Prognostic factors for metachronous contralateral breast cancer: a comparison of the linear Cox regression model and its artificial neural network extension

Machine Learning in Hypertrophic Cardiomyopathy: Nonlinear Model From Clinical and CMR Features Predicting Cardiovascular Events

BACKGROUND

The cumulative burden of hypertrophic cardiomyopathy (HCM) is significant, with a noteworthy percentage (10%-15%) of patients with HCM per year experiencing major adverse cardiovascular events (MACEs). A current risk stratification scheme for HCM had only limited accuracy in predicting sudden cardiac death (SCD) and failed to account for a broader spectrum of adverse cardiovascular events and cardiac magnetic resonance (CMR) parameters.

OBJECTIVES

This study sought to develop and evaluate a machine learning (ML) framework that integrates CMR imaging and clinical characteristics to predict MACEs in patients with HCM.

METHODS

A total of 758 patients with HCM (67% male; age 49 ± 14 years) who were admitted between 2010 and 2017 from 4 medical centers were included. The ML model was built on the internal discovery cohort (533 patients with HCM, admitted to Fuwai Hospital, Beijing, China) by using the light gradient-boosting machine and internally evaluated using cross-validation. The external test cohort consisted of 225 patients with HCM from 3 medical centers. A total of 14 CMR imaging features (strain and late gadolinium enhancement [LGE]) and 23 clinical variables were evaluated and used to inform the ML model. MACEs included a composite of arrhythmic events, SCD, heart failure, and atrial fibrillation-related stroke.

RESULTS

MACEs occurred in 191 (25%) patients over a median follow-up period of 109.0 months (Q1-Q3: 73.0-118.8 months). Our ML model achieved areas under the curve (AUCs) of 0.830 and 0.812 (internally and externally, respectively). The model outperformed the classic HCM Risk-SCD model, with significant improvement (P < 0.001) of 22.7% in the AUC. Using the cubic spline analysis, the study showed that the extent of LGE and the impairment of global radial strain (GRS) and global circumferential strain (GCS) were nonlinearly correlated with MACEs: an elevated risk of adverse cardiovascular events was observed when these parameters reached the high enough second tertiles (11.6% for LGE, 25.8% for GRS, -17.3% for GCS).

CONCLUSIONS

ML-empowered risk stratification using CMR and clinical features enabled accurate MACE prediction beyond the classic HCM Risk-SCD model. In addition, the nonlinear correlation between CMR features (LGE and left ventricular pressure gradient) and MACEs uncovered in this study provides valuable insights for the clinical assessment and management of HCM.

ResDeepSurv: A Survival Model for Deep Neural Networks Based on Residual Blocks and Self-attention Mechanism

Survival analysis, as a widely used method for analyzing and predicting the timing of event occurrence, plays a crucial role in the medicine field. Medical professionals utilize survival models to gain insight into the effects of patient covariates on the disease, and the correlation with the effectiveness of different treatment strategies. This knowledge is essential for the development of treatment plans and the enhancement of treatment approaches. Conventional survival models, such as the Cox proportional hazards model, require a significant amount of feature engineering or prior knowledge to facilitate personalized modeling. To address these limitations, we propose a novel residual-based self-attention deep neural network for survival modeling, called ResDeepSurv, which combines the benefits of neural networks and the Cox proportional hazards regression model. The model proposed in our study simulates the distribution of survival time and the correlation between covariates and outcomes, but does not impose strict assumptions on the basic distribution of survival data. This approach effectively accounts for both linear and nonlinear risk functions in survival data analysis. The performance of our model in analyzing survival data with various risk functions is on par with or even superior to that of other existing survival analysis methods. Furthermore, we validate the superior performance of our model in comparison to currently existing methods by evaluating multiple publicly available clinical datasets. Through this study, we prove the effectiveness of our proposed model in survival analysis, providing a promising alternative to traditional approaches. The application of deep learning techniques and the ability to capture complex relationships between covariates and survival outcomes without relying on extensive feature engineering make our model a valuable tool for personalized medicine and decision-making in clinical practice.

Unveiling breast cancer risk profiles: a survival clustering analysis empowered by an online web application

Aim: To develop a shiny app for doctors to investigate breast cancer treatments through a new approach by incorporating unsupervised clustering and survival information. Materials & methods: Analysis is based on the Molecular Taxonomy of Breast Cancer International Consortium (METABRIC) dataset, which contains 1726 subjects and 22 variables. Cox regression was used to identify survival risk factors for K-means clustering. Logrank tests and C-statistics were compared across different cluster numbers and Kaplan-Meier plots were presented. Results & conclusion: Our study fills an existing void by introducing a unique combination of unsupervised learning techniques and survival information on the clinician side, demonstrating the potential of survival clustering as a valuable tool in uncovering hidden structures based on distinct risk profiles.

Breast cancer survival analysis agents for clinical decision support

Personalized support and assistance are essential for cancer survivors, given the physical and psychological consequences they have to suffer after all the treatments and conditions associated with this illness. Digital assistive technologies have proved to be effective in enhancing the quality of life of cancer survivors, for instance, through physical exercise monitoring and recommendation or emotional support and prediction. To maximize the efficacy of these techniques, it is challenging to develop accurate models of patient trajectories, which are typically fed with information acquired from retrospective datasets. This paper presents a Machine Learning-based survival model embedded in a clinical decision system architecture for predicting cancer survivors' trajectories. The proposed architecture of the system, named PERSIST, integrates the enrichment and pre-processing of clinical datasets coming from different sources and the development of clinical decision support modules. Moreover, the model includes detecting high-risk markers, which have been evaluated in terms of performance using both a third-party dataset of breast cancer patients and a retrospective dataset collected in the context of the PERSIST clinical study.

Trends and patterns in cancer nanotechnology research: A survey of NCI's caNanoLab and nanotechnology characterization laboratory

Cancer nanotechnologies possess immense potential as therapeutic and diagnostic treatment modalities and have undergone significant and rapid advancement in recent years. With this emergence, the complexities of data standards in the field are on the rise. Data sharing and reanalysis is essential to more fully utilize this complex, interdisciplinary information to answer research questions, promote the technologies, optimize use of funding, and maximize the return on scientific investments. In order to support this, various data-sharing portals and repositories have been developed which not only provide searchable nanomaterial characterization data, but also provide access to standardized protocols for synthesis and characterization of nanomaterials as well as cutting-edge publications. The National Cancer Institute's (NCI) caNanoLab is a dedicated repository for all aspects pertaining to cancer-related nanotechnology data. The searchable database provides a unique opportunity for data mining and the use of artificial intelligence and machine learning, which aims to be an essential arm of future research studies, potentially speeding the design and optimization of next-generation therapies. It also provides an opportunity to track the latest trends and patterns in nanomedicine research. This manuscript provides the first look at such trends extracted from caNanoLab and compares these to similar metrics from the NCI's Nanotechnology Characterization Laboratory, a laboratory providing preclinical characterization of cancer nanotechnologies to researchers around the globe. Together, these analyses provide insight into the emerging interests of the research community and rise of promising nanoparticle technologies.

