Kernel-based naive bayes classifier for breast cancer prediction

The classification of breast cancer patients is of great importance in cancer diagnosis. Most classical cancer classification methods are clinical-based and have limited diagnostic ability. The recent advances in machine learning technique has made a great impact in cancer diagnosis. In this research, we develop a new algorithm: Kernel-Based Naive Bayes (KBNB) to classify breast cancer tumor based on memography data. The performance of the proposed algorithm is compared with that of classical navie bayes algorithm and kernel-based decision tree algorithm C4.5. The proposed algorithm is found to outperform in the both cases. We recommend the proposed algorithm could be used as a tool to classify the breast patient for early cancer diagnosis.

Breast cancer : the embodied transfer of uncertainty and risk

The thesis highlights how women reconstruct themselves after mammography, following a positive diagnosis of cancer, and post mastectomy. It juxtaposes women's experiences of breast cancer with doctors' perceptions of their role in treating patients, allowing an understanding of how risk and uncertainty are transferred between the private and public spheres.

The need to examine metastatic tissue at the time of progression of breast cancer : is re-biopsy a necessity or a luxury?

Knowledge of estrogen receptor (ER), progesterone receptor (PgR) and human epidermal growth factor receptor-2 (HER2) status is necessary for determining the optimal treatment of breast cancer patients. At the same time, the discordance between marker profiles (ER/PR and HER2) of primary and metastatic breast cancer is well documented. Whether discordant cases are secondary to “clonal selection” in the face of targeted anti-estrogen or anti-HER2 therapy or whether they are a laboratory artifact is still debated; both scenarios are likely. This article outlines current modalities for ER, PR, and HER2 testing in primary breast carcinoma and its metastases and reviews prospective and retrospective studies that have addressed these issues, as well as recent advances in the field.

Is chemotherapy dose intensity adequate in breast cancer management in the Australian healthcare setting: a retrospective analysis

Aim
To determine the adequacy of chemotherapy received dose intensity (RDI) in breast cancer treatment in a general population and to identify factors that influence RDI.

Methods
A retrospective analysis of breast cancer patients who commenced a course of i.v. chemotherapy in 2008 was undertaken. Data were collected on patient and tumor characteristics, chemotherapy regimen, dose (including delays, reductions and the reasons for these), granulocyte colony-stimulating factor (G-CSF) use and febrile neutropenia incidence. RDI was calculated using the planned and actual dose received and time taken. A level of ≥85% RDI was considered acceptable for treatment given with curative intent.

Results
In all, 131 patients (aged 28 to 77 years) received chemotherapy in adjuvant (n = 76, 58%), neoadjuvant (n = 11, 8%) and metastatic settings (n = 44, 34%). RDI did not reach 85% for 12% adjuvant, 36% neoadjuvant and 34% metastatic cases (χ2 = 10.55, P = 0.005). Overall, 43% of patients received G-CSF.

Conclusion
Acceptable chemotherapy RDI was delivered for most patients in the adjuvant setting but not in the neoadjuvant setting. G-CSF treatment contributed to the optimization of dose intensity in the adjuvant setting only. Dose intensity in the metastatic setting was considered satisfactory where quality of life is the primary focus. Other factors can be modified to improve RDI.

Breast cancer prognosis risk estimation using integrated gene expression and clinical data

Novel prognostic markers are needed so newly diagnosed breast cancer patients do not undergo any unnecessary therapy. Various microarray gene expression datasets based studies have generated gene signatures to predict the prognosis outcomes, while ignoring the large amount of information contained in established clinical markers. Nevertheless, small sample sizes in individual microarray datasets remain a bottleneck in generating robust gene signatures that show limited predictive power. The aim of this study is to achieve high classification accuracy for the good prognosis group and then achieve high classification accuracy for the poor prognosis group.

