Prognostic models for breast cancer: a systematic review

Mammographic features at primary breast cancer diagnosis in relation to recurrence-free survival

PURPOSE

The number of women living with breast cancer (BC) is increasing, and the efficacy of surveillance programs after BC treatment is essential. Identification of links between mammographic features and recurrence could help design follow up strategies, which may lead to earlier detection of recurrence. The aim of this study was to analyze associations between mammographic features at diagnosis and their potential association with recurrence-free survival (RFS).

METHODS

Women with invasive BC in the prospective Malmö Diet and Cancer Study (n = 1116, 1991-2014) were assessed for locoregional and distant recurrences, with a median follow-up of 10.15 years. Of these, 34 women were excluded due to metastatic disease at diagnosis or missing recurrence data. Mammographic features (breast density [BI-RADS and clinical routine], tumor appearance, mode of detection) and tumor characteristics (tumor size, axillary lymph node involvement, histological grade) at diagnosis were registered. Associations were analyzed using Cox regression, yielding hazard ratios (HR) with 95 % confidence intervals (CI).

RESULTS

Of the 1082 women, 265 (24.4 %) had recurrent disease. There was an association between high mammographic breast density at diagnosis and impaired RFS (adjusted HR 1.32 (0.98-1.79). In analyses limited to screen-detected BC, this association was stronger (adjusted HR 2.12 (1.35-3.32). There was no association between mammographic tumor appearance and recurrence.

CONCLUSION

RFS was impaired in women with high breast density compared to those with low density, especially among women with screen-detected BC. This study may lead to insights on mammographic features preceding BC recurrence, which could be used to tailor follow up strategies.

Deconstructing neutrophil to lymphocyte ratio (NLR) in early breast cancer: lack of prognostic utility and biological correlates across tumor subtypes

PURPOSE

The prognostic utility and biological correlates of neutrophil to lymphocyte ratio (NLR), a potential biomarker of the balance between immune response and the inflammatory status, are still uncertain in breast cancer (BC).

METHODS

We analysed a cohort of 959 women with early breast cancer, mostly treated with neoadjuvant or adjuvant chemotherapy. Clinical and pathological data, survival, NLR (continuous and categorical) and stromal tumor infiltrating lymphocytes (sTIL) were evaluated.

RESULTS

NLR was only weakly associated with Ki67, while no association was found for grade, histology, immunohistochemical subtype or stage. Lymphocyte infiltration of the tumor did not correlate with NLR (Rho: 0.05, p = 0.30). These results were similar in the whole group and across the different BC subtypes, with no differences in triple negative BC. Relapse free interval (RFI), breast cancer specific survival (BCSS) and overall survival (OS) changed according to pre-treatment NLR neither in the univariate nor in the multivariate Cox models (RFI: HR 0.948, p = 0.61; BCSS: HR 0.920, p = 0.57; OS: HR 0.96, p = 0.59).

CONCLUSION

These results question the utility of NLR as a prognostic biomarker in early breast cancer and suggest the lack of correlation of NLR with tumor microenvironment immune response.

CD301 and LSECtin glycan-binding receptors of innate immune cells serve as prognostic markers and potential predictors of immune response in breast cancer subtypes

Glycosylation is a prominent posttranslational modification, and alterations in glycosylation are a hallmark of cancer. Glycan-binding receptors, primarily expressed on immune cells, play a central role in glycan recognition and immune response. Here, we used the recombinant C-type glycan-binding receptors CD301, Langerin, SRCL, LSECtin, and DC-SIGNR to recognize their ligands on tissue microarrays (TMA) of a large cohort (n = 1859) of invasive breast cancer of different histopathological types to systematically determine the relevance of altered glycosylation in breast cancer. Staining frequencies of cancer cells were quantified in an unbiased manner by a computer-based algorithm. CD301 showed the highest overall staining frequency (40%), followed by LSECtin (16%), Langerin (4%) and DC-SIGNR (0.5%). By Kaplan-Meier analyses, we identified LSECtin and CD301 as prognostic markers in different breast cancer subtypes. Positivity for LSECtin was associated with inferior disease-free survival in all cases, particularly in estrogen receptor positive (ER+) breast cancer of higher histological grade. In triple negative breast cancer, positivity for CD301 correlated with a worse prognosis. Based on public RNA single-cell sequencing data of human breast cancer infiltrating immune cells, we found CLEC10A (CD301) and CLEC4G (LSECtin) exclusively expressed in distinct subpopulations, particularly in dendritic cells and macrophages, indicating that specific changes in glycosylation may play a significant role in breast cancer immune response and progression.

Exploring Prognostic Gene Factors in Breast Cancer via Machine Learning

Breast cancer remains the most prevalent cancer in women. To date, its underlying molecular mechanisms have not been fully uncovered. The determination of gene factors is important to improve our understanding on breast cancer, which can correlate the specific gene expression and tumor staging. However, the knowledge in this regard is still far from complete. Thus, this study aimed to explore these knowledge gaps by analyzing existing gene expression profile data from 3149 breast cancer samples, where each sample was represented by the expression of 19,644 genes and classified into Nottingham histological grade (NHG) classes (Grade 1, 2, and 3). To this end, a machine learning-based framework was designed. First, the profile data were analyzed by using seven feature ranking algorithms to evaluate the importance of features (genes). Seven feature lists were generated, each of which sorted features in accordance with feature importance evaluated from a special aspect. Then, the incremental feature selection method was applied to each list to determine essential features for classification and building efficient classifiers. Consequently, overlapping genes, such as AURKA, CBX2, and MYBL2, were deemed as potentially related to breast cancer malignancy and prognosis, indicating that such genes were identified to be important by multiple feature ranking algorithms. In addition, the study formulated classification rules to reflect special gene expression patterns for three NHG classes. Some genes and rules were analyzed and supported by recent literature, providing new references for studying breast cancer.

The prognostic potential of mammographic growth rate of invasive breast cancer in the Nijmegen breast cancer screening cohort

OBJECTIVES

Insight into the aggressiveness of potential breast cancers found in screening may optimize recall decisions. Specific growth rate (SGR), measured on mammograms, may provide valuable prognostic information. This study addresses the association of SGR with prognostic factors and overall survival in patients with invasive carcinoma of no special type (NST) from a screened population.

METHODS

In this historic cohort study, 293 women with NST were identified from all participants in the Nijmegen screening program (2003-2007). Information on clinicopathological factors was retrieved from patient files and follow-up on vital status through municipalities. On consecutive mammograms, tumor volumes were estimated. After comparing five growth functions, SGR was calculated using the best-fitting function. Regression and multivariable survival analyses described associations between SGR and prognostic factors as well as overall survival.

RESULTS

Each one standard deviation increase in SGR was associated with an increase in the Nottingham prognostic index by 0.34 [95% confidence interval (CI): 0.21-0.46]. Each one standard deviation increase in SGR increased the odds of a tumor with an unfavorable subtype (based on histologic grade and hormone receptors; odds ratio 2.14 [95% CI: 1.45-3.15]) and increased the odds of diagnosis as an interval cancer (versus screen-detected; odds ratio 1.57 [95% CI: 1.20-2.06]). After a median of 12.4 years of follow-up, 78 deaths occurred. SGR was not associated with overall survival (hazard ratio 1.12 [95% CI: 0.87-1.43]).

CONCLUSIONS

SGR may indicate prognostically relevant differences in tumor aggressiveness if serial mammograms are available. A potential association with cause-specific survival could not be determined and is of interest for future research.

An Innovative Non-Linear Prediction Model for Clinical Benefit in Women with Newly Diagnosed Breast Cancer Using Baseline FDG-PET/CT and Clinical Data

Objectives: We aimed to develop a novel non-linear statistical model integrating primary tumor features on baseline [18F]-fluorodeoxyglucose positron emission tomography/computed tomography (FDG-PET/CT), molecular subtype, and clinical data for treatment benefit prediction in women with newly diagnosed breast cancer using innovative statistical techniques, as opposed to conventional methodological approaches. Methods: In this single-center retrospective study, we conducted a comprehensive assessment of women newly diagnosed with breast cancer who had undergone a FDG-PET/CT scan for staging prior to treatment. Primary tumor (PT) volume, maximum and mean standardized uptake value (SUVmax and SUVmean), metabolic tumor volume (MTV), and total lesion glycolysis (TLG) were measured on PET/CT. Clinical data including clinical staging (TNM) but also PT anatomical site, histology, receptor status, proliferation index, and molecular subtype were obtained from the medical records. Overall survival (OS), progression-free survival (PFS), and clinical benefit (CB) were assessed as endpoints. A logistic generalized additive model was chosen as the statistical approach to assess the impact of all listed variables on CB. Results: 70 women with newly diagnosed breast cancer (mean age 63.3 ± 15.4 years) were included. The most common location of breast cancer was the upper outer quadrant (40.0%) in the left breast (52.9%). An invasive ductal adenocarcinoma (88.6%) with a high tumor proliferation index (mean ki-67 expression 35.1 ± 24.5%) and molecular subtype B (51.4%) was by far the most detected breast tumor. Most PTs displayed on hybrid imaging a greater volume (12.8 ± 30.4 cm3) with hypermetabolism (mean ± SD of PT maximum SUVmax, SUVmean, MTV, and TLG, respectively: 8.1 ± 7.2, 4.9 ± 4.4, 12.7 ± 30.4, and 47.4 ± 80.2). Higher PT volume (p < 0.01), SUVmax (p = 0.04), SUVmean (p = 0.03), and MTV (<0.01) significantly compromised CB. A considerable majority of patients survived throughout this period (92.8%), while five women died (7.2%). In fact, the OS was 31.7 ± 14.2 months and PFS was 30.2 ± 14.1 months. A multivariate prediction model for CB with excellent accuracy could be developed using age, body mass index (BMI), T, M, PT TLG, and PT volume as predictive parameters. PT volume and PT TLG demonstrated a significant influence on CB in lower ranges; however, beyond a specific cutoff value (respectively, 29.52 cm3 for PT volume and 161.95 cm3 for PT TLG), their impact on CB only reached negligible levels. Ultimately, the absence of distant metastasis M displayed a strong positive impact on CB far ahead of the tumor size T (standardized average estimate 0.88 vs. 0.4). Conclusions: Our results emphasized the pivotal role played by FDG-PET/CT prior to treatment in forecasting treatment outcomes in women newly diagnosed with breast cancer. Nevertheless, careful consideration is required when selecting the methodological approach, as our innovative statistical techniques unveiled non-linear influences of predictive biomarkers on treatment benefit, highlighting also the importance of early breast cancer diagnosis.

