Breast Cancer Screening Research Articles

“It’s a Low-key Thing of Eugenics”: Barriers to Cervical Cancer Screening and Disability Reproductive Justice for People with Disabilities During the COVID-19 Pandemic

Breast and cervical cancer screening is essential to the sexual and reproductive health of women and transgender people, resulting in reduced cancer incidence, improved outcomes, and lower mortality risk. However, previous studies have found lower rates of cancer screening among people with disabilities compared to those without disabilities, and increased rates of adverse associated outcomes, including later-stage cancer diagnosis and lower survival rates (Cuypers et al., 2022; Hughes et al., 2022). As such, this paper aims to mobilize the disability reproductive justice framework as a relevant lens for examining disparities in breast and cervical cancer screening that have a detrimental impact on people with disabilities. A mixed deductive and inductive approach was used to analyze 32 interviews with people who self-identified as having a physical, sensory, psychiatric, intellectual and/or developmental disability. This study was grounded in community- based research and was guided by peer researchers with lived experiences of disability and community partners. Our findings revealed that disparities in breast and cervical cancer screening for disabled women are present and ongoing. Themes that emerged included intersectional injustices, inaccessible spaces and systems, barriers to the right to reproductive health care, lack of autonomy and self-determination, and recommendations from people with disabilities. We conclude that this inaccessibility to cancer screening is a form of modern-day eugenics. The lack of accommodation for people with disabilities and recognition of them as sexual beings has contributed to these evident health inequities. While cancer screening services were delayed and disrupted for the entire population during COVID-19, there needs to be a consideration for the heightened vulnerability of this group, as well as the existing marginalization that creates barriers to access in the first place.

Quality assurance in lung cancer screening.

The effectiveness of screening programmes is critically dependent on the accuracy of the screening test. Where this relies on clinical expertise, there is an imperative to assure that the level of expertise meets expected standards. In cancer screening involving images, the focus is on the reader. Auditing of results is fraught with difficulty because of the time taken to accumulate enough data with confirmed outcomes to identify underperformance before any harm is done. Late recognition can lead to the need for reanalysis and recall of screening participants with loss of confidence in the programme. External Quality Assurance (EQA) is a method that enables clinical expertise to be tested rapidly by using test datasets with confirmed clinical outcome. In the UK, the breast cancer screening programme has had EQA in place for over 30 years. This article describes the development of the first EQA process in lung cancer screening, using the experience gained from running the breast cancer EQA, and the proposed future developments.

Survivorship care plans and adherence to breast and cervical cancer screening guidelines among cancer survivors in a national sample

PurposeThe impact of the components of survivorship care plans on adherence to cancer screening guidelines among cancer survivors is limited. We examined the association of receipt of treatment summaries, follow-up instructions, and type of doctor providing survivorship care with adherence to breast cancer screening (BCS) and cervical cancer screening (CCS) guidelines in female cancer survivors.MethodsA cross-sectional analysis using Behavioral Risk Factor Surveillance System (BRFSS) data from 2014, 2016 and 2018 was conducted. BCS and CCS-eligible women were aged 40–74 and 30–64, respectively. BCS adherence was defined as a mammogram within 2 years and CCS adherence as a pap smear within 3 years or HPV test within 5 years. Univariate analysis with chi-square and multivariable logistic regression are reported.Results5,001 BCS and 3,014 CCS-eligible survivors were identified. In the BCS group, recipients of treatment summaries and follow-up instructions were significantly more adherent with BCS (84.1% vs. 77.4%; 83.4% vs. 74%, respectively, p < 0.001). In the CCS group, recipients of follow-up instructions were significantly more adherent with CCS (78.1% vs. 67.7%, p < 0.001). In both groups, there was no significant difference in BCS or CCS based on type of physician providing care (p = 0.087). On multivariate analysis, receipt of follow-up instructions was the only factor significantly associated with BCS (OR:2.81; 95%CI:1.76–4.49) and CCS (OR:3.14; 95%CI:1.88–5.23).ConclusionsFollow-up instructions, as part of survivorship care plans, have the strongest association with BCS and CCS among female cancer survivors. Additional research should focus on improving the distribution of survivorship care plans, particularly follow-up instructions, as a method to increase BCS and CCS among cancer survivors.

