Bayesian Pathway Analysis for Complex Interactions

Simple SummaryAn early prediction of Breast Cancer Recurrence (BCR) for patients undergoing neoadjuvant chemotherapy (NACT) could better guide clinicians in the identification of the most suitable combination treatments for individual patient scenarios. We proposed a transfer learning approach to give an early prediction of three-year BCR for patients undergoing NACT, using DCE-MRI exams from I-SPY1 TRIAL and BREAST-MRI-NACT-Pilot public databases. Because no technical expertise is required in the extraction of meaningful features from images, the predictive model qualifies as a user-friendly tool for any medical expert in support of therapeutic choices. Only pre-treatment and early-treatment MRI examinations were analyzed to allow for potential therapy changes at a very early stage of treatment. We tested the strength of the model on an independent test. The best predictive performances (accuracy of 85.2%, sensitivity of 84.6%, and AUC of 0.83) were achieved by combining the extracted features with some clinical factors: age, ER, PgR, HER2+.Cancer treatment planning benefits from an accurate early prediction of the treatment efficacy. The goal of this study is to give an early prediction of three-year Breast Cancer Recurrence (BCR) for patients who underwent neoadjuvant chemotherapy. We addressed the task from a new perspective based on transfer learning applied to pre-treatment and early-treatment DCE-MRI scans. Firstly, low-level features were automatically extracted from MR images using a pre-trained Convolutional Neural Network (CNN) architecture without human intervention. Subsequently, the prediction model was built with an optimal subset of CNN features and evaluated on two sets of patients from I-SPY1 TRIAL and BREAST-MRI-NACT-Pilot public databases: a fine-tuning dataset (70 not recurrent and 26 recurrent cases), which was primarily used to find the optimal subset of CNN features, and an independent test (45 not recurrent and 17 recurrent cases), whose patients had not been involved in the feature selection process. The best results were achieved when the optimal CNN features were augmented by four clinical variables (age, ER, PgR, HER2+), reaching an accuracy of 91.7% and 85.2%, a sensitivity of 80.8% and 84.6%, a specificity of 95.7% and 85.4%, and an AUC value of 0.93 and 0.83 on the fine-tuning dataset and the independent test, respectively. Finally, the CNN features extracted from pre-treatment and early-treatment exams were revealed to be strong predictors of BCR.

52 Background: Modified Bloom-Richardson (MBR) grade is a pathologic grading system for breast cancer that has been shown to have prognostic significance in patients with node-negative disease. Oncotype DX Score is a 21-gene expression analysis that has been clinically validated as a reliable predictor of recurrence risk for node-negative estrogen receptor-positive breast cancer. A score of less than 18 signifies a low risk of recurrence, a score of 18 to 31 signifies an intermediate risk and a score greater than 31 signifies a high risk. Several reports have questioned the concordance between the Oncotype score and MBR grade. The objective of this study is to evaluate the concordance between Oncotype score and MBR grade, thereby ascertaining if MBR is a reliable predictor of breast cancer recurrence. Methods: An IRB-exempted restrospective chart review of female patients at Wellspan Group who had Oncotype DX analysis in 2008 and 2009 was carried out. Data collected included Oncotype DX score, MBR grade, BMI and menopausal status. Data were analyzed to determine the association between Oncotype DX score and MBR grade. Results: A total of 125 patients were identified. Of these, 107 had MBR grades available. The remaining patients did not have MBR grade as it was not applicable to their breast cancer type. The mean Oncotype scores were 15.11 (95% CI 13.33-16.89) for patients with MBR grade 1 carcinoma, 20.31 (95% CI 17.90-22.72) for MBR grade 2 carcinoma, and 39.93 (95% CI 30.05-49.80) for MBR grade 3 carcinoma. The mean Oncotype score differences were 5.201 (P = .007, 95% CI 1.46-8.94) between MBR grades 1 and 2, and 19.616 (P < 0.001, 95% CI 14.14-25.09) for MBR grades 2 and 3. The ranges of Oncotype scores for MBR grade 1, grade 2 and grade 3 were 3 to 36, 9 to 56 and 20 to 70 respectively. Conclusions: MBR grade may predict breast cancer recurrence risk reliably as there is acceptable concordance between MBR grade and Oncotype Dx recurrence risk.