Associations of accumulated persistent organic pollutants in breast adipose tissue with the evolution of breast cancer after surgery

Chronic exposure to persistent organic pollutants (POPs) is suspected to contribute to the onset of breast cancer, but the impact on the evolution of patients after diagnosis is unclear. We aimed to analyze the contribution of long-term exposure to five POPs to overall mortality, cancer recurrence, metastasis, and development of second primary tumors over a global follow-up of 10 years after surgery in breast cancer patients in a cohort study. Between 2012 and 2014, a total of 112 newly diagnosed breast cancer patients were recruited from a public hospital in Granada, Southern Spain. Historical exposure to POPs was estimated by analyzing their concentrations in breast adipose tissue samples. Sociodemographic data were collected through face-to-face interviews, while data on evolution tumor were retrieved from clinical records. Statistical analyses were performed using Cox regression (overall survival, breast cancer recurrence or metastasis) and binary logistic regression models (joint outcome variable). We also tested for statistical interactions of POPs with age, residence, and prognostic markers. The third vs first tertile of hexachlorobenzene concentrations was associated with a lower risk of all-cause mortality (Hazard Ratio, HR = 0.26; 95 % Confidence Interval, CI = 0.07-0.92) and of the appearance of any of the four events (Odds Ratio = 0.37; 95 % CI = 0.14-1.03). Polychlorinated biphenyl 138 concentrations were significantly and inversely associated with risk of metastasis (HR = 0.65; 95 % CI = 0.44-0.97) and tumor recurrence (HR = 0.69; 95 % CI = 0.49-0.98). Additionally, p,p'-dichlorodiphenyldichloroethylene showed inverse associations with risk of metastasis in women with ER-positive tumors (HR = 0.49; 95 % CI = 0.25-0.93) and in those with a tumor size <2.0 cm (HR = 0.39; 95 % CI = 0.18-0.87). The observed paradoxical inverse associations of POP exposure with breast cancer evolution might be related to either a better prognosis of hormone-dependent tumors, which have an approachable pharmacological target, or an effect of sequestration of circulating POPs by adipose tissue.

Development and testing of a random forest-based machine learning model for predicting events among breast cancer patients with a poor response to neoadjuvant chemotherapy

BACKGROUND

Breast cancer (BC) is the most common malignant tumor around the world. Timely detection of the tumor progression after treatment could improve the survival outcome of patients. This study aimed to develop machine learning models to predict events (defined as either (1) the first tumor relapse locally, regionally, or distantly; (2) a diagnosis of secondary malignant tumor; or (3) death because of any reason.) in BC patients post-treatment.

METHODS

The patients with the response of stable disease (SD) and progressive disease (PD) after neoadjuvant chemotherapy (NAC) were selected. The clinicopathological features and the survival data were recorded in 1 year and 5 years, respectively. Patients were randomly divided into the training set and test set in the ratio of 8:2. A random forest (RF) and a logistic regression were established in both of 1-year cohort and the 5-year cohort. The performance was compared between the two models. The models were validated using data from the Surveillance, Epidemiology, and End Results (SEER) database.

RESULTS

A total of 315 patients were included. In the 1-year cohort, 197 patients were divided into a training set while 87 were into a test set. The specificity, sensitivity, and AUC were 0.800, 0.833, and 0.810 in the RF model. And 0.520, 0.833, and 0.653 of the logistic regression. In the 5-year cohort, 132 patients were divided into the training set while 33 were into the test set. The specificity, sensitivity, and AUC were 0.882, 0.750, and 0.829 in the RF model. And 0.882, 0.688, and 0.752 of the logistic regression. In the external validation set, of the RF model, the specificity, sensitivity, and AUC were 0.765, 0.812, and 0.779. Of the logistics regression model, the specificity, sensitivity, and AUC were 0.833, 0.376, and 0.619.

CONCLUSION

The RF model has a good performance in predicting events among BC patients with SD and PD post-NAC. It may be beneficial to BC patients, assisting in detecting tumor recurrence.

Integrative dissection of 5-hydroxytryptamine receptors-related signature in the prognosis and immune microenvironment of breast cancer

Background

Depression increases the risk of breast cancer recurrence and metastasis. However, there lacks potential biomarkers for predicting prognosis in breast cancer. 5-hydroxytryptamine (5-HT) plays a key role in the pathogenesis and treatment of depression. In this study, we developed a prognostic signature based on 5-HT receptors (5-HTRs) and elucidated its potential immune regulatory mechanisms for breast cancer prognosis.

Methods

Oncomine, GEPIA, UALCAN, cBioPortal, Kaplan-Meier plotter, and TIMER were used to analyze differential expression, prognostic value, genetic alteration, and immune cell infiltration of HTRs in breast cancer patients. The model training and validation assays were based on the analyses of GSE1456 and GSE86166. A risk signature was established by univariate and multivariate Cox regression analyses. The transwell assay was utilized to verify the effect of the 5-HTRs expression on breast cancer invasion. Effects of HTR2A/2B inhibitor on CD8+ T cell proliferation and infiltration as well as apoptosis of 4T1 cells in the tumor microenvironment were detected by flow cytometry and TUNEL assay. Zebrafish and mouse breast cancer xenografts were used to determine the effect of HTR2A/2B inhibitor on breast cancer metastasis.

Results

The expression levels of HTR1A, HTR1B, HTR2A, HTR2B, HTR2C, HTR4, and HTR7 were significantly downregulated in highly malignant breast cancer types. 5-HTRs were significantly associated with recurrence-free survival (RFS) in breast cancer patients. The genetic alteration of HTR1D, HTR3A, HTR3B, and HTR6 in breast cancer patients was significantly associated with shorter overall survival (OS). Finally, HTR2A and HTR2B were determined to construct the risk signature. The expression of HTR2A/2B was positively correlated with the infiltration of immune cells such as CD8+ T cells and macrophages. Furthermore, inhibition of HTR2A expression could suppress CD8+ T cell proliferation and enhance invasion and metastasis of breast cancer cells in both zebrafish and mice model.

Conclusions

The HTR2A/2B risk signature not only highlights the significance of HTRs in breast cancer prognosis by modulating cancer immune microenvironment, but also provides a novel gene-testing tool for early prevention of depression in breast cancer patients and lead to an improved prognosis and quality of life.

Clinicopathological Factors Associated with Oncotype DX Risk Group in Patients with ER+/HER2- Breast Cancer

Oncotype DX (ODX), a 21-gene assay, predicts the recurrence risk in early breast cancer; however, it has high costs and long testing times. We aimed to identify clinicopathological factors that can predict the ODX risk group and serve as alternatives to the ODX test. This retrospective study included 547 estrogen receptor-positive, human epidermal growth factor receptor 2-negative, and lymph node-negative breast cancer patients who underwent ODX testing. Based on the recurrence scores, three ODX risk categories (low: 0-15, intermediate: 16-25, and high: 26-100) were established in patients aged ≤50 years (n = 379), whereas two ODX risk categories (low: 0-25 and high: 26-100) were established in patients aged >50 years (n = 168). Factors selected for analysis included body mass index, menopausal status, type of surgery, and pathological and immunohistochemical features. The ODX risk groups showed significant association with histologic grade (p = 0.0002), progesterone receptor expression (p < 0.0001), Ki-67 (p < 0.0001), and p53 expression (p = 0.023) in patients aged ≤50 years. In patients aged >50 years, tumor size (p = 0.022), Ki-67 (p = 0.001), and p53 expression (p = 0.001) were significantly associated with the risk group. Certain clinicopathological factors can predict the ODX risk group and enable decision-making on adjuvant chemotherapy; these factors differ according to age.

Prognostic Tools for Older Women with Breast Cancer: A Systematic Review

Background: Breast cancer is the most common cancer in women, and older patients comprise an increasing proportion of patients with this disease. The older breast cancer population is heterogenous with unique factors affecting clinical decision making. While many models have been developed and tested for breast cancer patients of all ages, tools specifically developed for older patients with breast cancer have not been recently reviewed. We systematically reviewed prognostic models developed and/or validated for older patients with breast cancer. Methods: We conducted a systematic search in 3 electronic databases. We identified original studies that were published prior to 8 November 2022 and presented the development and/or validation of models based mainly on clinico-pathological factors to predict response to treatment, recurrence, and/or mortality in older patients with breast cancer. The PROBAST was used to assess the ROB and applicability of each included tool. Results: We screened titles and abstracts of 7316 records. This generated 126 studies for a full text review. We identified 17 eligible articles, all of which presented tool development. The models were developed between 1996 and 2022, mostly using national registry data. The prognostic models were mainly developed in the United States (n = 7; 41%). For the derivation cohorts, the median sample size was 213 (interquartile range, 81-845). For the 17 included modes, the median number of predictive factors was 7 (4.5-10). Conclusions: There have been several studies focused on developing prognostic tools specifically for older patients with breast cancer, and the predictions made by these tools vary widely to include response to treatment, recurrence, and mortality. While external validation was rare, we found that it was typically concordant with interval validation results. Studies that were not validated or only internally validated still require external validation. However, most of the models presented in this review represent promising tools for clinical application in the care of older patients with breast cancer.