An umbrella review of socioeconomic status and cancer

Extensive evidence underscores the pivotal role of socioeconomic status (SES) in shaping cancer-related outcomes. However, synthesizing definitive and actionable insights from the expansive body of literature remains a significant challenge. To elucidate the associations between SES, cancer outcomes, and the overall cancer burden, we conducted a comprehensive burden estimation coupled with an umbrella review of relevant meta-analyses. Our findings reveal that robust or highly suggestive meta-analytic evidence supports only a limited number of these associations. Individuals with lower SES, compared to those with higher SES, are disproportionately disadvantaged by reduced access to immunotherapy, KRAS testing for colorectal cancer, targeted cancer therapies, and precision treatments for melanoma. Additionally, they exhibit lower rates of breast cancer screening and higher incidence rates of lung cancer. Furthermore, countries with a higher Human Development Index demonstrate a substantially greater burden related cancer incidence, with this disparity being more pronounced among men than women.

Categorizing and Determining of BI-RAD Breast Cancer Score by Using Deep Learning Techniques

Breast cancer is second only to skin cancer in prevalence. Failure to detect and treat breast cancer early could be fatal. Breast cancer is more common in underdeveloped countries due to low health awareness and limited early detection methods. However, detecting equipment and radiography advances have helped solve this difficulty and suggest a drop in mortality. Along with ultrasounds, mammography, Magnetic Resonance Imaging (MRI), Computed tomography (CT) scan, and Positron emission tomography (PET) scans are used for diagnosis. These devices add data to test findings for greater accuracy. Diagnosticians determine breast cancer stage by examining tumor size, shape, and spread. Artificial intelligence users employ these factors as fixed values to classify the illness using region of interest (RIO), Gray Level Co-Occurrence Matrix (GLCAM), clustering, or mass constraints like diameter and volume. Artificial intelligence algorithms have created many techniques to extract features from massive volumes of data through training, such as deep learning. The study investigated DL algorithms (Attention mechanism and efficintNetB7 ) to determine the breast imaging-reporting and data system (BI-RADS) score by categorizing mammography images. The dataset Digital Database for Screening Mammography (DDSM) used in this study, acquired from Kaggle, contains 55,890 training samples, of which 86% are negative, and 14% are positive, categorized into classes C1, C2, C3, C4, and C5. This work utilized deep learning techniques and algorithms to accurately categorize breast cancer at 93%, 92%, 90%, and 93% for each category (C2, C3, C4, and C5). We developed the BI-RADS classifier model using the bycharm framework, an integrated development environment (IDE) for Python programming, and using multiple libraries, namely NumPy, Pandas, TensorFlow, Keras, Matplotlib, and Seaborn. This study used a laptop with the following specifications: an Intel Core i7 CPU, 16GB of RAM, and Intel RTX integrated graphics.

Fine-tuning pre-trained networks with emphasis on image segmentation: A multi-network approach for enhanced breast cancer detection

Accurate classification of mammography images into normal and cancerous categories is critical for the early detection of breast cancer. This study utilizes transfer learning and deep learning models to extract and diversify features from a combined dataset consisting of the Mini Digital Database for Screening Mammography (DDSM, containing 7808 images) and the Mammographic Image Analysis Society (MIAS) dataset (containing 322 images). The preprocessing steps involve image cropping, removal of artifacts, and enhancement of contrast using Contrast-Limited Adaptive Histogram Equalization (CLAHE). Data augmentation techniques, including the application of median and Gaussian blur, were used to improve the robustness of the models. Three pre-trained networks—Residual Networks with 50 layers (ResNet-50), Visual Geometry Group Network with 19 layers (VGG-19), and Residual Networks with 152 layers Version 2 (ResNet-152V2)—were fine-tuned specifically for mammography data. Image segmentation and the removal of the pectoral muscle significantly improved classification accuracy. The VGG-19 model achieved an Area Under the Receiver Operating Characteristic Curve (AUC) of 0.80 for segmented images and 0.86 for non-segmented images. A stacked generalization model, which combined features from all three networks, further optimized performance. Artificial Neural Network (ANN) and Extreme Gradient Boosting (XGBoost) models achieved AUCs of 0.897 and 0.890, respectively, for segmented images. Data augmentation improved performance by 2.7%–4%.