Development and Validation of a DeepSurv Nomogram to Predict Survival Outcomes and Guide Personalized Adjuvant Chemotherapy in Non-Small Cell Lung Cancer

Objective

To develop and validate a DeepSurv nomogram based on radiomic features extracted from computed tomography images and clinicopathological factors, to predict the overall survival and guide individualized adjuvant chemotherapy in patients with non-small cell lung cancer (NSCLC).

Patients and Methods

This retrospective study involved 976 consecutive patients with NSCLC (training cohort, n=683; validation cohort, n=293). DeepSurv was constructed based on 1,227 radiomic features, and the risk score was calculated for each patient as the output. A clinical multivariate Cox regression model was built with clinicopathological factors to determine the independent risk factors. Finally, a DeepSurv nomogram was constructed by integrating the risk score and independent clinicopathological factors. The discrimination capability, calibration, and clinical usefulness of the nomogram performance were assessed using concordance index evaluation, the Greenwood-Nam-D’Agostino test, and decision curve analysis, respectively. The treatment strategy was analyzed using a Kaplan–Meier curve and log-rank test for the high- and low-risk groups.

Results

The DeepSurv nomogram yielded a significantly better concordance index (training cohort, 0.821; validation cohort 0.768) with goodness-of-fit (P<0.05). The risk score, age, thyroid transcription factor-1, Ki-67, and disease stage were the independent risk factors for NSCLC.The Greenwood-Nam-D’Agostino test showed good calibration performance (P=0.39). Both high- and low-risk patients did not benefit from adjuvant chemotherapy, and chemotherapy in low-risk groups may lead to a poorer prognosis.

Conclusions

The DeepSurv nomogram, which is based on the risk score and independent risk factors, had good predictive performance for survival outcome. Further, it could be used to guide personalized adjuvant chemotherapy in patients with NSCLC.

Use of a deep learning and random forest approach to track changes in the predictive nature of socioeconomic drivers of under-5 mortality rates in sub-Saharan Africa

OBJECTIVES

We used machine learning algorithms to track how the ranks of importance and the survival outcome of four socioeconomic determinants (place of residence, mother's level of education, wealth index and sex of the child) of under-5 mortality rate (U5MR) in sub-Saharan Africa have evolved.

SETTINGS

This work consists of multiple cross-sectional studies. We analysed data from the Demographic Health Surveys (DHS) collected from four countries; Uganda, Zimbabwe, Chad and Ghana, each randomly selected from the four subregions of sub-Saharan Africa.

PARTICIPANTS

Each country has multiple DHS datasets and a total of 11 datasets were selected for analysis. A total of n=85 688 children were drawn from the eleven datasets.

PRIMARY AND SECONDARY OUTCOMES

The primary outcome variable is U5MR; the secondary outcomes were to obtain the ranks of importance of the four socioeconomic factors over time and to compare the two machine learning models, the random survival forest (RSF) and the deep survival neural network (DeepSurv) in predicting U5MR.

RESULTS

Mother's education level ranked first in five datasets. Wealth index ranked first in three, place of residence ranked first in two and sex of the child ranked last in most of the datasets. The four factors showed a favourable survival outcome over time, confirming that past interventions targeting these factors are yielding positive results. The DeepSurv model has a higher predictive performance with mean concordance indexes (between 67% and 80%), above 50% compared with the RSF model.

CONCLUSIONS

The study reveals that children under the age of 5 in sub-Saharan Africa have favourable survival outcomes associated with the four socioeconomic factors over time. It also shows that deep survival neural network models are efficient in predicting U5MR and should, therefore, be used in the big data era to draft evidence-based policies to achieve the third sustainable development goal.

Machine learning-based prediction of 1-year mortality for acute coronary syndrome✰

BACKGROUND

Clinical risk assessment with quantitative formal risk scores may add to intuitive physician risk assessment and are advised by the international guidelines for the management of acute coronary syndrome (ACS) patients. Most previous studies have used the binary regression/classification approach (dead/alive) for long-term mortality post-ACS, without considering the time-to-event as in survival analysis. The use of machine learning (ML)-based survival models has yet to be validated. The primary objective was to compare survival prediction performance of 1-year mortality following ACS of two newly developed ML-based models [random survival forest (RSF) and deep learning (DeepSurv)] with the traditional Cox-proportional hazard (CPH) model. The secondary objective was external validation of the findings.

METHODS

This was a retrospective, supervised learning data mining study based on the Acute Coronary Syndrome Israeli Survey (ACSIS) and the Myocardial Ischemia National Audit Project (MINAP). The ACSIS data were divided to train/test in a 70/30 fashion. Next, the models were externally validated on the MINAP data. Harrell's C-index, inverse probability of censoring weighting (IPCW), and the Brier-score were used for models' performance comparison.

RESULTS

RSF performed best among the three models, with Harrell's C-index on training and testing sets reaching 0.953 and 0.924 respectively, followed by CPH multivariate selected model (0.805/0.849), CPH Univariate selected model (0.828/0.806), DeepSurv model (0.801/0.804), and the traditional CPH model (0.826/0.738). The RSF model also had the highest performance on the validation data set with 0.811 for Harrell's C-index, 0.844 for IPCW, and 0.093 for Brier score. The CPH model performance on the validation set had C-index range between 0.689 to 0.790, 0.713 to 0.826 for IPCW, and 0.094 to 0.103 Brier score.

CONCLUSIONS

RSF survival predictions for long-term mortality post-ACS show improved model performance compared with the classic statistical method. This may benefit patients by allowing better risk stratification and tailored therapy, however further prospective evaluations are required.

Cohort and Trajectory Analysis in Multi-Agent Support Systems for Cancer Survivors

In the past decades, the incidence rate of cancer has steadily risen. Although advances in early and accurate detection have increased cancer survival chances, these patients must cope with physical and psychological sequelae. The lack of personalized support and assistance after discharge may lead to a rapid diminution of their physical abilities, cognitive impairment, and reduced quality of life. This paper proposes a personalized support system for cancer survivors based on a cohort and trajectory analysis (CTA) module integrated within an agent-based personalized chatbot named EREBOTS. The CTA module relies on survival estimation models, machine learning, and deep learning techniques. It provides clinicians with supporting evidence for choosing a personalized treatment, while allowing patients to benefit from tailored suggestions adapted to their conditions and trajectories. The development of the CTA within the EREBOTS framework enables to effectively evaluate the significance of prognostic variables, detect patient's high-risk markers, and support treatment decisions.