Machine Learning-Based Prediction of Distant Recurrence in Invasive Breast Carcinoma Using Clinicopathological Data: A Cross-Institutional Study

Breast cancer is the most common type of cancer worldwide. Alarmingly, approximately 30% of breast cancer cases result in disease recurrence at distant organs after treatment. Distant recurrence is more common in some subtypes such as invasive breast carcinoma (IBC). While clinicians have utilized several clinicopathological measurements to predict distant recurrences in IBC, no studies have predicted distant recurrences by combining clinicopathological evaluations of IBC tumors pre- and post-therapy with machine learning (ML) models. The goal of our study was to determine whether classification-based ML techniques could predict distant recurrences in IBC patients using key clinicopathological measurements, including pathological staging of the tumor and surrounding lymph nodes assessed both pre- and post-neoadjuvant therapy, response to therapy via standard-of-care imaging, and binary status of adjuvant therapy administered to patients. We trained and tested four clinicopathological ML models using a dataset (144 and 17 patients for training and testing, respectively) from Duke University and validated the best-performing model using an external dataset (8 patients) from Dartmouth Hitchcock Medical Center. The random forest model performed better than the C-support vector classifier, multilayer perceptron, and logistic regression models, yielding AUC values of 1.0 in the testing set and 0.75 in the validation set (p < 0.002) across both institutions, thereby demonstrating the cross-institutional portability and validity of ML models in the field of clinical research in cancer. The top-ranking clinicopathological measurement impacting the prediction of distant recurrences in IBC were identified to be tumor response to neoadjuvant therapy as evaluated via SOC imaging and pathology, which included tumor as well as node staging.

Multi-task banded regression model: A novel individual survival analysis model for breast cancer

PURPOSE

To reveal the hazard probability of individual breast cancer patients, a multi-task banded regression model is proposed for individual survival analysis of breast cancer.

METHODS

A banded verification matrix is designed to construct the response transform function of the proposed multi-task banded regression model, which can solve the repeated switching of survival rate. A martingale process is introduced to construct different nonlinear regressions for different survival subintervals. The concordance index (C-index) is used to compare the proposed model with Cox proportional hazards (CoxPH) models and previous multi-task regression models.

RESULTS

Two commonly-used breast cancer datasets are employed to validate the proposed model. Specifically, the Molecular Taxonomy of Breast Cancer International Consortium (METABRIC) includes 1981 breast cancer patients, of which 57.7% died of breast cancer. The Rotterdam & German Breast Cancer Study Group (GBSG) includes 1546 patients with lymph node-positive breast cancer in a randomized clinical trial, of which 44.4% died. Experimental results indicate that the proposed model is superior to some existing models for overall and individual survival analysis of breast cancer, with the C-index of 0.6786 for the GBSG and 0.6701 for the METABRIC.

CONCLUSION

The superiority of the proposed model can be contributed to three novel ideas. One is that a banded verification matrix can band the response of the survival process. Second, the martingale process can construct different nonlinear regressions for different survival subintervals. Third, the novel loss can adapt the model to making the multi-task regression similar to the real survival process.

Assessment of emerging pretraining strategies in interpretable multimodal deep learning for cancer prognostication

BACKGROUND

Deep learning models can infer cancer patient prognosis from molecular and anatomic pathology information. Recent studies that leveraged information from complementary multimodal data improved prognostication, further illustrating the potential utility of such methods. However, current approaches: 1) do not comprehensively leverage biological and histomorphological relationships and 2) make use of emerging strategies to "pretrain" models (i.e., train models on a slightly orthogonal dataset/modeling objective) which may aid prognostication by reducing the amount of information required for achieving optimal performance. In addition, model interpretation is crucial for facilitating the clinical adoption of deep learning methods by fostering practitioner understanding and trust in the technology.

METHODS

Here, we develop an interpretable multimodal modeling framework that combines DNA methylation, gene expression, and histopathology (i.e., tissue slides) data, and we compare performance of crossmodal pretraining, contrastive learning, and transfer learning versus the standard procedure.

RESULTS

Our models outperform the existing state-of-the-art method (average 11.54% C-index increase), and baseline clinically driven models (average 11.7% C-index increase). Model interpretations elucidate consideration of biologically meaningful factors in making prognosis predictions.

DISCUSSION

Our results demonstrate that the selection of pretraining strategies is crucial for obtaining highly accurate prognostication models, even more so than devising an innovative model architecture, and further emphasize the all-important role of the tumor microenvironment on disease progression.

Prognostic models for breast cancer: based on logistics regression and Hybrid Bayesian Network

BACKGROUND

To construct two prognostic models to predict survival in breast cancer patients; to compare the efficacy of the two models in the whole group and the advanced human epidermal growth factor receptor-2-positive (HER2+) subgroup of patients; to conclude whether the Hybrid Bayesian Network (HBN) model outperformed the logistics regression (LR) model.

METHODS

In this paper, breast cancer patient data were collected from the SEER database. Data processing and analysis were performed using Rstudio 4.2.0, including data preprocessing, model construction and validation. The L_DVBN algorithm in Julia0.4.7 and bnlearn package in R was used to build and evaluate the HBN model. Data with a diagnosis time of 2018(n = 23,384) were distributed randomly as training and testing sets in the ratio of 7:3 using the leave-out method for model construction and internal validation. External validation of the model was done using the dataset of 2019(n = 8128). Finally, the late HER2 + patients(n = 395) was selected for subgroup analysis. Accuracy, calibration and net benefit of clinical decision making were evaluated for both models.

RESULTS

The HBN model showed that seventeen variables were associated with survival outcome, including age, tumor size, site, histologic type, radiotherapy, surgery, chemotherapy, distant metastasis, subtype, clinical stage, ER receptor, PR receptor, clinical grade, race, marital status, tumor laterality, and lymph node. The AUCs for the internal validation of the LR and HBN models were 0.831 and 0.900; The AUCs for the external validation of the LR and HBN models on the whole population were 0.786 and 0.871; the AUCs for the external validation of the two models on the subgroup population were 0.601 and 0.813.

CONCLUSION

The accuracy, net clinical benefit, and calibration of the HBN model were better than LR model. The predictive efficacy of both models decreased and the difference was greater in advanced HER2 + patients, which means the HBN model had higher robustness and more stable predictive performance in the subgroup.

Conventional ultrasound and contrast-enhanced ultrasound radiomics in breast cancer and molecular subtype diagnosis

Objectives

This study aimed to explore the value of conventional ultrasound (CUS) and contrast-enhanced ultrasound (CEUS) radiomics to diagnose breast cancer and predict its molecular subtype.

Method

A total of 170 lesions (121 malignant, 49 benign) were selected from March 2019 to January 2022. Malignant lesions were further divided into six categories of molecular subtype: (non-)Luminal A, (non-)Luminal B, (non-)human epidermal growth factor receptor 2 (HER2) overexpression, (non-)triple-negative breast cancer (TNBC), hormone receptor (HR) positivity/negativity, and HER2 positivity/negativity. Participants were examined using CUS and CEUS before surgery. Regions of interest images were manually segmented. The pyradiomics toolkit and the maximum relevance minimum redundancy algorithm were utilized to extract and select features, multivariate logistic regression models of CUS, CEUS, and CUS combined with CEUS radiomics were then constructed and evaluated by fivefold cross-validation.

Results

The accuracy of the CUS combined with CEUS model was superior to CUS model (85.4% vs. 81.3%, p<0.01). The accuracy of the CUS radiomics model in predicting the six categories of breast cancer is 68.2% (82/120), 69.3% (83/120), 83.7% (100/120), 86.7% (104/120), 73.5% (88/120), and 70.8% (85/120), respectively. In predicting breast cancer of Luminal A, HER2 overexpression, HR-positivity, and HER2 positivity, CEUS video improved the predictive performance of CUS radiomics model [accuracy=70.2% (84/120), 84.0% (101/120), 74.5% (89/120), and 72.5% (87/120), p<0.01].

Conclusion

CUS radiomics has the potential to diagnose breast cancer and predict its molecular subtype. Moreover, CEUS video has auxiliary predictive value for CUS radiomics.

Development and internal-external validation of statistical and machine learning models for breast cancer prognostication: cohort study

OBJECTIVE

To develop a clinically useful model that estimates the 10 year risk of breast cancer related mortality in women (self-reported female sex) with breast cancer of any stage, comparing results from regression and machine learning approaches.

DESIGN

Population based cohort study.

SETTING

QResearch primary care database in England, with individual level linkage to the national cancer registry, Hospital Episodes Statistics, and national mortality registers.

PARTICIPANTS

141 765 women aged 20 years and older with a diagnosis of invasive breast cancer between 1 January 2000 and 31 December 2020.

MAIN OUTCOME MEASURES

Four model building strategies comprising two regression (Cox proportional hazards and competing risks regression) and two machine learning (XGBoost and an artificial neural network) approaches. Internal-external cross validation was used for model evaluation. Random effects meta-analysis that pooled estimates of discrimination and calibration metrics, calibration plots, and decision curve analysis were used to assess model performance, transportability, and clinical utility.

RESULTS

During a median 4.16 years (interquartile range 1.76-8.26) of follow-up, 21 688 breast cancer related deaths and 11 454 deaths from other causes occurred. Restricting to 10 years maximum follow-up from breast cancer diagnosis, 20 367 breast cancer related deaths occurred during a total of 688 564.81 person years. The crude breast cancer mortality rate was 295.79 per 10 000 person years (95% confidence interval 291.75 to 299.88). Predictors varied for each regression model, but both Cox and competing risks models included age at diagnosis, body mass index, smoking status, route to diagnosis, hormone receptor status, cancer stage, and grade of breast cancer. The Cox model's random effects meta-analysis pooled estimate for Harrell's C index was the highest of any model at 0.858 (95% confidence interval 0.853 to 0.864, and 95% prediction interval 0.843 to 0.873). It appeared acceptably calibrated on calibration plots. The competing risks regression model had good discrimination: pooled Harrell's C index 0.849 (0.839 to 0.859, and 0.821 to 0.876, and evidence of systematic miscalibration on summary metrics was lacking. The machine learning models had acceptable discrimination overall (Harrell's C index: XGBoost 0.821 (0.813 to 0.828, and 0.805 to 0.837); neural network 0.847 (0.835 to 0.858, and 0.816 to 0.878)), but had more complex patterns of miscalibration and more variable regional and stage specific performance. Decision curve analysis suggested that the Cox and competing risks regression models tested may have higher clinical utility than the two machine learning approaches.

CONCLUSION

In women with breast cancer of any stage, using the predictors available in this dataset, regression based methods had better and more consistent performance compared with machine learning approaches and may be worthy of further evaluation for potential clinical use, such as for stratified follow-up.