Many new prognostic factors for breast cancer have been described, and yet the ability to predict patient outcomes remains poor. Overexpression of p-glycoprotein (p-gp), the multidrug resistance efflux pump, confers a worse prognosis to patients with certain leukemias and other tumors. The purpose of this study was to analyze the potential usefulness of p-gp expression as a prognostic factor in patients with breast cancer. Paraffin blocks were obtained from 55 previously untreated patients who underwent surgery between 1987 and 1988. To determine p-gp expression, tumor cell suspensions were incubated with the p-gp-specific C219 monoclonal antibody and analyzed using an indirect immunofluorescent flow cytometric assay. Twenty-four (44%) of the tumors were p-gp positive and 31 (56%) were p-gp negative. Among the p-gp positive patients, 65% had recurrence of their disease, whereas only 13% of the p-gp negative patients experienced recurrence (p = 0.0001). The 5-year disease-free rate for p-gp positive patients was 39% compared with 83% for p-gp negative patients (p = 0.0001). In univariate analysis examining 10 different variables, significant predictors of recurrence were p-gp, stage, and tumor size. Multivariate analysis using Cox Proportional Hazards regression showed that only p-gp and stage were significant independent predictors of recurrence (p = 0.0002). p-gp is frequently expressed in patients with untreated breast cancer, with p-gp-positive patients being at significantly greater risk for disease recurrence. p-gp appears to be a useful prognostic factor in breast cancer and could potentially help guide management.

In recent years, due to an increase in the incidence of different cancers, various data sources are available in this field. Consequently, many researchers have become interested in the discovery of useful knowledge from available data to assist faster decision-making by doctors and reduce the negative consequences of such diseases. Data mining includes a set of useful techniques in the discovery of knowledge from the data: detecting hidden patterns and finding unknown relations. However, these techniques face several challenges with real-world data. Particularly, dealing with inconsistencies, errors, noise, and missing values requires appropriate preprocessing and data preparation procedures. In this article, we investigate the impact of preprocessing to provide high-quality data for classification techniques. A wide range of preprocessing and data preparation methods are studied, and a set of preprocessing steps was leveraged to obtain appropriate classification results. The preprocessing is done on a real-world breast cancer dataset of the Reza Radiation Oncology Center in Mashhad with various features and a great percentage of null values, and the results are reported in this article. To evaluate the impact of the preprocessing steps on the results of classification algorithms, this case study was divided into the following 3 experiments:Breast cancer recurrence prediction without data preprocessingBreast cancer recurrence prediction by error removalBreast cancer recurrence prediction by error removal and filling null valuesThen, in each experiment, dimensionality reduction techniques are used to select a suitable subset of features for the problem at hand. Breast cancer recurrence prediction models are constructed using the 3 widely used classification algorithms, namely, naïve Bayes, k-nearest neighbor, and sequential minimal optimization. The evaluation of the experiments is done in terms of accuracy, sensitivity, F-measure, precision, and G-mean measures. Our results show that recurrence prediction is significantly improved after data preprocessing, especially in terms of sensitivity, F-measure, precision, and G-mean measures.

178 Background: There has been conflicting evidence in the literature regarding the association between age and breast cancer recurrence risk. Cancer Research UK reported a better survival among patients aged 50 to 69 compared to younger women. The National Cancer Institute had reported the same, but only in women with stage 1 cancer. Fox Chase Cancer Center and Lyman et al had however suggested that there is no association between breast cancer recurrence and age at diagnosis. Our objective is to investigate the association between breast cancer recurrence and age at diagnosis. Methods: An IRB-exempted restrospective chart review of female patients at Wellspan Group who had Oncotype DX analysis in 2008 and 2009. Data collected included Oncotype DX score and age at diagnosis. Data was analyzed to determine the correlation between Oncotype DX score and age at diagnosis. The patients were divided into three groups: age less than 45 years, age 45 to 59 years, and age 60 or more. Oncotype DX score was used because it has been clinically validated as a reliable predictor of breast cancer recurrence for node-negative breast cancer. Results: A total of 125 patients were identified. The Pearson Correlation score for Oncotype DX score and age at diagnosis was -0.064 (p = 0.478). The mean score was 18.36 for those aged less than 45 years, 22.04 for those aged 45 to 59 years, and 19.16 for those age 60 or more. The difference between these groups was not significant (p = 0.340). Conclusions: There was neither significant correlation between breast recurrence and age, nor difference between the three age groups. Our study shows that age at diagnosis is not an independent predictor of breast cancer recurrence risk.