Identification of mortality-risk-related missense variant for renal clear cell carcinoma using deep learning

Introduction:

Kidney renal clear cell carcinoma (KIRCC) is a highly heterogeneous and lethal cancer that can arise in patients with renal disease. DeepSurv combines a deep feed-forward neural network with a Cox proportional hazards function and could provide optimized survival results compared with convenient survival analysis.

Methods:

This study used an improved DeepSurv algorithm to identify the candidate genes to be targeted for treatment on the basis of the overall mortality status of KIRCC subjects. All the somatic mutation missense variants of KIRCC subjects were abstracted from TCGA-KIRC database.

Results:

The improved DeepSurv model (95.1%) achieved greater balanced accuracy compared with the DeepSurv model (75%), and identified 610 high-risk variants associated with overall mortality. The results of gene differential expression analysis also indicated nine KIRCC mortality-risk-related pathways, namely the tRNA charging pathway, the D-myo-inositol-5-phosphate metabolism pathway, the DNA double-strand break repair by nonhomologous end-joining pathway, the superpathway of inositol phosphate compounds, the 3-phosphoinositide degradation pathway, the production of nitric oxide and reactive oxygen species in macrophages pathway, the synaptic long-term depression pathway, the sperm motility pathway, and the role of JAK2 in hormone-like cytokine signaling pathway. The biological findings in this study indicate the KIRCC mortality-risk-related pathways were more likely to be associated with cancer cell growth, cancer cell differentiation, and immune response inhibition.

Conclusion:

The results proved that the improved DeepSurv model effectively classified mortality-related high-risk variants and identified the candidate genes. In the context of KIRCC overall mortality, the proposed model effectively recognized mortality-related high-risk variants for KIRCC.

CNN-based survival model for pancreatic ductal adenocarcinoma in medical imaging

Background

Cox proportional hazard model (CPH) is commonly used in clinical research for survival analysis. In quantitative medical imaging (radiomics) studies, CPH plays an important role in feature reduction and modeling. However, the underlying linear assumption of CPH model limits the prognostic performance. In this work, using transfer learning, a convolutional neural network (CNN) based survival model was built and tested on preoperative CT images of resectable Pancreatic Ductal Adenocarcinoma (PDAC) patients.

Results

The proposed CNN-based survival model outperformed the traditional CPH-based radiomics approach in terms of concordance index and index of prediction accuracy, providing a better fit for patients’ survival patterns.

Conclusions

The proposed CNN-based survival model outperforms CPH-based radiomics pipeline in PDAC prognosis. This approach offers a better fit for survival patterns based on CT images and overcomes the limitations of conventional survival models.

Prediction and clinical utility of a contralateral breast cancer risk model

BACKGROUND

Breast cancer survivors are at risk for contralateral breast cancer (CBC), with the consequent burden of further treatment and potentially less favorable prognosis. We aimed to develop and validate a CBC risk prediction model and evaluate its applicability for clinical decision-making.

METHODS

We included data of 132,756 invasive non-metastatic breast cancer patients from 20 studies with 4682 CBC events and a median follow-up of 8.8 years. We developed a multivariable Fine and Gray prediction model (PredictCBC-1A) including patient, primary tumor, and treatment characteristics and BRCA1/2 germline mutation status, accounting for the competing risks of death and distant metastasis. We also developed a model without BRCA1/2 mutation status (PredictCBC-1B) since this information was available for only 6% of patients and is routinely unavailable in the general breast cancer population. Prediction performance was evaluated using calibration and discrimination, calculated by a time-dependent area under the curve (AUC) at 5 and 10 years after diagnosis of primary breast cancer, and an internal-external cross-validation procedure. Decision curve analysis was performed to evaluate the net benefit of the model to quantify clinical utility.

RESULTS

In the multivariable model, BRCA1/2 germline mutation status, family history, and systemic adjuvant treatment showed the strongest associations with CBC risk. The AUC of PredictCBC-1A was 0.63 (95% prediction interval (PI) at 5 years, 0.52-0.74; at 10 years, 0.53-0.72). Calibration-in-the-large was -0.13 (95% PI: -1.62-1.37), and the calibration slope was 0.90 (95% PI: 0.73-1.08). The AUC of Predict-1B at 10 years was 0.59 (95% PI: 0.52-0.66); calibration was slightly lower. Decision curve analysis for preventive contralateral mastectomy showed potential clinical utility of PredictCBC-1A between thresholds of 4-10% 10-year CBC risk for BRCA1/2 mutation carriers and non-carriers.

CONCLUSIONS

We developed a reasonably calibrated model to predict the risk of CBC in women of European-descent; however, prediction accuracy was moderate. Our model shows potential for improved risk counseling, but decision-making regarding contralateral preventive mastectomy, especially in the general breast cancer population where limited information of the mutation status in BRCA1/2 is available, remains challenging.

Dynamic Prediction in Clinical Survival Analysis Using Temporal Convolutional Networks

Accurate prediction of disease trajectories is critical for early identification and timely treatment of patients at risk. Conventional methods in survival analysis are often constrained by strong parametric assumptions and limited in their ability to learn from high-dimensional data. This paper develops a novel convolutional approach that addresses the drawbacks of both traditional statistical approaches as well as recent neural network models for survival. We present Match-Net: a missingness-aware temporal convolutional hitting-time network, designed to capture temporal dependencies and heterogeneous interactions in covariate trajectories and patterns of missingness. To the best of our knowledge, this is the first investigation of temporal convolutions in the context of dynamic prediction for personalized risk prognosis. Using real-world data from the Alzheimer's disease neuroimaging initiative, we demonstrate state-of-the-art performance without making any assumptions regarding underlying longitudinal or time-to-event processes-attesting to the model's potential utility in clinical decision support.

Flexible Modelling in Survival Analysis. Structuring Biological Complexity from the Information Provided by Tumor Markers

The aim of the present article is to introduce and discuss the problem of optimal modelling of the prognostic information provided by putative prognostic variables, possibly measured on a quantitative scale. A number of methodological aspects will be treated, with particular reference to the role of spline functions and artificial neural networks, which will be discussed in the context of the analysis of survival data. The problem of the evaluation and the choice of the optimal statistical models will be examined, with particular attention to the critical aspects related to the definition of prognostic indexes on the basis of the results of the selected models. Clinical examples in breast cancer on the evaluation of the prognostic impact of several tumor markers are provided. This paper is addressed to all researchers who are interested in the evaluation of the prognostic role of tumor markers, therefore we will stress the necessity of integrating the methodologies of biological, clinical and statistical research in the assessment of prognosis.