MHAttnSurv: Multi-head attention for survival prediction using whole-slide pathology images

Whole slide images (WSI) based survival prediction has attracted increasing interest in pathology. Despite this, extracting prognostic information from WSIs remains a challenging task due to their enormous size and the scarcity of pathologist annotations. Previous studies have utilized multiple instance learning approach to combine information from several randomly sampled patches, but this approach may not be adequate as different visual patterns may contribute unequally to prognosis prediction. In this study, we introduce a multi-head attention mechanism that allows each attention head to independently explore the utility of various visual patterns on a tumor slide, thereby enabling more comprehensive information extraction from WSIs. We evaluated our approach on four cancer types from The Cancer Genome Atlas database. Our model achieved an average c-index of 0.640, outperforming three existing state-of-the-art approaches for WSI-based survival prediction on these datasets. Visualization of attention maps reveals that the attention heads synergistically focus on different morphological patterns, providing additional evidence for the effectiveness of multi-head attention in survival prediction.

Plasma hPG80 (Circulating Progastrin) as a Novel Prognostic Biomarker for early-stage breast cancer in a breast cancer cohort

BACKGROUND

Recurrence and metastases are still frequent outcomes after initial tumour control in women diagnosed with breast cancer. Although therapies are selected based on tumour characteristics measured at baseline, prognostic biomarkers can identify those at risk of poor outcomes. Circulating progastrin or hPG₈₀ was found to be associated with survival outcomes in renal and hepatocellular carcinomas and was a plausible prognostic biomarker for breast cancer.

METHODS

Women with incident breast cancers from Calgary, Alberta, Canada enrolled in the Breast to Bone (B2B) study between 2010 to 2016 and provided blood samples prior to any treatment initiation. Plasma from these baseline samples were analysed for circulating progastrin or hPG₈₀. Participant characteristics as well as tumour ones were evaluated for their association with hPG₈₀ and survival outcomes (time to recurrence, recurrence - free survival, breast cancer specific survival and overall survival) in Cox proportional hazards regression models.

RESULTS

The 464 participants with measurable hPG₈₀ in this study had an average age of 57.03 years (standard deviation of 11.17 years) and were predominantly diagnosed with Stage I (52.2%) and Stage II (40.1%) disease. A total of 50 recurrences and 50 deaths were recorded as of June 2022. In Cox PH regression models adjusted for chemotherapy, radiation therapy, cancer stage and age at diagnosis, log hPG₈₀ (pmol/L) significantly increased the risks for recurrence (Hazard Ratio (HR) = 1.330, 95% Confidence Interval (CI) = (0.995 - 1.777, p = 0.054)), recurrence-free survival (HR = 1.399, 95% CI = (1.106 - 1.770), p = 0.005) and overall survival (HR = 1.385, 95% CI = (1.046 - 1.834), = 0.023) but not for breast cancer specific survival (HR = 1.015, 95% CI = (0.684 - 1.505), p = 0.942).

CONCLUSIONS

hPG₈₀ levels measured at diagnosis were significantly associated with the risk of recurrence or death from any cause in women with breast cancer. Since the recurrence rates of breast cancer are still relatively high amongst women diagnosed at an early stage, identifying women at high risk of recurrence at their time of diagnosis is important. hPG₈₀ is a promising new prognostic biomarker that could improve the identification of women at higher risk of poor outcomes.

A Comparison between the Online Prognostic Tool PREDICT and myBeST for Women with Breast Cancer in Malaysia

The PREDICT breast cancer is a well-known online calculator to estimate survival probability. We developed a new prognostic model, myBeST, due to the PREDICT tool’s limitations when applied to our patients. This study aims to compare the performance of the two models for women with breast cancer in Malaysia. A total of 532 stage I to III patient records who underwent surgical treatment were analysed. They were diagnosed between 2012 and 2016 in seven centres. We obtained baseline predictors and survival outcomes by reviewing patients’ medical records. We compare PREDICT and myBeST tools’ discriminant performance using receiver-operating characteristic (ROC) analysis. The five-year observed survival was 80.3% (95% CI: 77.0, 83.7). For this cohort, the median five-year survival probabilities estimated by PREDICT and myBeST were 85.8% and 82.6%, respectively. The area under the ROC curve for five-year survival by myBeST was 0.78 (95% CI: 0.73, 0.82) and for PREDICT was 0.75 (95% CI: 0.70, 0.80). Both tools show good performance, with myBeST marginally outperforms PREDICT discriminant performance. Thus, the new prognostic model is perhaps more suitable for women with breast cancer in Malaysia.

Development of a risk model to predict prognosis in breast cancer based on cGAS-STING-related genes

Background: Breast cancer (BRCA) is regarded as a lethal and aggressive cancer with increasing morbidity and mortality worldwide. cGAS-STING signaling regulates the crosstalk between tumor cells and immune cells in the tumor microenvironment (TME), emerging as an important DNA-damage mechanism. However, cGAS-STING-related genes (CSRGs) have rarely been investigated for their prognostic value in breast cancer patients.

Methods: Our study aimed to construct a risk model to predict the survival and prognosis of breast cancer patients. We obtained 1087 breast cancer samples and 179 normal breast tissue samples from the Cancer Genome Atlas (TCGA) and Genotype-Tissue Expression (GTEX) database, 35 immune-related differentially expression genes (DEGs) from cGAS-STING-related genes were systematically assessed. The Cox regression was applied for further selection, and 11 prognostic-related DEGs were used to develop a machine learning-based risk assessment and prognostic model.

Results: We successfully developed a risk model to predict the prognostic value of breast cancer patients and its performance acquired effective validation. The results derived from Kaplan-Meier analysis revealed that the low-risk score patients had better overall survival (OS). The nomogram that integrated the risk score and clinical information was established and had good validity in predicting the overall survival of breast cancer patients. Significant correlations were observed between the risk score and tumor-infiltrating immune cells, immune checkpoints and the response to immunotherapy. The cGAS-STING-related genes risk score was also relevant to a series of clinic prognostic indicators such as tumor staging, molecular subtype, tumor recurrence, and drug therapeutic sensibility in breast cancer patients.

Conclusion: cGAS-STING-related genes risk model provides a new credible risk stratification method to improve the clinical prognostic assessment for breast cancer.

Carbonic anhydrase IX-related tumoral hypoxia predicts worse prognosis in breast cancer: A systematic review and meta-analysis

Background

Tumoral hypoxia is associated with aggressiveness in many cancers including breast cancer. However, measuring hypoxia is complicated. Carbonic anhydrase IX (CAIX) is a reliable endogenous marker of hypoxia under the control of the master regulator hypoxia-inducible factor-1α (HIF-1α). The expression of CAIX is associated with poor prognosis in many solid malignancies; however, its role in breast cancer remains controversial.

Methods

The present study performed a meta-analysis to evaluate the correlation between CAIX expression and disease-free survival (DFS) and overall survival (OS) in breast cancer.

Results

A total of 2,120 publications from EMBASE, PubMed, Cochrane, and Scopus were screened. Of these 2,120 publications, 272 full texts were reviewed, and 27 articles were included in the meta-analysis. High CAIX was significantly associated with poor DFS (HR = 1.70, 95% CI = 1.39–2.07, p &lt; 0.00001) and OS (HR = 2.02, 95% CI 1.40–2.91, p = 0.0002) in patients with breast cancer. When stratified by subtype, the high CAIX group was clearly associated with shorter DFS (HR = 2.09, 95% CI =1.11–3.92, p = 0.02) and OS (HR = 2.50, 95% CI =1.53–4.07, p = 0.0002) in TNBC and shorter DFS in ER+ breast cancer (HR = 1.81 95% CI =1.38–2.36, p &lt; 0.0001).

Conclusion

High CAIX expression is a negative prognostic marker of breast cancer regardless of the subtypes.

The Need to Prioritize Model-Updating Processes in Clinical Artificial Intelligence (AI) Models: Protocol for a Scoping Review

BACKGROUND

With an increase in the number of artificial intelligence (AI) and machine learning (ML) algorithms available for clinical settings, appropriate model updating and implementation of updates are imperative to ensure applicability, reproducibility, and patient safety.

OBJECTIVE

The objective of this scoping review was to evaluate and assess the model-updating practices of AI and ML clinical models that are used in direct patient-provider clinical decision-making.

METHODS

We used the PRISMA (Preferred Reporting Items for Systematic Reviews and Meta-Analyses) checklist and the PRISMA-P protocol guidance in addition to a modified CHARMS (Checklist for Critical Appraisal and Data Extraction for Systematic Reviews of Prediction Modelling Studies) checklist to conduct this scoping review. A comprehensive medical literature search of databases, including Embase, MEDLINE, PsycINFO, Cochrane, Scopus, and Web of Science, was conducted to identify AI and ML algorithms that would impact clinical decision-making at the level of direct patient care. Our primary end point is the rate at which model updating is recommended by published algorithms; we will also conduct an assessment of study quality and risk of bias in all publications reviewed. In addition, we will evaluate the rate at which published algorithms include ethnic and gender demographic distribution information in their training data as a secondary end point.

RESULTS

Our initial literature search yielded approximately 13,693 articles, with approximately 7810 articles to consider for full reviews among our team of 7 reviewers. We plan to complete the review process and disseminate the results by spring of 2023.

CONCLUSIONS

Although AI and ML applications in health care have the potential to improve patient care by reducing errors between measurement and model output, currently there exists more hype than hope because of the lack of proper external validation of these models. We expect to find that the AI and ML model-updating methods are proxies for model applicability and generalizability on implementation. Our findings will add to the field by determining the degree to which published models meet the criteria for clinical validity, real-life implementation, and best practices to optimize model development, and in so doing, reduce the overpromise and underachievement of the contemporary model development process.

INTERNATIONAL REGISTERED REPORT IDENTIFIER (IRRID)

PRR1-10.2196/37685.

myBeST-A Web-Based Survival Prognostic Tool for Women with Breast Cancer in Malaysia: Development Process and Preliminary Validation Study

Women with breast cancer are keen to know their predicted survival. We developed a new prognostic model for women with breast cancer in Malaysia. Using the model, this study aimed to design the user interface and develop the contents of a web-based prognostic tool for the care provider to convey survival estimates. We employed an iterative website development process which includes: (1) an initial development stage informed by reviewing existing tools and deliberation among breast surgeons and epidemiologists, (2) content validation and feedback by medical specialists, and (3) face validation and end-user feedback among medical officers. Several iterative prototypes were produced and improved based on the feedback. The experts (n = 8) highly agreed on the website content and predictors for survival with content validity indices ≥ 0.88. Users (n = 20) scored face validity indices of more than 0.90. They expressed favourable responses. The tool, named Malaysian Breast cancer Survival prognostic Tool (myBeST), is accessible online. The tool estimates an individualised five-year survival prediction probability. Accompanying contents were included to explain the tool's aim, target user, and development process. The tool could act as an additional tool to provide evidence-based and personalised breast cancer outcomes.