Abstract #3032 The p160 coactivators AIB1 and SRC-1 are known to play a critical role in modulating transcription in breast cancer cells in conjunction with ligand-bound estrogen receptor. The interactions of the p160 proteins with this nuclear receptor are also important in the development of resistance to endocrine treatments. Using quantitative coassociation immunofluorescent microscopy, the colocalisation of the p160s and ERα was increased in the LY2 endocrine resistant cell line following treatment with the anti-estrogen tamoxifen in comparison to the endocrine sensitive MCF-7 cell line. In cell cultures derived from patient tumours at the time of primary surgery prior to treatment, there was an increase in association of the coactivators with ERα following treatment with estrogen but dissociation was evident in the presence of tamoxifen. Immunohistochemical staining of a tissue microarray, constructed from 560 breast cancer patients, revealed that SRC-1 was a strong predictor of reduced disease-free survival, both in patients receiving adjuvant tamoxifen treatment and untreated patients (p<0.0001 and p=0.0111 respectively). AIB1 was not a significant independent predictor of disease recurrence. SRC-1 was assigned a hazard ratio of 2.12 when survival analysis using a Cox proportional hazards model was applied. Quantitative coassociation analysis of the p160 coactivators with ERα in the patient TMA revealed significantly stronger colocalisation of SRC-1 and ERα in patients who are known to have relapsed than those patients who did not recur (p=0.00001). This data suggests SRC-1 is pivotal in tumour aggressiveness and is a powerful predictor of progression of disease in breast cancer patients. Citation Information: Cancer Res 2009;69(2 Suppl):Abstract nr 3032.