DeepSurv: personalized treatment recommender system using a Cox proportional hazards deep neural network

Background

Medical practitioners use survival models to explore and understand the relationships between patients’ covariates (e.g. clinical and genetic features) and the effectiveness of various treatment options. Standard survival models like the linear Cox proportional hazards model require extensive feature engineering or prior medical knowledge to model treatment interaction at an individual level. While nonlinear survival methods, such as neural networks and survival forests, can inherently model these high-level interaction terms, they have yet to be shown as effective treatment recommender systems.

Methods

We introduce DeepSurv, a Cox proportional hazards deep neural network and state-of-the-art survival method for modeling interactions between a patient’s covariates and treatment effectiveness in order to provide personalized treatment recommendations.

Results

We perform a number of experiments training DeepSurv on simulated and real survival data. We demonstrate that DeepSurv performs as well as or better than other state-of-the-art survival models and validate that DeepSurv successfully models increasingly complex relationships between a patient’s covariates and their risk of failure. We then show how DeepSurv models the relationship between a patient’s features and effectiveness of different treatment options to show how DeepSurv can be used to provide individual treatment recommendations. Finally, we train DeepSurv on real clinical studies to demonstrate how it’s personalized treatment recommendations would increase the survival time of a set of patients.

Conclusions

The predictive and modeling capabilities of DeepSurv will enable medical researchers to use deep neural networks as a tool in their exploration, understanding, and prediction of the effects of a patient’s characteristics on their risk of failure.

Clinicopathological Profile and Treatment Outcomes of Bilateral Breast Cancer: A Study from Tertiary Cancer Center in South India

Background: Bilateral breast cancer (BBC) is a rare clinical entity with limited data regarding clinicopathological aspects and treatment guidelines. Materials and Methods: This was an observational study of patients diagnosed with BBC from August 2012 to July 2014. Synchronous breast cancers (SBCs) was defined as two tumors diagnosed within an interval of 6 months and metachronous breast cancer (MBC) as second cancer diagnosed after 6 months. Results: Out of 750 breast cancer patients seen during a 2-year period, 35 had BBC. Ten patients were diagnosed as SBC whereas 25 patients as MBC. Among patients with MBC, the average time for development of contralateral breast cancer was 5 years. In 8 patients, the contralateral breast cancer was detected mammography whereas rest 27 patients were detected by clinical breast examination. At a median follow-up of 24 months, 23 (66%) patients were disease free, 9 (26%) patients had disease relapse, and 3 (8%) patients succumbed to the progressive disease. Conclusions: Every patient with breast cancer should be regularly followed up with clinical breast examination at a more frequent interval. The role of frequent clinical breast examination appears more than mammography especially beyond 5 years for early detection of contralateral breast cancer.

Complementarity of Clinician Judgment and Evidence Based Models in Medical Decision Making: Antecedents, Prospects, and Challenges

Early accounts of the development of modern medicine suggest that the clinical skills, scientific competence, and doctors' judgment were the main impetus for treatment decision, diagnosis, prognosis, therapy assessment, and medical progress. Yet, clinician judgment has its own critics and is sometimes harshly described as notoriously fallacious and an irrational and unfathomable black box with little transparency. With the rise of contemporary medical research, the reputation of clinician judgment has undergone significant reformation in the last century as its fallacious aspects are increasingly emphasized relative to the evidence based options. Within the last decade, however, medical forecasting literature has seen tremendous change and new understanding is emerging on best ways of sharing medical information to complement the evidence based medicine practices. This review revisits and highlights the core debate on clinical judgments and its interrelations with evidence based medicine. It outlines the key empirical results of clinician judgments relative to evidence based models and identifies its key strengths and prospects, the key limitations and conditions for the effective use of clinician judgment, and the extent to which it can be optimized and professionalized for medical use.

Contralateral breast cancer: a clinico-pathological study of second primaries in opposite breasts after treatment of breast malignancy

BACKGROUND

Breast cancer is by far the most frequent cancer of women (23 % of all cancers), ranking second overall when both sexes are considered together. Contralateral breast cancer (CBC) is becoming an important public health issue because of the increased incidence of primary breast cancer and improved survival. The present communication concerns a study to evaluate the role of various clinico-pathological factors on the occurrence of contralateral breast cancer.

MATERIALS AND METHODS

A detailed analysis was carried out with respect to age, menopausal status, family history, disease stage, surgery performed, histopathology, hormone receptor status, and use of chemotherapy or hormonal therapy. The diagnosis of CBC was confirmed on histopathology report. Relative risk with 95%CI was calculated for different risk factors of contralateral breast cancer development.

RESULTS

CBC was found in 24 (4.5%) out of 532 patients. Mean age of presentation was 43.2 years. Family history of breast cancer was found in 37.5% of the patients. There was statistically significant higher rate (83.3%) of CBC in patients in age group of 20-40 years with RR=11.3 (95% CI: 1.4, 89.4, p=0.006) seen in 20-30 years and RR=10.8 (95% CI:1.5-79.6, p=0.002) in 30-40 years as compared to older age of 60-70 years. Risk of development was higher in premenopausal women (RR=8.6, 95% CI: 3.5-21.3, p≤0.001). Women with family history of breast cancer had highest rate (20.9%) of CBC (RR=5.4, 95% CI: 2.5-11.6, p≤0.001). Use of hormonal therapy in hormone receptor positive patients was protective factor in occurrence of CBC but not significant (RR=0.7, 95% CI: 0.3-1.5, p=0.333).

CONCLUSIONS

Younger age, premenopausal status, and presence of family history were found to be significant risk factors for the development of CBC. Use of hormonal therapy in hormone receptor positive patients might be protective against occurrence of CBC but did not reach significance.

Prognostic factors of second primary contralateral breast cancer in early-stage breast cancer

The aim of the present study was to investigate the therapeutic outcome of early-stage breast cancer (pT1aN0M0) and to identify prognostic factors for secondary primary contralateral breast cancer (CBC). A total of 85 patients with mammary carcinomas were included. All patients had undergone breast surgery and adjuvant treatment between January 2001 and December 2008 at the Central Hospital of Grenoble University (Grenoble, France). The primary end-points were disease-free survival and secondary CBC, and the potential prognostic factors were investigated. During a median follow-up of 60 months, 10 of the 85 patients presented with secondary primary cancer, of which six suffered with CBC. No patient mortalities were reported. The rates of CBC were 2.35, 3.53 and 7.06% at one, two and five years, respectively. The cumulative univariate analysis showed that microinvasion and family history are potential risk factors for newly CBC. The current study also demonstrated that secondary CBC was more likely to occur in patients with microinvasion or a family history of hte dise. In addition, the systematic treatment of secondary CBC should include hormone therapy.