Ten-Year Survival of Breast Cancer in Iran: A National Study (Retrospective Cohort Study)

Purpose

This study aimed to estimate the 5- and 10-year survival rates of breast cancer in Iran.

Methods

This retrospective cohort study was performed in 2019 on breast cancer patients registered in the national cancer registry system of Iran during 2007-2014. The patients were contacted to collect their information and status (alive or dead). Age and pathological type of tumor were categorized into five groups, and the place of residence was divided into 13 regions. The Kaplan-Meier method and the Cox proportional hazards model were used for data analysis.

Results

A total of 87,902 patients were diagnosed with breast cancer during the study, 22,307 of whom were followed-up. The 5- and 10-year survival rates of the patients were 80% and 69%, respectively. The mean age of the patients was 50.68 ± 12.76 years (median age, 49 years). About 2.3% of the patients were male. The 5- and 10-year survival rates were 69% and 50% in men, respectively. The highest survival rate was reported in the age group of 40-49 years, and the lowest rate was found in the age group of ≥70 years. Of all pathological types, 88% were found in the invasive ductal carcinoma group; the highest survival rate was reported in the noninvasive carcinoma group. The highest survival rate was reported in the Tehran region and the lowest in the Hamedan region. Based on the results, the Cox proportional hazards model, sex, age group, and pathological type were statistically significant differences.

Conclusion

This nationwide study performed on breast cancer patients indicated an improvement in the overall survival rate of these patients over the past years (the 5-year survival rate increased from 71% in 2011 to 80% in the present study), which might be attributed to advances in cancer management.

The patient generated-subjective global assessment (PG-SGA) and ECOG performance status are associated with mortality in patients hospitalized with breast cancer

AIM

This study evaluated the association between risk of malnutrition and performance status, and mortality in hospitalized breast cancer patients.

METHODS

Prospective cohort study with hospitalized breast cancer patients evaluated at a referral Cancer Center. The Risk of malnutrition was assessed by the Patient-Generated Subjective Global Assessment (PG-SGA) and performance status was determined using the Eastern Cooperative Oncology Group Performance Status Scale (ECOG PS). Logistic regression was used to analyze the factors associated with death, using the odds ratio (OR) with a 95% confidence interval (CI) as an effect measure.

RESULTS

A total of 195 woman were included, with a mean age of 56.3 (±12.6) years. Patients with an overall PG-SGA score ≥18 (OR: 2.11; 95% CI: 1.03-4.62) and ECOG PS ≥ 3 (OR: 3.34; 95% CI: 1.48-7.52) had a higher occurrence of death during hospitalization, regardless of age or disease stage. The concomitant presence of these two factors improved the accuracy of the association (OR: 5.32; 95% CI: 3.11-9.76) and showed good predictive accuracy (C-statistics: 0.77).

CONCLUSION

Nutritional risk and poor performance status were associated with a higher occurrence of death in women with breast cancer. The use of these two indicators improves their predictive accuracy for mortality.

Development and Assessment of a Novel Core Biopsy-Based Prediction Model for Pathological Complete Response to Neoadjuvant Chemotherapy in Women with Breast Cancer

Purpose: Pathological complete response (pCR), the goal of NAC, is considered a surrogate for favorable outcomes in breast cancer (BC) patients administrated neoadjuvant chemotherapy (NAC). This study aimed to develop and assess a novel nomogram model for predicting the probability of pCR based on the core biopsy. Methods: This was a retrospective study involving 920 BC patients administered NAC between January 2012 and December 2018. The patients were divided into a primary cohort (769 patients from January 2012 to December 2017) and a validation cohort (151 patients from January 2017 to December 2018). After converting continuous variables to categorical variables, variables entering the model were sequentially identified via univariate analysis, a multicollinearity test, and binary logistic regression analysis, and then, a nomogram model was developed. The performance of the model was assessed concerning its discrimination, accuracy, and clinical utility. Results: The optimal predictive threshold for estrogen receptor (ER), Ki67, and p53 were 22.5%, 32.5%, and 37.5%, respectively (all p < 0.001). Five variables were selected to develop the model: clinical T staging (cT), clinical nodal (cN) status, ER status, Ki67 status, and p53 status (all p ≤ 0.001). The nomogram showed good discrimination with the area under the curve (AUC) of 0.804 and 0.774 for the primary and validation cohorts, respectively, and good calibration. Decision curve analysis (DCA) showed that the model had practical clinical value. Conclusions: This study constructed a novel nomogram model based on cT, cN, ER status, Ki67 status, and p53 status, which could be applied to personalize the prediction of pCR in BC patients treated with NAC.

Identification of a tumor immune-inflammation signature predicting prognosis and immune status in breast cancer

Background

Breast cancer has become the malignancy with the highest mortality rate in female patients worldwide. The limited efficacy of immunotherapy as a breast cancer treatment has fueled the development of research on the tumor immune microenvironment.

Methods

In this study, data on breast cancer patients were collected from The Cancer Genome Atlas Breast Invasive Carcinoma (TCGA-BRCA) and Molecular Taxonomy of Breast Cancer International Consortium (METABRIC) cohorts. Differential gene expression analysis, univariate Cox regression analysis, and least absolute shrinkage and selection operator (LASSO) Cox regression analysis were performed to select overall survival (OS)-related, tumor tissue highly expressed, and immune- and inflammation-related genes. A tumor immune-inflammation signature (TIIS) consisting of 18 genes was finally screened out in the LASSO Cox regression model. Model performance was assessed by time-dependent receiver operating characteristic (ROC) curves. In addition, the CIBERSORT algorithm and abundant expression of immune checkpoints were utilized to clarify the correlation between the risk signature and immune landscape in breast cancer. Furthermore, the association of IL27 with the immune signature was analyzed in pan-cancer and the effect of IL27 on the migration of breast cancer cells was investigated since the regression coefficient of IL27 was the highest.

Results

A TIIS based on 18 genes was constructed via LASSO Cox regression analysis. In the TCGA-BRCA training cohort, 10-year AUC reached 0.89, and prediction performance of this signature was also validated in the METABRIC set. The high-risk group was significantly correlated with less infiltration of tumor-killing immune cells and the lower expression level of the immune checkpoint. Furthermore, we recommended some small-molecule drugs as novel targeted drugs for new breast cancer types. Finally, the relationship between IL27, a significant prognostic immune and inflammation cytokine, and immune status was analyzed in pan-cancer. Expression of IL27 was significantly correlated with immune regulatory gene expression and immune cell infiltration in pan-cancer. Furthermore, IL27 treatment improved breast cancer cell migration.

Conclusion

The TIIS represents a promising prognostic tool for estimating OS in patients with breast cancer and is correlated with immune status.

Correlation between conventional ultrasound features combined with contrast-enhanced ultrasound patterns and pathological prognostic factors in malignant non-mass breast lesions

OBJECTIVE

To investigate the correlation between ultrasound performance and prognostic factors in malignant non-mass breast lesions (NMLs).

MATERIALS AND METHODS

This study included 106 malignant NMLs in 104 patients. Different US features and contrast enhancement patterns were evaluated. Prognostic factors, including histological types and grades, axillary lymph node and peritumoral lymphovascular status, estrogen and progesterone receptor status and the expression of HER-2 and Ki-67 were determined. A chi-square test and logistic regression analysis were used to analyse possible associations.

RESULTS

Lesion size (OR: 3.08, p = 0.033) and posterior echo attenuation (OR: 8.38, p < 0.001) were useful in reflecting malignant NMLs containing an invasive carcinoma component. Posterior echo attenuation (OR: 7.51, p = 0.003) and unclear enhancement margin (OR: 6.50, p = 0.018) were often found in tumors with axillary lymph node metastases. Peritumoural lymphovascular invasion mostly exhibited posterior echo attenuation (OR: 3.84, p = 0.049) and unclear enhancement margin (OR: 8.68, p = 0.042) on ultrasound images. Perfusion defect was a comparatively accurate enhancement indicator for negative ER (OR: 2.57, p = 0.041) and PR (OR: 3.04, p = 0.008) expression. Calcifications (OR: 3.03, p = 0.025) and enlarged enhancement area (OR: 5.36, p = 0.033) imply an increased risk of positive HER-2 expression. Similarly, Calcifications (OR: 4.13, p = 0.003) and enlarged enhancement area (OR: 11.05, p < 0.001) were valid predictors of high Ki-67 proliferation index.

CONCLUSION

Ultrasound performance is valuable for non-invasive prediction of prognostic factors in malignant NMLs.

Clinical characteristics, risk factors, and outcomes in Chilean triple negative breast cancer patients: a real-world study

BACKGROUND

Latin American (LA) studies on triple-negative breast cancer (TNBC) and their characteristics are scarce. This forces physicians to make clinical decisions based on data obtained from studies that include non-Hispanic patients. Our study sought to obtain local epidemiological data, including risk factors and clinical outcomes from a Chilean BC registry.

METHODS

This was a retrospective population-cohort study that included patients treated at a community hospital (mid-low income) or an academic private center (high income), in the 2010-2021 period. Univariate and multivariate analyses were performed to identify prognostic factors associated with survival.

RESULTS

647 out of 5,806 BC patients (11.1%) were TNBC. These patients were younger (p = 0.0001) and displayed lower rates of screening-detected cases (p = 0.0001) compared to non-TNBC counterparts. Among TNBC patients, lower income (i. e., receiving treatment at a community hospital) was associated with poorer overall survival (HR: 1.53; p = 0.0001) and poorer BC specific survival (HR: 1.29; p = 0.004). Other risk factors showed no significant differences between TNBC and non-TNBC. As expected, 5-year OS was significantly shorter on TNBC versus non-TNBC patients (p = 0.00001). In our multivariate analyses TNBC subtype (HR: 2.30), locally advanced stage (HR: 7.04 for stage III), lower income (HR: 1.64), or non-screening detected BC (HR: 1.32) were associated with poorer OS.