IPA: Integrated predictive gene signature from gene expression based breast cancer patient samples

Background: Novel predictive markers are needed to accurately diagnose the breast cancer patients so they do not need to undergo any unnecessary aggressive therapies. Various gene expression studies based predictive gene signatureshave generated in the recent past to predict the binary estrogen-receptor subclass or to predict the therapy response subclass. However, the existing algorithms comes with many limitations, including low predictive performances over multiple cohorts of patients and non-significant or limited biological roles associated with thepredictive gene signatures. Therefore, the aim of this study is to develop novel predictive markers with improved performances.Methods: We propose a novel prediction algorithm called IPA to construct a predictive gene signature for performing multiple prediction tasks of predicting estrogen-receptor based binary subclass and predicting chemotherapy response (neoadjuvantly) based binary subclass. The constructed gene signature with considering multiple classification techniques was used to evaluate the algorithm performance on multiple cohorts of breast cancer patients.Results: The evaluation on multiple validation cohorts demonstrated that proposed algorithm achieved stable and high performance to perform prediction tasks, with consideration given to any classification techniques. We show that the predictive gene signature of our proposed algorithm reflects the mechanisms underlying the estrogen-receptors or response to therapy with significant greater biological interpretations, compared with the other existing algorithm.

Tumour but not stromal expression of β3 integrin is essential, and is required early, for spontaneous dissemination of bone-metastatic breast cancer.

Although many preclinical studies have implicated β3 integrin receptors (αvβ3 and αIIbβ3) in cancer progression, β3 inhibitors have shown only modest efficacy in patients with advanced solid tumours. The limited efficacy of β3 inhibitors in patients could arise from our incomplete understanding of the precise function of β3 integrin and, consequently, inappropriate clinical application. Data from animal studies are conflicting and indicate heterogeneity with respect to the relative contributions of β3-expressing tumour and stromal cell populations in different cancers. Here we aimed to clarify the function and relative contributions to metastasis of tumour versus stromal β3 integrin in clinically relevant models of spontaneous breast cancer metastasis, with particular emphasis on bone metastasis. We show that stable down-regulation of tumour β3 integrin dramatically impairs spontaneous (but not experimental) metastasis to bone and lung without affecting primary tumour growth in the mammary gland. Unexpectedly, and in contrast to subcutaneous tumours, orthotopic tumour vascularity, growth and spontaneous metastasis were not altered in mice null for β3 integrin. Tumour β3 integrin promoted migration, protease expression and trans-endothelial migration in vitro and increased vascular dissemination in vivo, but was not necessary for bone colonization in experimental metastasis assays. We conclude that tumour, rather than stromal, β3 expression is essential and is required early for efficient spontaneous breast cancer metastasis to bone and soft tissues. Accordingly, differential gene expression analysis in cohorts of breast cancer patients showed a strong association between high β3 expression, early metastasis and shorter disease-free survival in patients with oestrogen receptor-negative tumours. We propose that β3 inhibitors may be more efficacious if used in a neoadjuvant setting, rather than after metastases are established. Copyright © 2014 Pathological Society of Great Britain and Ireland. Published by John Wiley & Sons, Ltd.

Inhibition of HDAC3- and HDAC6-promoted survivin expression plays an important role in SAHA-induced autophagy and viability reduction in breast cancer cells

SAHA is a class I HDAC/HDAC6 co-inhibitor and an autophagy inducer currently undergoing clinical investigations in breast cancer patients. However, the molecular mechanism of action of SAHA in breast cancer cells remains unclear. In this study, we found that SAHA is equally effective in targeting cells of different breast cancer subtypes and tamoxifen sensitivity. Importantly, we found that down-regulation of survivin plays an important role in SAHA-induced autophagy and cell viability reduction in human breast cancer cells. SAHA decreased survivin and XIAP gene transcription, induced survivin protein acetylation and early nuclear translocation in MCF7 and MDA-MB-231 breast cancer cells. It also reduced survivin and XIAP protein stability in part through modulating the expression and activation of the 26S proteasome and heat-shock protein 90. Interestingly, targeting HDAC3 and HDAC6, but not other HDAC isoforms, by siRNA/pharmacological inhibitors mimicked the effects of SAHA in modulating the acetylation, expression, and nuclear translocation of survivin and induced autophagy in MCF7 and MDA-MB-231 cancer cells. Targeting HDAC3 also mimicked the effect of SAHA in up-regulating the expression and activity of proteasome, which might lead to the reduced protein stability of survivin in breast cancer cells. In conclusion, this study provides new insights into SAHA's molecular mechanism of actions in breast cancer cells. Our findings emphasize the complexity of the regulatory roles in different HDAC isoforms and potentially assist in predicting the mechanism of novel HDAC inhibitors in targeted or combinational therapies in the future.