A gradient boosting algorithm for survival analysis via direct optimization of concordance index

Survival analysis focuses on modeling and predicting the time to an event of interest. Many statistical models have been proposed for survival analysis. They often impose strong assumptions on hazard functions, which describe how the risk of an event changes over time depending on covariates associated with each individual. In particular, the prevalent proportional hazards model assumes that covariates are multiplicatively related to the hazard. Here we propose a nonparametric model for survival analysis that does not explicitly assume particular forms of hazard functions. Our nonparametric model utilizes an ensemble of regression trees to determine how the hazard function varies according to the associated covariates. The ensemble model is trained using a gradient boosting method to optimize a smoothed approximation of the concordance index, which is one of the most widely used metrics in survival model performance evaluation. We implemented our model in a software package called GBMCI (gradient boosting machine for concordance index) and benchmarked the performance of our model against other popular survival models with a large-scale breast cancer prognosis dataset. Our experiment shows that GBMCI consistently outperforms other methods based on a number of covariate settings. GBMCI is implemented in R and is freely available online.

Estrogen receptor status in relation to risk of contralateral breast cancer-a population-based cohort study

Background

It is unclear whether estrogen receptor (ER)-status of first primary breast cancer is associated with risk of metachronous (non-simultaneous) contralateral breast cancer (CBC), and to what extent endocrine therapy affects this association.

Methods

We studied the effect of ER-status of the first cancer on the risk of CBC overall, and for different ER-subtypes of CBC, using a large, population-based cohort. The cohort consisted of all women diagnosed with breast cancer in the Stockholm region 1976–2005; 25715 patients, of whom 940 suffered CBC. The relative risk was analyzed mainly using standardized incidence ratios (SIR).

Results

Women with breast cancer had a doubled risk of CBC compared to the risk of breast cancer in the general female population (SIR: 2.22 [2.08–2.36]), for women with a previous ER-positive cancer: SIR = 2.30 (95% CI:2.11–2.50) and for women with a previous ER-negative cancer: SIR = 2.17 (95% CI:1.82–2.55). The relative risk of ER-positive and ER-negative CBC was very similar for women with ER-positive first cancer (SIR = 2.02 [95%CI: 1.80–2.27] and SIR = 1.89 [95%CI: 1.46–2.41] respectively) while for patients with ER-negative first cancer the relative risk was significantly different (SIR = 1.27 [95% CI:0.94–1.68] for ER-positive CBC and SIR = 4.96 [95%CI:3.67–6.56] for ER-negative CBC). Patients with ER-positive first cancer who received hormone therapy still had a significantly higher risk of CBC than the risk of breast cancer for the general female population (SIR = 1.74 [95% CI:1.47–2.03]).

Conclusion

The risk of CBC for a breast cancer patient is increased to about two-fold, compared to the risk of breast cancer in the general female population. This excess risk decreases, but does not disappear, with adjuvant endocrine therapy. Patients with ER-positive first cancers have an increased risk for CBC of both ER subtypes, while patients with ER-negative first cancer have a specifically increased risk of ER-negative CBC.

Relation of risk of contralateral breast cancer to the interval since the first primary tumour

BACKGROUND

There is no consensus on how to separate contralateral breast cancer (CBC) occurring as distant spread of the primary breast cancer (BC) from an independent CBC.

METHODS

We used standardised incidence ratios (SIRs) to analyse the variations in the risk of CBC over time among 6629 women with BC diagnosed between 1954 and 1983. To explore the most appropriate cutoff to separate the two types of CBC, we analysed the deviance between models including different cutoff points as compared with the basal model with no cutoff date. We also performed a prognostic study through a Cox model.

RESULTS

The SIR was much higher during the first 2 years of follow-up than afterwards. The best cutoff appeared to be 2 years. The risk of early CBC was linked to tumour spread and the risk of late CBC was linked to age and to the size of the tumour. Radiotherapy was not selected by the model either for early or late CBC risk.

CONCLUSION

A clearer pattern of CBC risk might appear if studies used a similar cutoff time after the initial BC.

Second primary in the contralateral breast after treatment of breast cancer

PURPOSE

To study the potential risk factors for contralateral breast cancer (CBC) in women after treatment of the primary breast cancer.

PATIENTS AND METHODS

Between January 1985 and December 1995, records of 1084 breast cancer patients at our institution were analyzed for incidence of CBC. In all the patients a detailed analysis was carried out with respect to age, disease stage, radiation therapy technique, dose, the use of chemotherapy or hormone therapy, and other clinical and/or pathologic characteristics. The Kaplan-Meier method was used to estimate the acturial rate of CBC. The Cox proportional hazard regression model was used to estimate the relative risk (RR) of CBC.

RESULTS

Up to December 2005, the median follow up was 12 years. Overall incidence of CBC was 4%. The 10 and 20 year acturial rate of CBC was 5.6% and 11.3%, respectively. The CBC rate at 10 and 20 year was 5.4% and 10.2%, respectively, for patients with mastectomy only and 5.1% and 9.7%, respectively, in the mastectomy plus RT group (p=0.3). In the subset of patients <45 years of age at the time of treatment, 10 and 20 year acturial rate of CBC was 5% and 9%, respectively, for patients who underwent mastectomy only and 6.3% and 11%, respectively, for patients treated with mastectomy plus RT (RR=1.4, 95% CI: 1.14-1.45, p=0.003). There was statistically significant lower rate of CBC in patients given adjuvant hormonal therapy (8.5%) as compared to those without hormonal therapy (14.3%, p=0.004) at 20 year. Women with family history of breast cancer had highest rate (15.3%) of CBC (RR=1.6, 95% CI: 1.12-1.27) at 20 years. The adjuvant use of chemotherapy did not significantly affect the risk of second malignancy.

CONCLUSION

There seems to be little risk of second malignancies in patients treated with mastectomy plus RT using modern techniques, compared with mastectomy only, that was only prevalent in patients <45 years of age. Family history of breast cancer seems to be the highest risk factor for CBC.

Incidence and Prognosis of Synchronous and Metachronous Bilateral Breast Cancer

Purpose

Because the incidence of breast cancer is increasing and prognosis is improving, a growing number of women are at risk of developing bilateral disease. Little is known, however, about incidence trends and prognostic features of bilateral breast cancer.

Patients and Methods

Among 123,757 women with a primary breast cancer diagnosed in Sweden from 1970 to 2000, a total of 6,550 developed bilateral breast cancer. We separated synchronous (diagnosed within 3 months after a first breast cancer) and metachronous bilateral cancer, and analyzed incidence and mortality rates of breast cancer using Poisson regression models.