CONCLUSION

To the best of our knowledge, this is the largest LA cohort of TNBC patients. Interestingly, the proportion of TNBC among Chileans was smaller compared to similar studies within LA. As expected, TNBC patients had poorer survival and higher risk for early recurrence versus non-TNBC. Other relevant findings include a higher proportion of premenopausal patients among TNBC. Also, mid/low-income patients that received medical attention at a community hospital displayed lower survival versus private health center counterparts.

Adipose tissue levels of polybrominated diphenyl ethers in relation to prognostic biomarkers and progression-free survival time of breast cancer patients in eastern area of southern China: A hospital-based study

Evidence indicates that individual or groups of polybrominated diphenyl ethers (PBDEs) are associated with risk of breast cancer (BC). Epidemiological studies of PBDEs and BC progression are scarce. This study aimed to investigate the relationships between PBDE burdens in adipose tissues and prognostic biomarkers of BC as well as progression-free survival (PFS) of patients for the first time. The concentrations of 14 PBDE congeners in breast adipose tissues of 183 cases from the eastern area of southern China were analyzed by gas chromatography-mass spectrometry (GC-MS). Odds ratios (ORs) and 95% confidence intervals (CIs) were estimated by logistic regression models for the associations between PBDE levels and prognostic biomarkers. Kaplan-Meier and Cox regression analyses were conducted to identify the correlations between PBDEs and PFS. The results showed that BDE-99 and 190 levels were positively associated with clinical stage and N stage respectively (OR = 2.61 [1.26-5.40], OR = 2.78 [1.04-7.46]). Concentrations of BDE-28 and BDE-183 were negatively associated with the expression of estrogen receptor (ER) (OR = 0.30 [0.11-0.81]; 0.39 [0.15-0.99]) and progesterone receptor (PR) (OR = 0.36 [0.14-0.92]; 0.37 [0.15-0.91]), and increased BDE-47 was associated with lower human epidermal growth factor receptor 2 (HER2) expression (OR = 0.44 [0.23-0.86]). Adipose levels of BDE-71, 99, 138, 153, 154 and total PBDEs were positively associated with p53 expression (all P < 0.05). Finally, BDE-47, 99 and 183 were considered as independent prognostic factors for shorter PFS in the Cox models (adjusted hazard ratios = 3.14 [1.26-7.82]; 2.25 [1.03-4.94]; 2.60 [1.08-6.25], respectively). The recurrence risk and prognosis of BC may be closely bound to the body burdens of certain PBDE congeners. Further epidemiological and experimental studies are needed for confirmation.

Survival analysis and prognosis of patients with breast cancer with pleural metastasis

Background

Breast cancer (BC) is the most common malignant cancer. The prognosis of patients differs according to the location of distant metastasis, with pleura being a common metastatic site in BC. Nonetheless, clinical data of patients with pleural metastasis (PM) as the only distant metastatic site at initial diagnosis of metastatic BC (MBC) are limited.

Patient cohort and methods

The medical records of patients who were hospitalized in Shandong Cancer Hospital between January 1, 2012 and December 31, 2021 were reviewed, and patients eligible for the study were selected. Survival analysis was conducted using Kaplan-Meier (KM) method. Univariate and multivariate Cox proportional-hazards models were used to identify prognostic factors. Finally, based on these selected factors, a nomogram was constructed and validated.

Results

In total, 182 patients were included; 58 (group A), 81 (group B), and 43 (group C) patients presented with only PM, only lung metastasis (LM), and PM combined with LM, respectively. The KM curves revealed no significant difference in overall survival (OS) among the three groups. However, in terms of survival after distant metastasis (M-OS), the difference was significant: patients with only PM exhibited the best prognosis, whereas those with PM combined with LM exhibited the worst prognosis (median M-OS: 65.9, 40.5, and 32.4 months, respectively; P = 0.0067). For patients with LM in groups A and C, those with malignant pleural effusion (MPE) exhibited significantly worse M-OS than those without MPE. Univariate and multivariate analyses indicated that primary cancer site, T stage, N stage, location of PM, and MPE were independent prognostic factors for patients with PM without other distant metastasis. A nomogram prediction model incorporating these variables was created. According to the C-index (0.776), the AUC values of the 3-, 5-, and 8-year M-OS (0.86, 0.86, and 0.90, respectively), and calibration curves, the predicted and actual M-OS were in good agreement.

Conclusion

BC patients with PM only at the first diagnosis of MBC exhibited a better prognosis than those with LM only or PM combined with LM. We identified five independent prognostic factors associated with M-OS in this subset of patients, and a nomogram model with good predictive efficacy was established.

Methodological guidance for the evaluation and updating of clinical prediction models: a systematic review

BACKGROUND

Clinical prediction models are often not evaluated properly in specific settings or updated, for instance, with information from new markers. These key steps are needed such that models are fit for purpose and remain relevant in the long-term. We aimed to present an overview of methodological guidance for the evaluation (i.e., validation and impact assessment) and updating of clinical prediction models.

METHODS

We systematically searched nine databases from January 2000 to January 2022 for articles in English with methodological recommendations for the post-derivation stages of interest. Qualitative analysis was used to summarize the 70 selected guidance papers.

RESULTS

Key aspects for validation are the assessment of statistical performance using measures for discrimination (e.g., C-statistic) and calibration (e.g., calibration-in-the-large and calibration slope). For assessing impact or usefulness in clinical decision-making, recent papers advise using decision-analytic measures (e.g., the Net Benefit) over simplistic classification measures that ignore clinical consequences (e.g., accuracy, overall Net Reclassification Index). Commonly recommended methods for model updating are recalibration (i.e., adjustment of intercept or baseline hazard and/or slope), revision (i.e., re-estimation of individual predictor effects), and extension (i.e., addition of new markers). Additional methodological guidance is needed for newer types of updating (e.g., meta-model and dynamic updating) and machine learning-based models.

CONCLUSION

Substantial guidance was found for model evaluation and more conventional updating of regression-based models. An important development in model evaluation is the introduction of a decision-analytic framework for assessing clinical usefulness. Consensus is emerging on methods for model updating.

Development of Predictive Models for Survival among Women with Breast Cancer in Malaysia

Prediction of survival probabilities based on models developed by other countries has shown inconsistent findings among Malaysian patients. This study aimed to develop predictive models for survival among women with breast cancer in Malaysia. A retrospective cohort study was conducted involving patients who were diagnosed between 2012 and 2016 in seven breast cancer centres, where their survival status was followed until 31 December 2021. A total of 13 predictors were selected to model five-year survival probabilities by applying Cox proportional hazards (PH), artificial neural networks (ANN), and decision tree (DT) classification analysis. The random-split dataset strategy was used to develop and measure the models' performance. Among 1006 patients, the majority were Malay, with ductal carcinoma, hormone-sensitive, HER2-negative, at T2-, N1-stage, without metastasis, received surgery and chemotherapy. The estimated five-year survival rate was 60.5% (95% CI: 57.6, 63.6). For Cox PH, the c-index was 0.82 for model derivation and 0.81 for validation. The model was well-calibrated. The Cox PH model outperformed the DT and ANN models in most performance indices, with the Cox PH model having the highest accuracy of 0.841. The accuracies of the DT and ANN models were 0.811 and 0.821, respectively. The Cox PH model is more useful for survival prediction in this study's setting.

Ultrasonography and clinicopathological features of breast cancer in predicting axillary lymph node metastases

Background

Early identification of axillary lymph node metastasis (ALNM) in breast cancer (BC) is still a clinical difficulty. There is still no good method to replace sentinel lymph node biopsy (SLNB). The purpose of our study was to develop and validate a nomogram to predict the probability of ALNM preoperatively based on ultrasonography (US) and clinicopathological features of primary tumors.

Methods

From September 2019 to April 2022, the preoperative US) and clinicopathological data of 1076 T1-T2 BC patients underwent surgical treatment were collected. Patients were divided into a training set (875 patients from September 2019 to October 2021) and a validation set (201 patients from November 2021 to April 2022). Patients were divided into positive and negative axillary lymph node (ALN) group according pathology of axillary surgery. Compared the US and clinicopathological features between the two groups. The risk factors for ALNM were determined using multivariate logistic regression analysis, and a nomogram was constructed. AUC and calibration were used to assess its performance.

Results

By univariate and multivariate logistic regression analysis, age (p = 0.009), histologic grades (p = 0.000), molecular subtypes (p = 0.000), tumor location (p = 0.000), maximum diameter (p = 0.000), spiculated margin (p = 0.000) and distance from the skin (p = 0.000) were independent risk factors of ALNM. Then a nomogram was developed. The model was good discriminating with an AUC of 0.705 and 0.745 for the training and validation set, respectively. And the calibration curves demonstrated high agreement. However, in further predicting a heavy nodal disease burden (> 2 nodes), none of the variables were significant.

Conclusion

This nomogram based on the US and clinicopathological data can predict the presence of ALNM good in T1-T2 BC patients. But it cannot effectively predict a heavy nodal disease burden (> 2 nodes).

Theory and Practice of Integrating Machine Learning and Conventional Statistics in Medical Data Analysis

The practice of medical decision making is changing rapidly with the development of innovative computing technologies. The growing interest of data analysis with improvements in big data computer processing methods raises the question of whether machine learning can be integrated with conventional statistics in health research. To help address this knowledge gap, this paper presents a review on the conceptual integration between conventional statistics and machine learning, focusing on the health research. The similarities and differences between the two are compared using mathematical concepts and algorithms. The comparison between conventional statistics and machine learning methods indicates that conventional statistics are the fundamental basis of machine learning, where the black box algorithms are derived from basic mathematics, but are advanced in terms of automated analysis, handling big data and providing interactive visualizations. While the nature of both these methods are different, they are conceptually similar. Based on our review, we conclude that conventional statistics and machine learning are best to be integrated to develop automated data analysis tools. We also strongly believe that machine learning could be explored by health researchers to enhance conventional statistics in decision making for added reliable validation measures.