Characteristics of patients with haematological and breast cancer (1996-2009) who died of heart failure-related causes after cancer therapy

Aims To describe the characteristics and time to death of patients with breast or haematological cancer who died of heart failure (HF) after cancer therapy. Patients with an index admission for HF who died of HF-related causes (IAHF) and those with no index admission for HF who died of HF-related causes (NIAHF) were compared.

Methods and results We performed a linked data analysis of cancer registry, death registry, and hospital administration records (n = 15 987). Index HF admission must have occurred after cancer diagnosis. Of the 4894 patients who were deceased (30.6% of cohort), 734 died of HF-related causes (50.1% female) of which 279 (38.0%) had at least one IAHF (41.9% female) post-cancer diagnosis. Median age was 71 years [interquartile range (IQR) 62–78] for IAHF and 66 years (IQR 56–74) for NIAHF. There were fewer chemotherapy separations for IAHF patients (median = 4, IQR 2–9) compared with NIAHF patients (median = 6, IQR 2–12). Of the IAHF patients, 71% had died within 1 year of the index HF admission. There was no significant difference in HF-related mortality in IAHF patients compared with NIAHF (HR, 1.10, 95% CI, 0.94–1.29, P = 0.225).

Conclusions The profile of IAHF patients who died of HF-related causes after cancer treatment matched the current profile of HF in the general population (over half were aged ≥70 years). However, NIAHF were younger (62% were aged ≤69 years), female patients with breast cancer that died of HF-related causes before hospital admission for HF-related causes—a group that may have been undiagnosed or undertreated until death.

Evaluation of advanced breast cancer multidisciplinary team meatings

Background: Multidisciplinary team meetings (MDMs) have become an important decision-making forum in oncology. These meetings bring together expertise from each relevant field to improve continuity of care and health care outcomes for cancer patients. However there is a lack of evidence demonstrating the effectiveness of MDT meetings in improving cancer patient outcomes. The aim of this study was to explore the perceived value and potential usefulness of multidisciplinary team meetings for patients with advanced breast cancer (ABC).

Methods: ABC MDMs have been conducted since 2002 at two sites of Eastern Health, the second largest health service in Melbourne. Attendees were invited to complete a confidential questionnaire in November 2007 that comprised seven areas aimed to assess their judgment of how well the MDMs have improved patient management, including medical recommendations, psychosocial care, palliative care, community care, and team development. Average scores were calculated for improvement of each area.

Results: A total of 16 (69%) health practitioners participated in the survey, with main representation from nursing (37%), allied health (25%) and medicine (19%). Preliminary results indicate that the broad areas members reported the meeting had improved patient outcomes were in palliative care and medical management. Specific areas of perceived improvement were medical outcomes for patients; early referral to palliative care services; confirmation of diagnosis; referral to supportive care; and appropriateness of palliative care referrals. Conversely, the area that had least improved was community care, as there was no input from GPs or community services other than palliative care. Attendance by GPs and radiologists were considered important for further improving medical outcomes for patients.

Conclusions: This study demonstrates the perceived value of the MDT approach in the care of ABC patients, particularly in improving patient outcomes. The next stage of this research is to conduct a survey of ABC patient satisfaction level.

Psychosocial factors and survival of young women with breast cancer: a population-based prospective cohort study

Purpose: Most women with early-stage breast cancer believe that psychosocial factors are an important influence over whether their cancer will recur. Studies of the issue have produced conflicting results.

Patients and Methods: A population-based sample of 708 Australian women diagnosed before age 60 years with nonmetastatic breast cancer was observed for a median of 8.2 years. Depression and anxiety, coping style, and social support were assessed at a median of 11 months after diagnosis. Hazard ratios for distant disease-free survival (DDFS) and overall survival (OS) associated with psychosocial factors were estimated separately using Cox proportional hazards survival models, with and without adjustment for known prognostic factors.