Results

The incidence of synchronous breast cancer increased by age and by 40% during the 1970s, whereas the incidence of metachronous cancer decreased by age and by approximately 30% since the early 1980s, most likely due to increasing use of adjuvant therapy. Women who developed bilateral cancer within 5 years and at age younger than 50 years were 3.9 times (95% CI, 3.5 to 4.5) more likely to die as a result of breast cancer than women with unilateral cancer. Women with a bilateral cancer diagnosed more than 10 years after the first cancer had a prognosis similar to that of a unilateral breast cancer. Adjuvant chemotherapy of primary cancer is a predictor of poor survival after diagnosis of early metachronous cancers.

Conclusion

We found profound differences in the incidence trends and prognostic outlook between synchronous and metachronous bilateral breast cancer diagnosed at different ages. Adjuvant chemotherapy therapy has a dual effect on metachronous cancer: it reduces the risk, while at the same time it seems to worsen the prognosis.

Double-blind evaluation and benchmarking of survival models in a multi-centre study

Accurate modelling of time-to-event data is of particular importance for both exploratory and predictive analysis in cancer, and can have a direct impact on clinical care. This study presents a detailed double-blind evaluation of the accuracy in out-of-sample prediction of mortality from two generic non-linear models, using artificial neural networks benchmarked against a partial logistic spline, log-normal and COX regression models. A data set containing 2880 samples was shared over the Internet using a purpose-built secure environment called GEOCONDA (www.geoconda.com). The evaluation was carried out in three parts. The first was a comparison between the predicted survival estimates for each of the four survival groups defined by the TNM staging system, against the empirical estimates derived by the Kaplan-Meier method. The second approach focused on the accurate prediction of survival over time, quantified with the time dependent C index (C(td)). Finally, calibration plots were obtained over the range of follow-up and tested using a generalization of the Hosmer-Lemeshow test. All models showed satisfactory performance, with values of C(td) of about 0.7. None of the models showed a systematic tendency towards over/under estimation of the observed survival at tau=3 and 5 years. At tau=10 years, all models underestimated the observed survival, except for COX regression which returned an overestimate. The study presents a robust and unbiased benchmarking methodology using a bespoke web facility. It was concluded that powerful, recent flexible modelling algorithms show a comparative predictive performance to that of more established methods from the medical and biological literature, for the reference data set.

Artificial neural network for the joint modelling of discrete cause-specific hazards

OBJECTIVE

Artificial neural network (ANN) based regression methods have been introduced for modelling censored survival data to account for complex prognostic patterns. In the framework of ANN extensions of generalized linear models for survival data, PLANN is a partial logistic ANN, suitable for smoothed discrete hazard estimation as a function of time and covariates. An extension of PLANN for competing risks analysis (PLANNCR) is now proposed for discrete or grouped survival times, resorting to the multinomial likelihood.

METHODS AND MATERIALS

PLANNCR is built by assigning input nodes to the explanatory variables with the time interval treated as an ordinal variable. The logistic function is used as activation for the hidden nodes of the network, whereas the softmax, which corresponds to the canonical link of generalized linear models for polytomous regression, is adopted for multiple output nodes, to provide a smoothed estimation of discrete conditional event probabilities for each event. The Kullback-Leibler distance is used as error function for the target vectors, amounting to half of the deviance of a multinomial logistic regression model. PLANNCR can jointly model non-linear, non-proportional and non-additive effects on cause-specific hazards (CSHs). The degree of smoothing is modulated by the number of hidden nodes and penalization of the error function (weight decay). Model optimisation is achieved by quasi-Newton algorithms, while non-linear cross-validation (NCV) and the Network Information Criterion (NIC) were adopted for model selection. PLANNCR was applied to data on 1793 women with primary invasive breast cancer, histologically N-, who underwent surgery at the Milan Cancer Institute between 1981 and 1986.

RESULTS

Differential effects of covariates and time on the shape of the CSH for the three main failure causes, namely intra-breast tumor recurrences, distant metastases and contralateral breast cancer, have been enlightened.

CONCLUSIONS

PLANNCR can be suitably adopted in an exploratory framework for a thorough evaluation of the disease dynamics in the presence of competing risks.

High risk of contralateral breast carcinoma in women with hereditary/familial non-BRCA1/BRCA2 breast carcinoma

BACKGROUND

The objectives of the current study were to estimate the risk of developing contralateral breast carcinoma (CBC) among women with hereditary/familial non-BRCA1/BRCA2 breast carcinoma and to determine the factors that may predict their risk of CBC.

METHODS

The study sample consisted of all families (n = 217 families) that were referred between 1994-2001 to the Clinic of Cancer Genetics at the University Hospital of Umeå for suspected hereditary breast carcinoma. The study included all women in the 217 families who had carcinoma of the breast as their first primary invasive malignancy diagnosed between 1970-2001 in northern Sweden. Exclusion criteria were an estimated lifetime risk < 20%, BRCA1/BRCA2 mutation, noninvasive carcinoma (ductal or lobular carcinoma in situ), and bilateral breast carcinoma. In the final analysis, 204 women were included from 120 families.

RESULTS

The cumulative probability of developing CBC among women who had hereditary/familial non-BRCA1/BRCA2 breast carcinoma after 20 years was 27.3% (95% confidence interval, 15.0-37.8) compared with the expected risk (4.9%) among women in northern Sweden who had primary breast carcinoma. A significantly increased risk of CBC was associated with age younger than 50 years at the time of diagnosis of the first primary breast carcinoma (P = 0.006). Adjuvant hormone therapy reduced the risk of CBC (P = 0.036).

CONCLUSIONS

Women with hereditary/familial non-BRCA1/BRCA2 breast carcinoma had a high risk of developing CBC. This risk was attenuated further among women who were younger at the time of onset, who had a cumulative probability of developing CBC of nearly 40% after 15 years, which is similar to the estimated risk among BRCA1/BRCA2 mutation carriers. The results of this study emphasized the importance of genetic counseling for these women.

Risk of second primary cancer in the contralateral breast in women treated for early-stage breast cancer: a population-based study

PURPOSE

To study the potential risk factors, including radiotherapy (RT) for contralateral breast cancer (CBC), in patients treated for early-stage breast cancer.

METHODS AND MATERIALS

The Surveillance, Epidemiology, and End Results database (1973-1996) was used to study the incidence of CBC after breast cancer. The Cox proportional hazards regression model was used to estimate the relative risk (RR) of CBC, with adjustment for confounders, including age, race, histologic subtype, and use of RT. Information on the use of hormonal therapy and chemotherapy was not available in the Surveillance, Epidemiology, and End Results database.

