Employing Raman Spectroscopy and Machine Learning for the Identification of Breast Cancer.

BACKGROUND: Breast cancer poses a significant health risk to women worldwide, with approximately 30% being diagnosed annually in the United States. The identification of cancerous mammary tissues from non-cancerous ones during surgery is crucial for the complete removal of tumors. RESULTS: Our study innovatively utilized machine learning techniques (Random Forest (RF), Support Vector Machine (SVM), and Convolutional Neural Network (CNN)) alongside Raman spectroscopy to streamline and hasten the differentiation of normal and late-stage cancerous mammary tissues in mice. The classification accuracy rates achieved by these models were 94.47% for RF, 96.76% for SVM, and 97.58% for CNN, respectively. To our best knowledge, this study was the first effort in comparing the effectiveness of these three machine-learning techniques in classifying breast cancer tissues based on their Raman spectra. Moreover, we innovatively identified specific spectral peaks that contribute to the molecular characteristics of the murine cancerous and non-cancerous tissues. CONCLUSIONS: Consequently, our integrated approach of machine learning and Raman spectroscopy presents a non-invasive, swift diagnostic tool for breast cancer, offering promising applications in intraoperative settings.

Drivers of racial, regional, and socioeconomic disparities in late-stage breast cancer mortality.

BACKGROUND: The authors identified tumor, treatment, and patient characteristics that may contribute to differences in breast cancer (BC) mortality by race, rurality, and area-level socioeconomic status (SES) among women diagnosed with stage IIIB-IV BC in Georgia. METHODS: Using the Georgia Cancer Registry, 3084 patients with stage IIIB-IV primary BC (2013-2017) were identified. Cox proportional hazards regression was used to calculate the hazard ratios (HRs) and 95% confidence intervals (CIs) comparing mortality among non-Hispanic Black (NHB) versus non-Hispanic White (NHW), residents of rural versus urban neighborhoods, and residents of low- versus high-SES neighborhoods by tumor, treatment, and patient characteristics. The mediating effects of specific characteristics on the association between race and BC mortality were estimated. RESULTS: Among the study population, 41% were NHB, 21% resided in rural counties, and 72% resided in low SES neighborhoods. The authors observed mortality disparities by race (HR, 1.27; 95% CI, 1.13, 1.41) and rurality (HR, 1.14; 95% CI, 1.00, 1.30), but not by SES (HR, 1.04; 95% CI, 0.91, 1.19). In the stratified analyses, racial disparities were the most pronounced among women with HER2 overexpressing tumors (HR, 2.30; 95% CI, 1.53, 3.45). Residing in a rural county was associated with increased mortality among uninsured women (HR, 2.25; 95% CI, 1.31, 3.86), and the most pronounced SES disparities were among younger women (<40 years: HR, 1.46; 95% CI, 0.88, 2.42). CONCLUSIONS: There is considerable variation in racial, regional, and socioeconomic disparities in late-stage BC mortality by tumor, treatment, and patient characteristics.

Applications of Circulating Tumor Cells and Circulating Tumor DNA in Precision Oncology for Breast Cancers.

Liquid biopsies allow for the detection of cancer biomarkers such as circulating tumor cells (CTCs) and circulating tumor DNA (ctDNA). Elevated levels of these biomarkers during cancer treatment could potentially serve as indicators of cancer progression and shed light on the mechanisms of metastasis and therapy resistance. Thus, liquid biopsies serve as tools for cancer detection and monitoring through a simple, non-invasive blood draw, allowing multiple longitudinal sampling. These circulating markers have significant prospects for use in assessing patients' prognosis, monitoring response to therapy, and developing precision medicine. In addition, single-cell omics of these liquid biopsy markers can be potential tools for identifying tumor heterogeneity and plasticity as well as novel therapeutic targets. In this review, we focus on our current understanding of circulating tumor biomarkers, especially in breast cancer, and the scope of novel sequencing technologies and diagnostic methods for better prognostication and patient stratification to improve patient outcomes.

Factors associated with Late-Stage Diagnosis of Breast Cancer among Egyptian Women.

Background: Detecting Breast Cancer (BC) at earlier stages comes with a better prognosis, while diagnosis at late stages has poor outcomes and escalating mortality rates from the disease. The study aims to understand the factors associated with the late-stage diagnosis of BC in Egypt. Design and Methods: A sample of 400 women with a pathologically confirmed BC were enrolled from one of the main tertiary cancer hospitals in Egypt. A cross-sectional study design was conducted. The collected data included: clinical characteristics of the tumor, socio-demographic characteristics of the studied women, reproductive and medical history, screening practices, and the time from symptom onset to definite diagnosis as suspected predictors to the stage of BC at diagnosis. Data was analyzed by crude odds ratios (95% confidence interval) and multivariate logistic regression analysis. Results: The study revealed that 47.5% were diagnosed at late stages (40% at stage III/ 7.5% at stage IV), while (52.5%) were diagnosed at early stages (6.5% at stage I/46% at stage II). A binary logistic regression model showed that unmarried females (p=0.012), had non-luminal molecular subtype of BC including HER2 enriched and triple-negative tumors (p<0.001), presentation with breast changes and a non-palpable lump (p=0.024) or non-breast symptoms (P=0.002), a delay longer than 3 months to the first presentation by patients (p<0.001), and a delay to definite diagnosis longer than 1 month by providers (p<0.001) were significant risk factors of late-stage diagnosis of BC. Conclusions: Late-stage diagnosis of BC in Egypt is associated with the aggressiveness of some molecular subtypes and other important modifiable factors that should be addressed.

Delayed presentation and diagnosis of breast cancer in African women: a systematic review.

PURPOSE: Africa has low breast cancer incidence rates but high mortality rates from this disease due to poor survival. Delays in presentation and diagnosis are major determinants of breast cancer survival, but these have not been comprehensively investigated in Africa. METHODS: MEDLINE, Embase, and Global Health were searched to identify studies reporting on delays in presentation and/or diagnosis of breast cancer published between January 1, 2000 and May 31, 2016. Data were synthesized in narrative, tabular, and graphical forms. Meta-analyses were not possible due to between-study differences in the way delays were reported. RESULTS: Twenty-one studies were included in the review. Study-specific average times between symptom recognition and presentation to a health care provider ranged from less than 1 to 4 months in North Africa and from less than 3 to greater than 6 months in sub-Saharan Africa. Study-specific average times from presentation to diagnosis were less than 1 month in North Africa but ranged from less than 3 to greater than 6 months in sub-Saharan Africa. Reported reasons for these delays included patient-mediated (e.g., socioeconomic factors) and health system-mediated factors (e.g., referral pathways). CONCLUSIONS: This systematic review revealed marked delays in presentation and diagnosis of breast cancer in Africa. Identification of their drivers is crucial to the development of appropriate control strategies in the continent.