Breaking barriers: improving mammography screening accessibility and quality of care for breast cancer women with disabilities in Saudi Arabia.

Breast cancer screening remains pivotal in early detection and intervention. However, disparities persist, particularly among women with disabilities, necessitating a comprehensive understanding of their screening practices. This study aims to investigate breast cancer screening behaviours in Saudi women with disabilities. A cross-sectional study conducted in Saudi Arabia surveyed 307 women with disabilities, evaluating their screening frequency, knowledge of mammography, disability types, and duration. The Statistical Package for the Social Sciences (SPSS) was employed for data analysis. The study found that 70.4% of participants had irregular breast cancer screenings, and 92.5% lacked tailored information on breast cancer screening. The primary sources of information were support groups (59.3%) and healthcare professionals (25.4%). Significant associations were observed between education levels and awareness of the importance of mammography and the increased risk of breast cancer in individuals with disabilities. Notably, participants with higher education levels demonstrated greater awareness. The findings highlight substantial gaps in breast cancer screening practices and knowledge among Saudi women with disabilities. There is a critical need for tailored educational programs, accessible information, and targeted awareness campaigns to address these disparities. Enhancing the accessibility of screening services and information for this demographic is essential for improving healthcare equity and outcomes.

Predication on organs-on-chips applications the systematic treatment of breast cancer

Abstract. With the continuous development of cancer therapy, traditional in vitro models have been unable to reproduce the structure of organs and tissues of various parts of the human body, fluid flow and mechanical stimulation characteristics, and the human tumor microenvironment, which is crucial to the study of the behavior and progress of cancer, can not be presented through the animal model in vivo, which shows that the traditional physiological model of cancer can no longer meet the research of human anti-cancer therapy. Benefits from the continuous infusion of cell cultures through the microchannel, the device of organ-on-a-chip improves cell viability and activity and facilitates the simulation of the tumor cell microenvironment, which is expected to further replace traditional zoological experiments. This study reviews a method to simulate the microenvironment of the vitro breast cancer metastasis combined with microfluidic technology, and the application of this device in relevant researches of breast cancer cell metastasis and screening of breast cancer therapeutics.

Evaluating Factors Affecting Mean Glandular Dose in Mammography: Insights from a Retrospective Study in Dubai.

This study evaluates the mean glandular dose (MGD) in mammography screening for women aged 40-69 in Dubai, based on a retrospective analysis of a dose survey involving 2599 participants. MGD was calculated using the Dance formula. The average MGD was 0.96 ± 0.39 mGy for mediolateral oblique (MLO) views and 0.81 ± 0.33 mGy for craniocaudal (CC) views. Weak inverse correlations were found between age and organ dose (OD) for both views, while a direct relationship was observed between breast thickness and entrance skin dose (ESD). In adjusted models, ESD was strongly associated with MGD (β = 1.04, 95% CI: 0.97, 1.09), while OD showed a moderate association (β = 0.44, 95% CI: 0.40, 0.49). Significant variations in ESD, OD, and MGD were noted across age groups and breast thicknesses. Lower MGD indicates reduced radiation exposure risk, while higher MGD in MLO views suggests improved imaging quality. Monitoring and optimizing MGD are essential for enhancing patient safety and screening efficacy.

Awareness on breast cancer screening in Malaysia: a cross sectional study

Awareness on breast cancer screening in Malaysia: a cross sectional study

Impact of financial literacy and education on breast and cervical cancer screening participation in Japan.