Results: Distant recurrence occurred in 209 (33%) of 638 assessable patients, and 170 (24%) of 708 patients died during the follow-up period. There were no statistically significant associations between any of the measured psychosocial factors and DDFS or OS from the adjusted analyses. From unadjusted analyses, associations between greater anxious preoccupation and poorer DDFS and OS were observed (P = .02). These associations were no longer evident after adjustment for established prognostic factors; greater anxious preoccupation was associated with younger age at diagnosis (P = .03), higher tumor grade (P = .02), and greater number of involved axillary nodes (P = .008).

Conclusion: The findings do not support the measured psychosocial factors being an important influence on breast cancer outcomes. Interventions for adverse psychosocial factors are warranted to improve quality of life but should not be expected to improve survival.

Does multidisciplinary care enhance the management of advanced breast cancer? : evaluation of advanced breast cancer multidisciplinary team meetings

Purpose: To assess the contribution of the advanced breast cancer (ABC) multidisciplinary team meetings (MDMs) to patient care and clinical outcomes.

Methods: Members of ABC MDMs at two health services completed questionnaires in November 2007. The questionnaire asked about the performance of the MDMs and their contribution to improvement in patient care in five domains: medical management, psychosocial care, palliative care, care in the community, and benefits for team members. A final section covered the perceived value and importance of the MDM in patient management. Descriptive statistics (frequencies, mean, and standard deviation) were used to summarize the performance, improvement, and importance scores.

Results: A total of 27 multidisciplinary team members (73%) completed the questionnaire. The MDM performed best in medical management (mean performance score out of 5 [M] = 3.78) and palliative care (M = 3.77). These were also the areas that were most improved through the MDM. Benefits to team members and care in the community (both M = 3.05) ranked lowest by both measures. The MDM provided the most benefit for patient management in the areas of "awareness of services available" (M = 4.32), "efficiency of referrals" (M = 4.27) and "supportive care for patients" (M=4.27). "Awareness of services available," "psychological care for patients," and "continuity of care" were considered the most important (M = 4.64).

Conclusion: The study provides evidence that MDMs make an important contribution to the logistical and medical management of patients with advanced breast cancer.

Intracranial hemorrhage (ICH) in cancer patients treated with bevacizumab : the Memorial Sloan-Kettering experience

Background: Bevacizumab is a monoclonal antibody targeting vascular endothelial growth factor approved for recurrent glioblastoma (GBM), metastatic breast, colorectal and non-small-cell lung cancers (NSCLC). There has been a potentially increased risk of intracranial hemorrhage (ICH) in patients receiving bevacizumab.

Methods: We retrospectively identified patients with ICH who received bevacizumab between 1 January 2001 and 10 January 2009.

Results: We identified 1024 patients with ICH, 4191 patients who received bevacizumab and 12 (0.3%) who met both our criteria. There were eight women and four men with a median age of 66 years. Primary cancers were ovarian (n = 3), NSCLC (n = 3), colon (n = 1), angiosarcoma (n = 1) and GBM (n = 4). Intracranial tumors were present in 9 of the 12 patients; the remaining three (25%) had no evidence of intracranial pathology. Two hundred and fifty-seven patients with these same primary pathologies and brain tumors were treated with bevacizumab; ICH was seen in nine (3.7%), which was comparable to the 3.6% frequency seen in comparable patients not receiving bevacizumab.

Conclusions: ICH with bevacizumab treatment in this population is rare and does not appear to increase its frequency over the baseline rate of ICH in a comparable population. Most bevacizumab-related ICH occurs into central nervous system tumors but spontaneous hemorrhages were seen.

Immune thrombocytopenic purpura (ITP) and breast cancer. Does adjuvant therapy for breast cancer improve platelet counts in ITP?

Although both breast cancer and immune thrombocytopenic purpura (ITP) are common conditions, the simultaneous coexistence of these two diseases is rare. ITP is an autoimmune disease in which the presence of autoantibodies against platelets results in splenic sequestration and thrombocytopenia that may be associated with lymphoid neoplasms [1]. Except for an observational case series of 10 patients [2], only a few individual case reports of ITP coinciding with breast cancer have been reported [3–8]. We are reporting two cases with simultaneous confirmed ITP and breast cancer. The platelet counts in both women have improved during adjuvant breast cancer chemotherapy.