RESULTS

A CBC was documented in 5679 (4.2%) of the 134501 localized invasive or intraductal breast cancer patients surviving at least 3 months. The 10- and 20-year actuarial rate of CBC was 6.1% and 12%, respectively. In multivariate analysis, medullary carcinoma (RR = 1.18, 95% confidence interval [CI] 1.02-1.37), black race (RR = 1.20, 95% CI 1.08-1.33), and age >55 years at initial diagnosis (RR = 1.15, 95% CI 1.08-1.22) were associated with increased CBC risk. A total of 1234 (3.3%) of 37,379 patients who received RT developed CBC, and 4445 (4.6%) of 97122 patients who did not receive RT developed CBC. Overall, RT was not associated with an increased risk of CBC (RR = 1.04, 95% CI 0.97-1.10) in multivariate analysis. The CBC risk associated with RT varied substantially with the length of follow-up. During the first 5 years of follow-up, RT was not associated with an increased CBC risk (age-adjusted RR = 0.96, 95% CI 0.88-1.04). For patients surviving for >5 years, RT was associated with a 14% increase in CBC risk (RR = 1.14, 95% CI 1.03-1.26). The increased CBC risk with RT was evident in patients aged <45 years (RR = 1.32, p = 0.01) and >55 years (RR = 1.15, p = 0.04) at initial diagnosis. The 5-, 10-, 15-, and 20-year actuarial rate of CBC was 2.9%, 6.5%, 10.2%, and 13.4%, respectively, for patients with RT; the corresponding rates were 3.0%, 6.0%, 8.9%, and 11.8% for patients without RT. The absolute increase in CBC risk associated with RT was 0.5%, 1.3%, and 1.6% in the 10-, 15-, and 20-year actuarial rate, respectively.

CONCLUSION

CBC is not uncommon after breast cancer, especially for certain subsets of patients. RT was associated with a very small increased long-term CBC risk. This minimal increase in CBC risk should not affect clinical decision-making in treatment selection for patients with localized invasive breast cancer or ductal carcinoma in situ. Unnecessary radiation exposure to the contralateral breast should be avoided for all patients with early-stage breast cancer.

Evaluation of inherent performance of intelligent medical decision support systems: utilising neural networks as an example

Researchers who design intelligent systems for medical decision support, are aware of the need for response to real clinical issues, in particular the need to address the specific ethical problems that the medical domain has in using black boxes. This means such intelligent systems have to be thoroughly evaluated, for acceptability. Attempts at compliance, however, are hampered by lack of guidelines. This paper addresses the issue of inherent performance evaluation, which researchers have addressed in part, but a Medline search, using neural networks as an example of intelligent systems, indicated that only about 12.5% evaluated inherent performance adequately. This paper aims to address this issue by concentrating on the possible evaluation methodology, giving a framework and specific suggestions for each type of classification problem. This should allow the developers of intelligent systems to produce evidence of a sufficiency of output performance evaluation.

A general framework for neural network models on censored survival data

Flexible parametric techniques for regression analysis, such as those based on feed forward artificial neural networks (FFANNs), can be useful for the statistical analysis of censored time data. These techniques are of particular interest for the study of the outcome dependence from several variables measured on a continuous scale, since they allow for the detection of complex non-linear and non-additive effects. Few efforts have been made until now to account for censored times in FFANNs. In the attempt to fill this gap, specific error functions and data representation will be introduced for multilayer perceptron and radial basis function extensions of generalized linear models for survival data.

A review of evidence of health benefit from artificial neural networks in medical intervention

The purpose of this review is to assess the evidence of healthcare benefits involving the application of artificial neural networks to the clinical functions of diagnosis, prognosis and survival analysis, in the medical domains of oncology, critical care and cardiovascular medicine. The primary source of publications is PUBMED listings under Randomised Controlled Trials and Clinical Trials. The rĵle of neural networks is introduced within the context of advances in medical decision support arising from parallel developments in statistics and artificial intelligence. This is followed by a survey of published Randomised Controlled Trials and Clinical Trials, leading to recommendations for good practice in the design and evaluation of neural networks for use in medical intervention.

Reconstructive management of contralateral breast cancer in patients who previously underwent unilateral breast reconstruction

When a patient who has had unilateral breast reconstruction presents with a new cancer on the opposite side, the reconstructive management of the second breast can be unclear. This study was performed to determine whether reconstruction of the second breast is oncologically reasonable and to evaluate the reconstructive options available to these patients. Patients who had mastectomy with unilateral breast reconstruction between 1988 and 1994 and who had a minimal follow-up of 5 years from the initial breast cancer were reviewed. Of 469 patients reviewed, 18 patients (4 percent) were identified who developed contralateral breast cancer. Mean age at the initial breast cancer presentation was 43 years (range, 26 to 57 years), and mean age at presentation with contralateral breast cancer was 48 years (range, 36 to 67). The mean interval between the initial and contralateral breast cancer presentations was 5 years (range, 1 to 10 years). Mean follow-up from the time of contralateral breast cancer was 5 years (range, 1 to 9 years). In most cases, contralateral breast cancer presented at an early stage (13 of 18 patients; 72 percent), and a shift to an earlier stage at presentation of the contralateral cancer was evident compared with the initial breast cancer. Of the 18 patients who developed contralateral breast cancer, 16 (89 percent) had no evidence of disease, one was alive with disease, and one died. Reconstructive management after the initial mastectomy included 16 transverse rectus abdominis myocutaneous flaps (seven free and nine pedicled), one latissimus dorsi myocutaneous flap with implant, and one superior gluteal free flap. Surgical management of the second breast after contralateral breast cancer included breast conservation in two patients, mastectomy without reconstruction in four, and mastectomy with reconstruction in 12. Reconstruction of the second breast included one free transverse rectus abdominis myocutaneous flap, three extended latissimus dorsi flaps, two latissimus dorsi myocutaneous flaps with implants, three implants alone, two Rubens flaps, and one superior gluteal free flap. No major complications were noted after the reconstruction of the second breast. The best symmetry was obtained when similar methods and tissues were used on both sides. The incidence of contralateral breast cancer after mastectomy and unilateral breast reconstruction is low. In most cases, contralateral breast cancer presents at an earlier stage compared with the initial breast cancer, and the prognosis is good. In patients who develop a contralateral breast cancer after mastectomy and unilateral breast reconstruction, the reconstruction of the second breast after mastectomy is oncologically reasonable and should be offered to provide optimal breast symmetry and a better quality of life. The best result is obtained when similar methods and tissues are used on both sides.

Clinical and histological predictors of contralateral breast cancer

AIMS

Women previously treated for primary operable breast cancer are at increased risk of developing cancer in the contralateral breast. The purpose of this study was to assess the annual incidence of metachronous contralateral breast cancer (CBC) and to identify factors that predict for its development.