Despite government efforts, the uptake of screening for breast and cervical cancers among Japanese women remains low. This study employs financial literacy and financial education as proxies for rational decision-making to explore their potential to enhance cancer screening practices in Japan. Using data from Osaka University's Preference Parameters Study, mean comparison tests and probit regression models are utilized to examine the association between breast and cervical cancer screening and financial literacy and financial education. The results of probit regression show that individuals with higher levels of financial education tend to participate in both breast and cervical cancer screening. In contrast, individuals with higher financial literacy are likely to participate in breast cancer screening, whereas no significant impact is observed for cervical cancer screening. Furthermore, our findings reveal that financial education positively influences both breast and cervical cancer screening. Factors such as employment, marriage, higher education, increased household income, and greater assets demonstrate robust positive relationships with breast and cervical cancer screening. Meanwhile, psychological factors including happiness, a myopic view of the future, anxiety about later life, and perceived health status have no significant associations, except for a positive association between anxiety about life and cervical cancer screening. Our study suggests the development of targeted educational programs that leverage financial literacy and financial education to raise awareness about the importance of breast and cervical cancer screening.

Centering intersectional breast cancer screening experiences among black, Latina, and white women: a qualitative analysis.

Mammography screening guidelines in the United States highlight the importance of informing and involving women when making their breast cancer screening decisions. However, the complexity of interpreting and applying these population-level guidelines can contribute to patient burden. Patient-centered communication strategies can alleviate patient burden, but few consider perspectives from racially and ethnically marginalized populations. We examine diverse women's perspectives on screening to characterize patient-centered experiences. We conducted 28 focus groups with 134 non-Latina Black (n = 51), non-Latina White (n = 39), and Latina (n = 44) participants. We coded participants' discussion of their screening influences. We used deductive and inductive qualitative methods to identify common themes. We identified three themes: (1) personal relationships with primary care providers, (2) potential impacts of cancer on families, and (3) interactions with medical systems. Most White participants described trusting physician relationships in contrast to perfunctory, surface-level relationships experienced by many Black participants; high costs of care prevented many Latina participants from accessing care (Theme 1). Diagnosis was a concern for most Black participants as it could burden family and most Latina participants as it could prevent them from maintaining family well-being (Theme 2). While many White participants had general ease in accessing and navigating healthcare, Latina participants were often held back by embarrassment-and Black participants frequently described disrespectful providers, false negatives, and unnecessary pain (Theme 3). Cultural and structural factors appeared to influence participants' approaches to breast cancer screening. Structural barriers may counteract culturally salient beliefs, especially among Black and Latina participants. We suggest patient-centered communication interventions be culturally adjusted and paired with structural changes (e.g., policy, insurance coverage, material resources) to reflect women's nuanced values and intersectional social contexts.

Abstract IA004: Early cancer dissemination: Circulating tumor cells in ductal carcinoma in situ patients

Abstract Raised awareness about the importance of early breast cancer diagnostics has led to an increased detection rate of ductal carcinoma in situ (DCIS) through mammographic screening. DCIS, often termed as 'Stage 0' carcinoma, is characterized by neoplastic cells confined within the basement membrane. Despite the significant treatment efforts for most DCIS patients, the 20-year breast cancer mortality rate post-diagnosis, with or without treatment, remains at 3.3%. To deepen the understanding of breast cancer oncogenesis, recent studies have highlighted the clonal diversity within the DCIS tumor microenvironment and the presence of disseminated tumor cells in DCIS patients. Nonetheless, significant gaps persist in identifying diagnostic characteristics that predict which DCIS patients are more likely to experience progression or recurrence. Ultimately, this project aims to enhance DCIS patient stratification through the high-throughput isolation and analysis of circulating biomarkers. In this study, we establish a novel workflow that addresses the limitations of traditional tissue-based diagnostics by transitioning to liquid biopsies. This research not only builds upon emerging evidence of early breast cancer cell dissemination during carcinogenesis but also explores the utility of circulating tumor cells (CTCs) as biomarkers in DCIS. The use of the labyrinth, a high-throughput inertial microfluidic device, has shown success in isolating CTCs based on their larger size relative to white blood cells. Unlike antigen- based isolation methods, inertial microfluidic devices can capture heterogeneous CTCs with varying surface proteins. Leveraging this technology, we successfully isolated and identified CTCs in DCIS patients. Furthermore, single-cell RNA sequencing of the isolated DCIS CTCs allowed us to identify prognostically significant signatures. Overall, our study presents a workflow capable of identifying characteristics associated with a greater risk of progression, thus contributing valuable insights into the stratification and management of DCIS patients. Citation Format: Sunitha Nagrath, Neha Nagpal, Brittany Rupp, Yan Hong, Fariba Behbod, Max Wicha. Early cancer dissemination: Circulating tumor cells in ductal carcinoma in situ patients [abstract]. In: Proceedings of the AACR Special Conference: Liquid Biopsy: From Discovery to Clinical Implementation; 2024 Nov 13-16; San Diego, CA. Philadelphia (PA): AACR; Clin Cancer Res 2024;30(21_Suppl):Abstract nr IA004.