Aim. To study the recurrence of stage I–II breast cancer after subcutaneous/skin-sparing mastectomies with reconstruction with or without radiation therapy. Materials and methods. From 2013 to 2022, 984 patients diagnosed with breast cancer underwent 1020 subcutaneous/skin-sparing mastectomies with reconstruction at the P.A. Herzen Moscow State Medical Institute. Histological types are presented: cancer in situ – 7, invasive cancer without signs of specificity – 818, invasive lobular cancer – 105, combined cancer – 40, rare forms – 50. Subcutaneous mastectomy with reconstruction was performed in 617 (60.5 %), skin-sparing mastectomy in 403 (39.5 %) cases. Reconstruction with own tissues was performed in 5.7 %, expanders/implants in 94.3 % of patients. Patients with diagnosed mutations in the genes ВRCА1, 2, СНЕК2 amounted to 208 (21.1 %), while among patients with primary multiple synchronous cancer, the percentage with mutations was 25 %. Results. In the studied group of patients, recurrence of breast cancer was diagnosed in 40 (4.1 ± 0.1 %) cases, distant metastases – in 52 (5.3 ± 0.1 %) cases. The minimum time to relapse was 36 months, and the maximum was 108 months. In a single-factor analysis of the stage of the disease: at stage I, relapse was diagnosed in 25 (5.8 %) cases, at stage IIA (T2N0M0) – in 5 (2.0 %), at stage IIA (T1N1M0) – in 6 (4.2 %), at stage IIB T2N1M0 – in 4 (2.1 %) (p > 0.05). The recurrence in the group with radiation therapy was 2.5 ± 0.6 (odd ratio 0.98, 95 % confidential interval 1.52–3.48), without radiation therapy 5.1 % (odd ratio 2.13, 95 % confidential interval 0.92–5.18) regardless of the stage of breast cancer (t-criterion >2, p > 0.05). In our study, the recurrence of breast cancer at the edge of R1 was 6.8 ± 2.5 %, at R0 – 3 ± 0.6 % (p > 0.05). When analyzing age and risk of recurrence, we did not identify age dependence, up to 40 years the probability of recurrence is 4.3 ± 1 %, after 40 years – 3.3 ± 0.7 % (t-criterion 0.44, p > 0.05). The dependence of the degree of malignancy of the tumor node and the frequency of recurrence is as follows: G1 – 2. 3 ± 2.3 %, G2 – 3 ± 0.7 %, G3 – 3.9 ± 1 %, when compared G3 c G1 (t-criterion 0.52, p>0.05), when comparing G3 from G2 (t-criterion 0.49, p > 0.05). Recurrence of breast cancer with triple negative type was diagnosed in 2.5 ± 0.9 % relative to other molecular biological types (t-criterion 1.49, p > 0.05). We analyzed the dependence of relapse on the non-luminal and luminal HER2 positive types; the relapse was 5.4 ± 1.5 % (p > 0.05); the dependence on the level of Ki-67; at a level of 40 %, the probability of recurrence is 4 ± 0.8 %, at a level > 40 %, recurrence is 2 ± 0.8 % (t-criterion 1.77, p > 0.05). A statistically significant difference in our study was revealed, in addition to radiation therapy, during neoadjuvant polychemotherapy, so in the group with neoadjuvant polychemotherapy, the recurrence was 2 ± 0.8 %, without neoadjuvant polychemotherapy – 4.1 ± 0.7 % (t-criterion 2.16, р < 0.05). Conclusion. A link between breast cancer recurrence and morphological features (R1 resection margin, lymphovascular invasion, lymphatic tumor emboli, luminal and non-luminal HER2+ subtype, G3) and clinical characteristics (presence of mutations, location of a lesion in the gland, stages) was found. Further search for predictors of breast cancer recurrence after combination or integrated treatment is necessary.

Breast cancer mortality is usually due to distant recurrence of cancer at an advanced stage of the disease rather than from primary cancer. Therefore, prediction of breast cancer recurrence at the time of diagnosis could lead to advances in personalized treatment of cancer patients in order to prevent risk of recurrence. Two prognostic biomarkers that are currently being used in clinical practice are a 70-gene MammaPrint signature and a 21-gene Oncotype DX panel. These assays generate relative risks of recurrence, but they do not provide a 'yes' or 'no' answer about recurrence in a given patient. These tests include genes that are involved in the cell cycle, invasion, metastasis and angiogenesis related to breast cancer. Emerging evidence suggests that a signature of genes involved in tumor-immune interactions may provide a more accurate prognostic tool. This paper reviews recent advances in the discovery of prognostic biomarkers for breast cancer patients.

Bayesian approaches have been demonstrated as effective methods for reliability analysis of complex systems with small-amount data, which integrate prior information and sample data using Bayes’ theorem. However, there is an assumption that precise prior probability distributions are available for unknown parameters, yet these prior distributions are sometimes unavailable in practical engineering. A possible way to avoiding this assumption is to generalize Bayesian reliability analysis approach by using imprecise probability theory. In this paper, we adopt a set of imprecise Dirichlet distributions as priors to quantify uncertainty of unknown parameters and extend traditional Bayesian reliability analysis approach by introducing an imprecise Dirichlet model (IDM). When the prior information is rare, the result of imprecise Bayesian analysis method is too rough to support engineering decision-making, so we proposed an optimization model to reduce the imprecision of the new method. Spindles are crucial for machine tools and reliability data related to spindles of new-developed machine tools are often rare. We can then use the imprecise Bayesian reliability analysis method to assess its reliability. In this paper, we mainly investigate the reliability assessment of a motorized spindle to illustrate the effectiveness of the proposed method.