METHODS

A retrospective study was performed on 3211 women aged </=70 years treated for primary operable breast cancer between 1975 and 1995.

RESULTS

Eighty-three developed CBC prior to locoregional or distant recurrence from the first primary. The clinical incidence of CBC was 6.4 per 1000 women years, three to four times the risk of occurrence of breast cancer in the general female population (or a risk of six to eight times to the remaining breast). Strong family history, age of onset <50 years and lobular histology were significant factors predicting for CBC in univariate and multivariate models. Other clinical factors (previous hormone therapy, chemotherapy, radiotherapy) or histological factors (DCIS, invasive tumour size, grade, vascular invasion, lymph node and oestrogen receptor status) were not significant predictors for CBC.

CONCLUSIONS

In women previously treated for primary operable breast cancer, early age of onset and a strong family history are predictors for the subsequent development of metachronous CBC. Ipsilateral mastectomy with contralateral prophylactic mastectomy with or without immediate breast reconstruction is a reasonable option for a young woman diagnosed with breast cancer and who has a strong family history, particularly if the cancer has histological features suggesting a good prognosis.

Randomized trial of fenretinide to prevent second breast malignancy in women with early breast cancer

BACKGROUND

Fenretinide, a vitamin A analogue, has been shown to inhibit breast carcinogenesis in preclinical studies. We determined the efficacy of fenretinide in preventing a second breast malignancy in women with breast cancer.

METHODS

We randomly assigned 2972 women, aged 30-70 years, with surgically removed stage I breast cancer or ductal carcinoma in situ to receive for 5 years either fenretinide orally (200 mg/day) or no treatment. The primary end point was the incidence of contralateral breast cancer or ipsilateral breast cancer 7 years after randomization. Other end points considered post hoc were the same outcomes stratified by menopausal status, incidence of distant metastases, overall mortality, and tumors in other organs. The hazards of breast cancer occurrence were determined by Cox proportional hazards regression analysis. Statistical tests were two-sided.

RESULTS

At a median observation time of 97 months, there were no statistically significant differences in the occurrence of contralateral breast cancer (P =.642) or ipsilateral breast cancer (P =.177) between the two arms. However, an interaction was detected between fenretinide treatment and menopausal status in both outcomes (P for interaction in both outcomes =.045), with a possible beneficial effect in premenopausal women (contralateral breast cancer: adjusted hazard ratio [HR] = 0.66, and 95% confidence interval [CI] = 0.41-1.07; ipsilateral breast cancer: adjusted HR = 0.65, and 95% CI = 0.46-0. 92) and an opposite effect in postmenopausal women (contralateral breast cancer: adjusted HR = 1.32, and 95% CI = 0.82-2.15; ipsilateral breast cancer: adjusted HR = 1.19, and 95% CI = 0.75-1. 89). There were no statistically significant differences between the two arms in tumors in other organs, incidence of distant metastasis, and all-cause mortality.

CONCLUSIONS

Fenretinide treatment of women with breast cancer for 5 years appears to have no statistically significant effect on the incidence of second breast malignancies overall, although a possible benefit was detected in premenopausal women. These studies, particularly the post hoc analyses, are considered exploratory and need to be confirmed.

Detection of metastases in sentinel lymph nodes of breast cancer patients by multiple-marker RT-PCR

This study was undertaken to assess a multiple-marker RT-PCR and Southern blot assay for detection of metastases in frozen sections of sentinel lymph nodes from breast cancer patients. Sentinel lymphadenectomy was performed in 41 AJCC (American Joint Committee on Cancer) stage I-IIIA breast cancer patients and 57 sentinel nodes (SNs) were excised. The SN, which is the first node in the lymphatic basin to receive metastases from the primary tumor, was identified using isosulfan blue dye. Hematoxylin and eosin (H&E), immuno-histochemistry (IHC) and RT-PCR were performed on adjacent sections of the SN. Six consecutive 12-microm frozen sections of each SN were obtained for the RT-PCR assay to determine expression of mRNA tumor markers C-Met, beta1 --> 4GalNAc-T and P97. Metastatic breast cancer was detected by H&E in 10 of 57 (18%) SNs and by IHC in an additional 7 (12%). Only 1 of 17 (6%) SNs with metastases did not express any of the 3 tumor mRNA markers. C-Met, beta1 --> 4GalNAc-T and P97 tumor mRNA markers were expressed in 31 (78%), 21 (53%) and 25 (63%) of 40 SNs without metastases, respectively. At least 2 mRNA tumor markers were expressed in 25/40 (63%) histo-pathologically tumor-free SNs, whereas all 3 mRNA tumor markers were expressed in 17/40 (43%) SNs. Expression of all 3 mRNA tumor markers in a SN was significantly higher in patients with a family history of breast cancer (p = 0.05), prior history of breast cancer (p < 0.05), infiltrating lobular carcinoma (p = 0.06), estrogen receptor-negative (p = 0.04) tumor or a higher Bloom Richardson score (p = 0.04). The multiple-marker RT-PCR and Southern blot assay improves the detection of occult metastases in the SN when compared to conventional H&E and IHC analysis. Expression of all 3 tumor mRNA markers in the SN correlated with poor prognostic clinico-pathologic factors compared to expression of 0 to 2 markers.

Evolving perspectives in contralateral breast cancer

Despite extensive publications reviewing contralateral breast cancer (CBC), the role of screening and preventative measures for contralateral tumours is controversial and optimal clinical management remains undefined. This paper addresses the incidence, the predisposing factors, the prevention and the treatment of bilateral breast cancer based on a review of the literature. Risk factors for CBC include young age at primary breast cancer diagnosis, hereditary breast cancer (due to a germline mutation), familial breast cancer (one or more affected relatives), radiation exposure at a young age, lobular carcinoma in situ (LCIS), lobular invasive carcinoma and multicentricity. Retrospective studies suggest that contralateral mammographic surveillance results in the early detection of breast cancer, but no clear survival benefit has been demonstrated. Trials of adjuvant tamoxifen in breast cancer patients have shown a reduction in the incidence of CBC in both pre- and postmenopausal women. In addition, breast cancer patients treated with ovarian ablation and prednisone have significantly reduced CBC versus controls. In patients with primary breast cancer there is no evidence that contralateral breast biopsies or contralateral prophylactic mastectomy reduce mortality. Randomised, prospective trials to determine optimal surveillance, prevention and treatment strategies for the contralateral breast in breast cancer patients have not been conducted. Based on the published literature, contralateral breast surveillance in breast cancer patients reasonably includes breast self-examination, regular physical examinations and annual mammography. In women who have no evidence of distant metastasis at the time of CBC diagnosis, we recommend that the CBC be treated in the same manner as a first breast cancer, taking into account prior local and systemic therapy.