Abstract A053: Liquid biopsy-based detection of triple negative breast cancer using DNA methylation biomarkers

Abstract Triple-negative breast cancer (TNBC) presents significant clinical challenges due to its aggressive phenotype, rapid progression, and limited targeted treatment options. TNBC often mimics benign lesions on ultrasound and metastatic features can be missed in routine mammography screening leading to misdiagnosis and delayed treatment. These limitations led us to investigate whether a blood-based liquid biopsy could provide a non-invasive, sensitive method for early TNBC detection, potentially overcoming the constraints of conventional imaging techniques. To discover biomarkers for TNBC, we performed targeted bisulfite sequencing on a cohort of 46 breast cancer solid tissue biopsy samples, comprising 19 TNBC and 27 non-TNBC cases. We identified 150 differentially methylated regions (mean length 703bp) separating TNBC and non-TNBC samples. Upon linking each region to its nearest gene, we observed several genes previously associated with prognosis and survival (HOXB3, PAX9, SOX9) substantiating the clinical relevance of these biomarkers. Using public TCGA data (369 breast cancer samples), we integrated expression and methylation data and observed directionally consistent changes. For example, HOXB3 showed increased methylation at its associated differential regions and decreased expression in TNBC cases. To ascertain whether these biomarkers could be useful in a liquid biopsy approach, we performed targeted bisulfite- sequencing on cell-free DNA samples derived from prospectively collected patients with breast cancer. All samples had independent tissue-based assessment of ER, PR and HER2 using immunohistochemistry or in situ hybridization. We then built a feed-forward neural network classifier with classes TNBC and non-TNBC that used transfer-learning and the identified biomarkers to learn methylation signatures in the biopsy samples and map them to cell-free DNA. To emulate clinical workflow, where subtyping follows cancer diagnosis and tissue of origin identification, we evaluated cfDNA samples correctly identified as breast cancer using two independent machine learning models trained using 2,393 prospectively collected multi- indication cancer and non-cancer samples (NCT05435066). Subsequent TNBC subtyping of breast cancer-positive cases (N=56) accurately identified 77% (10/13) of TNBC samples and 91% (39/43) of non-TNBC cases, with overall accuracy of 84%. The estimated tumor content range for correctly predicted TNBC samples was 0.5-33% with the three mis-classified samples all showing very low tumor content (0.22%, 0.28%, 0.59%). Non-TNBC cases showed a tumor content range of 0.07-36% for correct and 2.3-14% for misclassified samples. In conclusion, we identified novel methylation biomarkers that distinguish TNBC in the cell-free DNA of patients without needing invasive tissue biopsies. The high sensitivity of our assay at low tumor fractions has the potential to improve outcomes through earlier intervention and may enable earlier screening in high-risk groups, monitoring of minimal residual disease and longitudinal monitoring during treatment. Citation Format: Jocelyn Charlton, Shiva Farashahi, Kade Pettie, Elie Massaad, Josh Hubbell, Feras Hantash, Kieran I Chacko. Liquid biopsy-based detection of triple negative breast cancer using DNA methylation biomarkers [abstract]. In: Proceedings of the AACR Special Conference: Liquid Biopsy: From Discovery to Clinical Implementation; 2024 Nov 13-16; San Diego, CA. Philadelphia (PA): AACR; Clin Cancer Res 2024;30(21_Suppl):Abstract nr A053.