Is laterality in breast Cancer still worth studying? Local experience in Bahrain

Background

Laterality in breast cancer means an increased frequency of left-sided breast cancers compared to right-sided breast cancers ranging between 1.05 and 1.26. It was first described in 1935 by Fellenberg, Sweden. The explanation of this phenomenon is not clear, but the association with other factors was found. This study aimed to explore the laterality of breast cancer in Bahrain as a model for Arabian countries. The association of laterality with the clinicopathological characteristics of the tumor was also analyzed to explore any applied clinical value.

Methods

This is a cross-sectional, retrospective review of a particular ethnic population to study laterality of breast cancer versus a number of clinicopathological factors, as well as prognosis. The study analyzed 228 breast cancer patients treated in Arabian Gulf University facilities in Bahrain between 1999 and 2020. Three bilateral breast cancer and two malignant phyllodes patients were excluded.

The following variables were analyzed: laterality ratio (Lt/Rt) and the association between laterality and clinicopathological characteristics (age at diagnosis, family history of malignancy, size of the tumor, tumor grade, histological type, hormonal receptors and HER2, axillary lymph node status, tumor stage, five-year survival rate, nulliparity, and multifocality).

Results

The laterality ratio (Lt/Rt) was 1.06 and was 0.97 for patients below 50 years of age, and 1.19 for patients 50 years of age and above.

Analysis of our data showed a statistically significant association between laterality and tumor stage (p. value =0.025) at presentation, and laterality and family history of malignancy (p. value =0.052).

Right-sided breast cancer was associated with a higher positive family history of malignancy and an increased ratio of locally advanced and metastatic disease, and a reduced 5-year survival in relation to size and stage. Left-sided breast cancer was associated with higher early tumor stage.

Conclusion

This is the first study exploring the issue of breast cancer laterality in a defined Arabian population. The laterality ratio in this study was 1.06, which is consistent with the globally published range (1.05 to 1.26) and is increasing with increasing age.

The association between breast cancer laterality, and the hormonal and HER2 is still not widely addressed in the available literature, although other clinicopathological characteristics were extensively analyzed.

A prognostic survival model for women diagnosed with invasive breast cancer in Queensland, Australia

PURPOSE

Prognostic models can help inform patients on the future course of their cancer and assist the decision making of clinicians and patients in respect to management and treatment of the cancer. In contrast to previous studies considering survival following treatment, this study aimed to develop a prognostic model to quantify breast cancer-specific survival at the time of diagnosis.

METHODS

A large (n = 3323), population-based prospective cohort of women were diagnosed with invasive breast cancer in Queensland, Australia between 2010 and 2013, and followed up to December 2018. Data were collected through a validated semi-structured telephone interview and a self-administered questionnaire, along with data linkage to the Queensland Cancer Register and additional extraction from medical records. Flexible parametric survival models, with multiple imputation to deal with missing data, were used.

RESULTS

Key factors identified as being predictive of poorer survival included more advanced stage at diagnosis, higher tumour grade, "triple negative" breast cancers, and being symptom-detected rather than screen detected. The Harrell's C-statistic for the final predictive model was 0.84 (95% CI 0.82, 0.87), while the area under the ROC curve for 5-year mortality was 0.87. The final model explained about 36% of the variation in survival, with stage at diagnosis alone explaining 26% of the variation.

CONCLUSIONS

In addition to confirming the prognostic importance of stage, grade and clinical subtype, these results highlighted the independent survival benefit of breast cancers diagnosed through screening, although lead and length time bias should be considered. Understanding what additional factors contribute to the substantial unexplained variation in survival outcomes remains an important objective.

Association of early changes of circulating cancer stem-like cells with survival among patients with metastatic breast cancer

Background:

This study aimed to investigate the role of circulating tumor cells (CTCs) and circulating cancer stem-like cells (cCSCs) before and after one cycle of chemotherapy and assessed the effects of early changes in CTCs and cCSCs on the outcomes of patients with metastatic breast cancer.

Methods:

Patients with stage IV invasive ductal carcinoma of the breast who received first-line chemotherapy between April 2014 and January 2016 were enrolled. CTCs and cCSCs were measured before the first cycle of chemotherapy (baseline) and on day 21, before the second cycle of chemotherapy commenced; a negative selection strategy and flow cytometry protocol were employed.

Results:

CTC and cCSC counts declined in 68.8 and 45.5% of patients, respectively. Declines in CTCs and cCSCs following the first chemotherapy cycle were associated with superior chemotherapy responses, longer progression-free survival (PFS), and longer overall survival (OS). An early decline in cCSCs remained an independent prognostic indicator for OS and PFS in multivariate analysis.

Conclusions:

A cCSC decline after one cycle of chemotherapy for metastatic breast cancer is predictive of a superior chemotherapy response and longer PFS and OS, implying that cCSC dynamic monitoring may be helpful in early prediction of treatment response and prognosis.

Systemic Treatment of Breast Cancer. 1st Central-Eastern European Professional Consensus Statement on Breast Cancer

This text is based on the recommendations accepted by the 4th Hungarian Consensus Conference on Breast Cancer, modified based on the international consultation and conference within the frames of the Central-Eastern European Academy of Oncology. The professional guideline primarily reflects the resolutions and recommendations of the current ESMO, NCCN and ABC5, as well as that of the St. Gallen Consensus Conference statements. The recommendations cover classical prognostic factors and certain multigene tests, which play an important role in therapeutic decision-making. From a didactic point of view, the text first addresses early and then locally advanced breast cancer, followed by locoregionally recurrent and metastatic breast cancer. Within these, we discuss each group according to the available therapeutic options. At the end of the recommendations, we summarize the criteria for treatment in certain rare clinical situations.

Using population-based data to evaluate the impact of adherence to endocrine therapy on survival in breast cancer through the web-application BreCanSurvPred

We show how the use and interpretation of population-based cancer survival indicators can help oncologists talk with breast cancer (BC) patients about the relationship between their prognosis and their adherence to endocrine therapy (ET). The study population comprised a population-based cohort of estrogen receptor positive BC patients (N = 1268) diagnosed in Girona and Tarragona (Northeastern Spain) and classified according to HER2 status (+ / −), stage at diagnosis (I/II/III) and five-year cumulative adherence rate (adherent > 80%; non-adherent ≤ 80%). Cox regression analysis was performed to identify significant prognostic factors for overall survival, whereas relative survival (RS) was used to estimate the crude probability of death due to BC (P_BC). Stage and adherence to ET were the significant factors for predicting all-cause mortality. Compared to stage I, risk of death increased in stage II (hazard ratio [HR] 2.24, 95% confidence interval [CI]: 1.51–3.30) and stage III (HR 5.11, 95% CI 3.46–7.51), and it decreased with adherence to ET (HR 0.57, 95% CI 0.41–0.59). P_BC differences were higher in non-adherent patients compared to adherent ones and increased across stages: stage I: 6.61% (95% CI 0.05–13.20); stage II: 9.77% (95% CI 0.59–19.01), and stage III: 22.31% (95% CI 6.34–38.45). The age-adjusted survival curves derived from this modeling were implemented in the web application BreCanSurvPred (https://pdocomputation.snpstats.net/BreCanSurvPred). Web applications like BreCanSurvPred can help oncologists discuss the consequences of non-adherence to prescribed ET with patients.

Methodological conduct of prognostic prediction models developed using machine learning in oncology: a systematic review

BACKGROUND

Describe and evaluate the methodological conduct of prognostic prediction models developed using machine learning methods in oncology.

METHODS

We conducted a systematic review in MEDLINE and Embase between 01/01/2019 and 05/09/2019, for studies developing a prognostic prediction model using machine learning methods in oncology. We used the Transparent Reporting of a multivariable prediction model for Individual Prognosis Or Diagnosis (TRIPOD) statement, Prediction model Risk Of Bias ASsessment Tool (PROBAST) and CHecklist for critical Appraisal and data extraction for systematic Reviews of prediction Modelling Studies (CHARMS) to assess the methodological conduct of included publications. Results were summarised by modelling type: regression-, non-regression-based and ensemble machine learning models.

RESULTS

Sixty-two publications met inclusion criteria developing 152 models across all publications. Forty-two models were regression-based, 71 were non-regression-based and 39 were ensemble models. A median of 647 individuals (IQR: 203 to 4059) and 195 events (IQR: 38 to 1269) were used for model development, and 553 individuals (IQR: 69 to 3069) and 50 events (IQR: 17.5 to 326.5) for model validation. A higher number of events per predictor was used for developing regression-based models (median: 8, IQR: 7.1 to 23.5), compared to alternative machine learning (median: 3.4, IQR: 1.1 to 19.1) and ensemble models (median: 1.7, IQR: 1.1 to 6). Sample size was rarely justified (n = 5/62; 8%). Some or all continuous predictors were categorised before modelling in 24 studies (39%). 46% (n = 24/62) of models reporting predictor selection before modelling used univariable analyses, and common method across all modelling types. Ten out of 24 models for time-to-event outcomes accounted for censoring (42%). A split sample approach was the most popular method for internal validation (n = 25/62, 40%). Calibration was reported in 11 studies. Less than half of models were reported or made available.

CONCLUSIONS

The methodological conduct of machine learning based clinical prediction models is poor. Guidance is urgently needed, with increased awareness and education of minimum prediction modelling standards. Particular focus is needed on sample size estimation, development and validation analysis methods, and ensuring the model is available for independent validation, to improve quality of machine learning based clinical prediction models.

Progress on deep learning in digital pathology of breast cancer: a narrative review

BACKGROUND AND OBJECTIVE

Pathology is the gold standard criteria for breast cancer diagnosis and has important guiding value in formulating the clinical treatment plan and predicting the prognosis. However, traditional microscopic examinations of tissue sections are time consuming and labor intensive, with unavoidable subjective variations. Deep learning (DL) can evaluate and extract the most important information from images with less need for human instruction, providing a promising approach to assist in the pathological diagnosis of breast cancer. To provide an informative and up-to-date summary on the topic of DL-based diagnostic systems for breast cancer pathology image analysis and discuss the advantages and challenges to the routine clinical application of digital pathology.

METHODS

A PubMed search with keywords ("breast neoplasm" or "breast cancer") and ("pathology" or "histopathology") and ("artificial intelligence" or "deep learning") was conducted. Relevant publications in English published from January 2000 to October 2021 were screened manually for their title, abstract, and even full text to determine their true relevance. References from the searched articles and other supplementary articles were also studied.