To investigate the associations between contrast-enhanced ultrasound imaging features and disease recurrence among patients with locally advanced breast cancer treated with neoadjuvant chemotherapy.In the study, pre- and post-neoadjuvant chemotherapy contrast-enhanced ultrasound images of 43 patients with breast cancer were retrospectively analysed. Post-acquisition image processing involved the placement of freehand-drawn regions of interest, followed by the generation of blood flow kinetics representing blood volume and velocity for these regions of interest. Qualitative and quantitative contrast-enhanced ultrasound parameters were compared to predict recurrence, and receiver operating characteristic analysis was used to evaluate predictive ability.Among the 43 patients, 10 (23%) exhibited disease recurrence (median [range]: 27 [4-68] months). Post-neoadjuvant chemotherapy peak enhancement, wash-in area under the curve, wash-out area under the curve, and wash-in and wash-out area under the curve (p=0.003, p=0.004, p=0.026, and p=0.014, respectively) differed between the no-recurrence and recurrence groups. The area under the receiver operating characteristic curve (0.88; 95% confidence interval: 0.75-1.00) for post-neoadjuvant chemotherapy peak enhancement was the highest among the contrast-enhanced ultrasound parameters, with a cut-off of 13.33 arbitrary units.Higher peak enhancement on post-neoadjuvant chemotherapy contrast-enhanced ultrasound images was associated with recurrence in women with locally advanced breast cancer and is a potential biomarker of tumor recurrence.

Breast Cancer is the most common type of cancer prevalent among female cancer patients, while it is also the second most dreaded disease, causing cancer deaths among women. This study proposes new criteria for the prediction of survival of breast cancer patients, based on the analysis performed using four ensemble machine learning techniques, which include, AdaBoost M1, Bagging, Voting, and Stacking. For this study, we have used a breast cancer dataset consisting of 23 attributes and containing 575 samples obtained from Mizoram State Cancer Institute of Aizawl, Mizoram, India. We have employed ensemble machine learning classifiers to predict the recurrence of breast cancer within a period of three years evaluated based on the comparison of their performance. We have used 10 fold cross-validation technique and ROC curve to arrive at the results. From the dataset, attributes are ranked according to their contribution towards the prediction.

Breast Cancer is a major health problem and is one of the significant causes of death among women. Recurrence occurs when cancer returns after few years of treatment. To aid in the medical treatment and for clinical management, the early cancer diagnosis and prognosis have become the necessity in breast cancer recurrence. As the medical data is increasing with the advancement in medical technology, data mining facilitates to manage the data and provide useful medical progression and treatment of cancerous conditions. Various machine learning techniques can be used to support the doctors in effective and accurate decision making. In this paper, various classifiers have been tested for the prediction of type of breast cancer recurrence and the results show that neural networks outperform others. These findings will help the physicians in identifying the best features which can lead to breast recurrence.

Additional age-related issues should be considered when managing breast cancer in young women.1 Among them, the potential consequences of anticancer treatments on ovarian function and fertility potential are of particular concern and need to be addressed as early as possible after diagnosis.2,3 Therefore, current guidelines strongly voice the need to provide proper oncofertility counseling with all patients of reproductive age with newly diagnosed cancer irrespective of its stage.2,3 This is a crucial step to discuss with all young women their disease and prognosis, the required treatments including their potential gonadotoxicity, the need for contraception during and after active systemic therapies, their future desire of conception, likelihood of pregnancy, its safety and outcomes as well as the available strategies to avoid the negative impact of the proposed treatment on ovarian function and fertility.

540Background: Tumor grade is a predictor of breast cancer recurrence, independent of gene expression assays such as Oncotype Dx (ODx). However, grade suffers from significant intra- and inter-obse...

Women who have recovered from breast cancer (BC) always fear its recurrence. The fact that they have endured the painstaking treatment makes recurrence their greatest fear. However, with current advancements in technology, early recurrence prediction can help patients receive treatment earlier. The availability of extensive data and advanced methods make accurate and fast prediction possible. This research aims to compare the accuracy of a few existing data mining algorithms in predicting BC recurrence. It embeds a particle swarm optimization as feature selection into three renowned classifiers, namely, naive Bayes, K-nearest neighbor, and fast decision tree learner, with the objective of increasing the accuracy level of the prediction model.