Mammography In Breast Cancer Screening – Current Knowledge, Challenges, The Impact of Artificial Intelligence, And Effectiveness With A Focus On Poland

Mammography is a critical tool in breast cancer screening and secondary prevention, enabling early detection and significantly reducing breast cancer mortality. This literature review assesses the effectiveness of mammography in identifying early-stage tumors, discussing its advantages, limitations, and specific challenges. Additionally, advancements in imaging techniques, such as 3D tomosynthesis, are examined, especially for their enhanced sensitivity in women with dense breast tissue, which reduces structural overlap and improves diagnostic precision. The integration of artificial intelligence (AI) in mammographic image analysis opens new opportunities, supporting radiologists by automating the detection and classification of potential lesions, thereby increasing screening efficiency and reducing false-positive rates. However, effective implementation of AI requires seamless integration with clinical systems and ongoing research to refine algorithms for diverse clinical needs. Furthermore, legal frameworks are essential to delineate responsibility in AI-supported diagnostics. This review emphasizes the status of breast cancer screening in Poland, where participation rates remain low despite the availability of free screenings. This highlights the need for improved public awareness and accessibility, especially in underserved areas. Overall, the findings underscore the fundamental role of mammography in breast cancer detection, with AI and other technological advancements significantly enhancing diagnostic accuracy while identifying areas for further improvement.

Enhancing Lung and Breast Cancer Screening with Advanced AI and Image Processing Techniques

This research investigates the application of CNNs for diagnostics improvements in lung and breast cancers based on AI image classification approaches. Using the datasets with 15,000 images describing lung cancer and 10,000 images describing cases of breast cancer, the models showed high performance: 90% for lung cancer and 99% for breast cancer classification. The descriptive analysis pointed out different features in imaging, such as dense tissue structure and irregular cell patterns; the models successfully identified these. The findings underlined the vital role that AI could play in assisting radiologists by delivering preliminary analysis, triaging high-risk cases, and leading to early cancer detection. Essential challenges were highlighted: ethical considerations concerning patients' privacy and AI algorithms' transparency. The limitation of the dataset diversity resulted in the conclusion that only broader data can ensure good generalization in various clinical settings. They recommended integrating the AI tool with clinical workflow and also called for training radiologists for effectiveness. Future research directions include real-time imaging and patient data integration for comprehensive diagnostic support and multi-modal approaches that combine imaging with genomics for more precise predictions. This leads to a more personalized cancer diagnosis and treatment plan, thus ultimately improving the results of the patients. This research, therefore, underlines the transformative capabilities of AI and image processing in modernizing cancer screening and diagnostics toward more accurate and efficient healthcare practices.

Using a behaviour-change approach to support uptake of population genomic screening and management options for breast or prostate cancer.

As the possibility of implementing population genomic screening programs for the risk of developing hereditary cancers in health systems increases, understanding how to support individuals who wish to have genomic screening is essential. This qualitative study aimed to link public perceived barriers to a) taking up the offer of population genomic screening for breast or prostate cancer risk and b) taking up risk-management options following their result, with possible theory-informed behaviour-change approaches that may support implementation. Ten focus groups were conducted with a total of 25 members of the Australian public to identify and then categorise barriers within the behaviour-change Capability, Opportunity, Motivation - Behaviour (COM-B) model. Ten COM-B categorised barriers were identified as perceived influences on an individual's intentions to take-up the offer, including Capability (e.g., low public awareness), Opportunity (e.g., inconvenient sample collection procedure) and Motivation (e.g., genomic screening not perceived as relevant to an individual). Ten barriers for taking up risk-management options included Motivation (e.g., concerns about adverse health impact) and Opportunity (e.g., social opportunity and cost incurred to the individual). Our findings demonstrate that a nuanced approach is required to support people to take-up the offer of population genomic screening and, where appropriate, to adopt risk-management options. Even amongst participants who were enthusiastic about a population genomic screening program, needs were varied, demanding a range of implementation strategies. Promulgating equitable uptake of genomic screening and management options for breast and prostate cancer risk will require a needs-based approach.