KEY CONTENT AND FINDINGS

DL-based computerized image analysis has obtained impressive achievements in breast cancer pathology diagnosis, classification, grading, staging, and prognostic prediction, providing powerful methods for faster, more reproducible, and more precise diagnoses. However, all artificial intelligence (AI)-assisted pathology diagnostic models are still in the experimental stage. Improving their economic efficiency and clinical adaptability are still required to be developed as the focus of further researches.

CONCLUSIONS

Having searched PubMed and other databases and summarized the application of DL-based AI models in breast cancer pathology, we conclude that DL is undoubtedly a promising tool for assisting pathologists in routines, but further studies are needed to realize the digitization and automation of clinical pathology.

Gene selection using pyramid gravitational search algorithm

Genetics play a prominent role in the development and progression of malignant neoplasms. Identification of the relevant genes is a high-dimensional data processing problem. Pyramid gravitational search algorithm (PGSA), a hybrid method in which the number of genes is cyclically reduced is proposed to conquer the curse of dimensionality. PGSA consists of two elements, a filter and a wrapper method (inspired by the gravitational search algorithm) which iterates through cycles. The genes selected in each cycle are passed on to the subsequent cycles to further reduce the dimension. PGSA tries to maximize the classification accuracy using the most informative genes while reducing the number of genes. Results are reported on a multi-class microarray gene expression dataset for breast cancer. Several feature selection algorithms have been implemented to have a fair comparison. The PGSA ranked first in terms of accuracy (84.5%) with 73 genes. To check if the selected genes are meaningful in terms of patient’s survival and response to therapy, protein-protein interaction network analysis has been applied on the genes. An interesting pattern was emerged when examining the genetic network. HSP90AA1, PTK2 and SRC genes were amongst the top-rated bottleneck genes, and DNA damage, cell adhesion and migration pathways are highly enriched in the network.

Impact of body mass index, weight gain, and metabolic disorders on survival and prognosis in patients with breast cancer who underwent chemotherapy

BACKGROUND

Weight gain during chemotherapy in patients with breast cancer contributes to their poor prognosis. However, a growing number of studies have found that metabolic disorders seem to play a more important role in breast cancer prognosis than weight gain. This study aimed to explore the prognostic effects of body mass index (BMI), weight gain, and metabolic disorders on the overall survival (OS) and prognosis of patients with breast cancer who underwent chemotherapy.

METHODS

Data from the inpatient medical records of patients with breast cancer who underwent chemotherapy at the Beijing Cancer Hospital Breast Cancer Center from January to December 2010 were retrospectively collected, and the patients were followed up until August 2020.

RESULTS

A total of 438 patients with stages I to III breast cancer met the inclusion and exclusion criteria. Forty-nine (11.19%) patients died, while 82 (18.72%) patients had tumor recurrence and metastasis at the last follow-up (August 2020). From the time of diagnosis until after chemotherapy, no significant differences were observed in the body weight (t = 4.694, P < 0.001), BMI categories (χ2 = 19.215, P = 0.001), and incidence of metabolic disorders (χ2 = 24.841, P < 0.001); the BMI categories and weight change had no effect on the OS. Both univariate (χ2 = 6.771, P = 0.009) and multivariate survival analyses (hazard ratio = 2.775, 95% confidence interval [CI]: 1.326-5.807, P = 0.007) showed that low high-density lipoprotein cholesterol (HDL-C) levels at diagnosis had a negative impact on the OS. The multivariate logistic regression analysis showed that the HDL-C level at diagnosis (odds ratio [OR] = 2.200, 95% CI: 0.996-4.859, P = 0.051) and metabolic disorders after chemotherapy (OR = 1.514, 95% CI: 1.047-2.189, P = 0.028) are risk factors for poor prognosis in patients with breast cancer.

CONCLUSIONS

Chemotherapy led to weight gain and aggravated the metabolic disorders in patients with breast cancer. Low HDL-C levels at diagnosis and metabolic disorders after chemotherapy may have negative effects on the OS and prognosis of patients with breast cancer.

Classification of Breast Cancer Nottingham Prognostic Index Using High-Dimensional Embedding and Residual Neural Network

The Nottingham Prognostics Index (NPI) is a prognostics measure that predicts operable primary breast cancer survival. The NPI value is calculated based on the size of the tumor, the number of lymph nodes, and the tumor grade. Next-generation sequencing advancements have led to measuring different biological indicators called multi-omics data. The availability of multi-omics data triggered the challenge of integrating and analyzing these various biological measures to understand the progression of the diseases. High-dimensional embedding techniques are incorporated to present the features in the lower dimension, i.e., in a 2-dimensional map. The dataset consists of three -omics: gene expression, copy number alteration (CNA), and mRNA from 1885 female patients. The model creates a gene similarity network (GSN) map for each omic using t-distributed stochastic neighbor embedding (t-SNE) before being merged into the residual neural network (ResNet) classification model. The aim of this work was to (i) extract multi-omics biomarkers that are associated with the prognosis and prediction of breast cancer survival; and (ii) build a prediction model for multi-class breast cancer NPI classes. We evaluated this model and compared it to different high-dimensional embedding techniques and neural network combinations. The proposed model outperformed the other methods with an accuracy of 98.48%, and the area under the curve (AUC) equals 0.9999. The findings in the literature confirm associations between some of the extracted omics and breast cancer prognosis and survival including CDCA5, IL17RB, MUC2, NOD2 and NXPH4 from the gene expression dataset; MED30, RAD21, EIF3H and EIF3E from the CNA dataset; and CENPA, MACF1, UGT2B7 and SEMA3B from the mRNA dataset.

Classification of Breast Cancer Nottingham Prognostic Index Using High-Dimensional Embedding and Residual Neural Network

Simple Summary

A deep learning model based on multi-omics data to classify Nottingham prognostic Index score levels. The model represents each omic dataset using 2-dimensional map before integrating all omics maps into the prediction model. The literature confirms the relationship between the extracted omics features with the progression and survival of breast cancer.

Abstract

The Nottingham Prognostics Index (NPI) is a prognostics measure that predicts operable primary breast cancer survival. The NPI value is calculated based on the size of the tumor, the number of lymph nodes, and the tumor grade. Next-generation sequencing advancements have led to measuring different biological indicators called multi-omics data. The availability of multi-omics data triggered the challenge of integrating and analyzing these various biological measures to understand the progression of the diseases. High-dimensional embedding techniques are incorporated to present the features in the lower dimension, i.e., in a 2-dimensional map. The dataset consists of three -omics: gene expression, copy number alteration (CNA), and mRNA from 1885 female patients. The model creates a gene similarity network (GSN) map for each omic using t-distributed stochastic neighbor embedding (t-SNE) before being merged into the residual neural network (ResNet) classification model. The aim of this work was to (i) extract multi-omics biomarkers that are associated with the prognosis and prediction of breast cancer survival; and (ii) build a prediction model for multi-class breast cancer NPI classes. We evaluated this model and compared it to different high-dimensional embedding techniques and neural network combinations. The proposed model outperformed the other methods with an accuracy of 98.48%, and the area under the curve (AUC) equals 0.9999. The findings in the literature confirm associations between some of the extracted omics and breast cancer prognosis and survival including CDCA5, IL17RB, MUC2, NOD2 and NXPH4 from the gene expression dataset; MED30, RAD21, EIF3H and EIF3E from the CNA dataset; and CENPA, MACF1, UGT2B7 and SEMA3B from the mRNA dataset.

Estimating latent, dynamic processes of breast cancer tumour growth and distant metastatic spread from mammography screening data

We propose a framework for jointly modelling tumour size at diagnosis and time to distant metastatic spread, from diagnosis, based on latent dynamic sub-models of growth of the primary tumour and of distant metastatic detection. The framework also includes a sub-model for screening sensitivity as a function of latent tumour size. Our approach connects post-diagnosis events to the natural history of cancer and, once refined, may prove useful for evaluating new interventions, such as personalised screening regimes. We evaluate our model-fitting procedure using Monte Carlo simulation, showing that the estimation algorithm can retrieve the correct model parameters, that key patterns in the data can be captured by the model even with misspecification of some structural assumptions, and that, still, with enough data it should be possible to detect strong misspecifications. Furthermore, we fit our model to observational data from an extension of a case-control study of post-menopausal breast cancer in Sweden, providing model-based estimates of the probability of being free from detected distant metastasis as a function of tumour size, mode of detection (of the primary tumour), and screening history. For women with screen-detected cancer and two previous negative screens, the probabilities of being free from detected distant metastases 5 years after detection and removal of the primary tumour are 0.97, 0.89 and 0.59 for tumours of diameter 5, 15 and 35 mm, respectively. We also study the probability of having latent/dormant metastases at detection of the primary tumour, estimating that 33% of patients in our study had such metastases.

Prognostic factors for recurrence in patients with surgically resected non-small cell lung cancer

INTRODUCTION

Patients with lung cancer receive treatment according to National Cancer Comprehensive Network (NCCN) standards. However, disease recurrence is reported in about 30% of patients during the first five years. Our study aimed to establish independent predictors of lung cancer recurrence.

MATERIAL AND METHODS

104 patients with definitive treatment for non-small-cell lung carcinoma receiving standard adjuvant chemotherapy in the period 2014-2018 in our cancer center were retrospectively reviewed. The prognostic significance of five routine immunohistochemical (IHC) markers was examined.

RESULTS

During the follow-up period disease recurrence occurred in 42 (40.4%) of the 104 enrolled patients. The median recurrence-free survival was 56.3 months, range 4-84.0 months (95% CI = 46.866-65.683). The recurrence-free survival rate was 58.8%. The frequencies of locoregional recurrence, lung recurrence, kidney, bone, lymph nodes of the neck, liver, and brain recurrence were 23.8%, 21.5%, 16.7%, 9.5%, 9.5%, 9.5% and 9.5%, respectively.

CONCLUSIONS

Using the Cox regression model, category T, histological differentiation, and smoking status were identified as independent predictors of disease recurrence. The studied biological markers (PD-L1, Ki67, p53, epidermal growth factor receptor, and ALK) did not help the model predict disease recurrence. For statistical reliability, it is necessary to conduct a study on a larger cohort of patients and compare the mutual influence of several biomarkers.