of 66 (20%) women in the dense and nondense groups, respectively, and there were no significant differences. Qualitative analysis of 122 coded responses revealed the majority of reactions to breast density notification were positive or neutral, with 17% being negative. Conclusion: Notification of dense breasts was not associated with elevated anxiety when compared to the notification of nondense breasts. Breast density notification approaches need to be considerate of the significant proportion of women with severe underlying anxiety.

Breast cancer is one of the most common malignancies and the leading cause of cancer-related mortality among women worldwide, with hormone receptor–positive (HR+) breast cancer being the most common subtype. Current guidelines recommend endocrine therapy as the first-line treatment for HR+, human epidermal growth factor Receptor 2–negative breast cancer. In this case report, we describe a patient with HR+ breast cancer who developed bone and liver metastases after breast cancer surgery. We document the disease progression from initial treatment to managing local recurrence and treating distant metastasis using salvage chemotherapy combined with endocrine therapy. Importantly, following denosumab treatment, the patient experienced a bone flare; this presented as increased radionuclide uptake on bone scans, but was later confirmed as pseudoprogression. Furthermore, we note changes in the patient's pathology as the disease progresses.

Background: Breast cancer is the most common cancer among women worldwide. Breast cancer screening programs are widely promoted because of their effectiveness in the early detection of cancer. However, a significant proportion of eligible Catholic nuns in the Lake Zone of Tanzania remain underscreened. This study is aimed at investigating the factors associated with breast cancer screening uptake among Catholic nuns in Lake Zone, Tanzania. Methods: This was a cross-sectional study design among 385 catholic nuns. Simple random sampling was deployed to enrolled catholic nuns, the ODK collect v2023.2.4 was electronically used to collect data. Binary logistic regression was used to assess the factors associated with the uptake of breast cancer screening. Statistical analysis was performed using STATA 18.0, with a significance level set at a p value less than 0.05. Result: The prevalence uptake of breast cancer screening (i.e., breast self-examination, clinical examination, or mammography examination) was 64% (n = 247, 95% CI, 59.3%-68.9%). A total of 57.4% had inadequate knowledge on the uptake of breast cancer screening (n = 221, 95% CI, 52.4%-62.4%). Also, the study found that 61.3% (95% CI, 56.4%-66.2%) of Catholic Nuns have negative attitudes towards the uptake of self-breast examination among Catholic nuns. The findings revealed that 55.6% (n = 133, 95% CI, 50.6%-60.6%) and 52.7% (n = 52.7%, 95% CI, 47.7%-57.7%) of Catholic nuns negatively accept breast cancer screening and self-breast examination, respectively. Nuns aged above 60 years were less likely to not perform BCS with a COR of 0.62 (95% CI, 0.39-0.97). Also, Catholic nuns who are in the nonhealth field are more likely to not perform BCS with a COR of 1.71 (95%, 1.07-2.74). Likewise, Catholic nuns who had negative acceptability of the Self-breast examination were more likely to not perform BCS with an AOR of 1.65 (95% CI, 1.07-2.55). Conclusion: A study found a low uptake of breast cancer screening among Catholic nuns. This highlights the need for breast health intervention programs within religious congregations to address misconceptions and promote early detection.

Background Breast cancer (BC) is globally the main cause of cancer-related deaths in women. Tumor biomarkers have significant role in diagnosis and predicting the prognosis and decide the specific therapy to each patient. Aim In this study, we investigated whether omentin and NGAL levels were altered in patients with breast cancer and the relationship between these markers and their clinicopathological parameters. Subjects and Methods. This study included 120 patients with breast cancer and 30 healthy individuals served as controls. We measured the serum level of omentin and NGAL by ELISA technique. Results Our results showed that there were statistically significant differences in serum omentin and NGAL levels between two groups. Also, in breast cancer patients, there was significant difference between omentin level, the same results with NGAL level and patient's age, tumor size, lymph node, and metastasis. No significant relationship was found between omentin level and tumor grade, ER, PR, and HER2. The cutoff value for the prediction of breast cancer was determined at >113.2 ng/ml for omentin and >145.3 ng/ml for NGAL with a sensitivity of 91.7% and 100%, specificity of 100% and 80%, positive predictive value of 100% and 90.9%, negative predictive value of 85.7% and 100%, and accuracy of 94.4% and 93.3%, respectively. In conclusion, serum omentin and NGAL can be used as strong diagnostic markers for breast cancer.