Impact of major depressive disorder on breast cancer outcomes: a national retrospective cohort study.

Establishing whether women with major depressive disorder (MDD) who develop breast cancer (BC) have poor outcomes is key to optimizing care for this population. To address this, we examined associations between MDD and BC recurrence and mortality. Using medical record data from the Veterans Affairs Healthcare System, we established a retrospective cohort of women with local or regional stage invasive BC between 2010 and 2019 and followed through 2022. We used a two-year window to identify women diagnosed with MDD prior to BC diagnosis. We used multivariable Cox-proportional hazards regression to estimate associations between MDD and BC recurrence and mortality while accounting for competing-risks and adjusting for sociodemographic, clinical, lifestyle, and tumor characteristics. We identified 6,051 women with BC, of whom 1,754 (29%) had MDD. The mean age at BC diagnosis was 57 years (standard deviation = 11). In multivariable analyses, women with MDD had a 37% (hazard ratio (HR)=1.37; 95% confidence interval (CI): 1.19-1.57) higher risk of recurrence and a 30% (HR = 1.30; 95% CI: 1.02-1.64) higher risk of BC mortality. The association between MDD and recurrence was stronger among women with estrogen receptor-positive BC. In secondary analyses, there were significant interactions between MDD and multiple exposures with respect to recurrence, including current smoking, substance abuse, and non-receipt of screening mammography. Women with MDD had inferior BC outcomes compared to women without a history of MDD. Research is needed to investigate underlying mechanisms linking depression to BC progression and evaluate interventions to improve outcomes in this high-risk population.

Higher Percentage of Virtual Primary Care Associated With Minimal Differences in Achievement of Quality Metrics.

To test the impact of virtual care usage on quality metrics used for performance measurement. Virtual care improves access to primary care; however, the quality of care must not be adversely impacted by its use. This is a mixed-design etiologic study using data from patients receiving primary care in a large, regional health system from January 2020 through December 2021. Eligible patients had at least one primary care contact. Eligible physicians had 10 or more patient contacts. The quartile of virtual visits per physician per month is calculated as the percentage of total visits conducted by phone or video (Q1 is the lowest). Six metrics used for value-based reimbursement were chosen for modeling with generalized linear mixed models. The data included 200,090 patients of 683 physicians in 42 clinics over 24 months. Virtual care usage peaked in April 2020 at 78% and then stabilized at 18%. The blood pressure metric was met in 66% (95% CI: 63%-69%) of physician months in Q1 and 65% (95% CI: 63%-68%) in Q4 ( P = 0.003). The hemoglobin A1c metric was met in 73% (95% CI: 70%-76%) of physician months in Q1 and 72% (95% CI: 69%-75%) in Q4, not a significant difference. Breast cancer screening completion and colon cancer screening completion did not differ across virtual care quartiles. Medicare annual wellness visits were completed in 55% (95% CI: 50%-60%) of Q1 physician months and 54% in each of Q2, Q3, and Q4 ( P < 0.0001). Some quality metrics were modestly impacted by high virtual primary care usage; the absolute differences in rates were small. This may provide reassurance to physicians and their health systems that telemedicine use may not adversely impact quality metrics.

Machine learning applications in breast cancer prediction using mammography

Breast cancer is the second leading cause of cancer-related deaths among women. Early detection of lumps and subsequent risk assessment significantly improves prognosis. In screening mammography, radiologist interpretation of mammograms is prone to high error rates and requires extensive manual effort. To this end, several computer-aided diagnosis methods using machine learning have been proposed for automatic detection of breast cancer in mammography. In this paper, we provide a comprehensive review and analysis of these methods and discuss practical issues associated with their reproducibility. We aim to aid the readers in choosing the appropriate method to implement and we guide them towards this purpose. Moreover, an effort is made to re-implement a sample of the presented methods in order to highlight the importance of providing technical details associated with those methods. Advancing the domain of breast cancer pathology classification using machine learning involves the availability of public databases and development of innovative methods. Although there is significant progress in both areas, more transparency in the latter would boost the domain progress.