scholarly journals Survival Outcome Prediction for Breast Cancer Patients

2020 ◽  
Vol 9 (1) ◽  
pp. 1589-1592
Keyword(s):  
Breast Cancer ◽  
Random Forest ◽  
Death Rate ◽  
Outcome Prediction ◽  
Malignant Tumors ◽  
Survival Outcome ◽  
Breast Cancer Patients ◽  
Malignant Growth ◽  
Machine Learning Classification ◽  
Past Data

The second most causative disease is breast cancer happening in women and a significant explanation behind expanding death rate among women. Observed rates of this cancer are increasing with industrialization and also with early detection facilities. As the finding of this ailment physically takes extended periods and the lesser accessibility of frameworks, there is a need to build up the programmed determination framework for early identification of malignant growth. We have used machine learning classification techniques to categorize benign and malignant tumors, in which the machine learns from past data and predicts the new input category. Models like logistic regression and Random Forest are Done on the UCI dataset. Our experiments have indicated that Random Forest has the best prescient examination with exactness of ~96%.

scholarly journals Ten-year survival outcome of breast cancer patients in India

2021 ◽  
Vol 20 (1) ◽  
pp. 1
Author(s):  
DK Vijaykumar ◽  
Patel Viral ◽  
K Pavithran ◽  
K Beena ◽  
Ajil Shaji
Keyword(s):  
Breast Cancer ◽  
Cancer Patients ◽  
Survival Outcome ◽  
Breast Cancer Patients

scholarly journals Classifications of Breast Cancer Diagnosis using Machine Learning

2020 ◽  
Vol 14 ◽  
Keyword(s):  
Breast Cancer ◽  
Machine Learning ◽  
Random Forest ◽  
Breast Cancer Diagnosis ◽  
Performance Comparison ◽  
Support Vector ◽  
Breast Cancer Dataset ◽  
K Nearest Neighbors ◽  
Cancer Dataset ◽  
Machine Learning Classification

Breast Cancer (BC) is amongst the most common and leading causes of deaths in women throughout the world. Recently, classification and data analysis tools are being widely used in the medical field for diagnosis, prognosis and decision making to help lower down the risks of people dying or suffering from diseases. Advanced machine learning methods have proven to give hope for patients as this has helped the doctors in early detection of diseases like Breast Cancer that can be fatal, in support with providing accurate outcomes. However, the results highly depend on the techniques used for feature selection and classification which will produce a strong machine learning model. In this paper, a performance comparison is conducted using four classifiers which are Multilayer Perceptron (MLP), Support Vector Machine (SVM), K-Nearest Neighbors (KNN) and Random Forest on the Wisconsin Breast Cancer dataset to spot the most effective predictors. The main goal is to apply best machine learning classification methods to predict the Breast Cancer as benign or malignant using terms such as accuracy, f-measure, precision and recall. Experimental results show that Random forest is proven to achieve the highest accuracy of 99.26% on this dataset and features, while SVM and KNN show 97.78% and 97.04% accuracy respectively. MLP shows the least accuracy of 94.07%. All the experiments are conducted using RStudio as the data mining tool platform.

scholarly journals HER1R497K andHER2I655V Polymorphisms Are Linked to Development of Breast Cancer

2013 ◽  
Vol 34 (6) ◽  
pp. 407-417 ◽  
Author(s):  
Naglaa R. AbdRaboh ◽  
Hanan H. Shehata ◽  
Manal B. Ahmed ◽  
Fatehia A. Bayoumi
Keyword(s):  
Breast Cancer ◽  
Malignant Tumors ◽  
Immunohistochemical Analysis ◽  
Control Group ◽  
Breast Cancer Patients ◽  
Tissue Samples ◽  
Her2 Protein ◽  
Restriction Fragment Polymorphism ◽  
Epidermal Growth ◽  
Control Study

BACKGROUND: Polymorphism of the genes of Human Epidermal growth factor receptor1 (HER1) and receptor2 (HER2) have been reported to be linked to pathogenesis of several malignant tumors but still there is contradiction regarding their association with breast cancer.OBJECTIVE: In this case control study we aimed to analyze the frequency ofHER1R497K (rs 11543848) andHER2I655V (rs 1136201) Polymorphisms in breast cancer.SUBJECT AND METHOD: The frequency ofHER1Arg(R) 497Lys (K) andHER2Ile (I) 655Val (V) polymorphisms were tested in 64 breast cancer patients and 86 normal control by polymerase chain reaction followed by restriction fragment polymorphism detection. Immunohistochemical analysis was done for HER2 protein on the available 18 malignant tissue samples.RESULTS:HER1497K andHER2655V variant had significantly increased breast cancer risk (OR=2.6, 95% CI 1.6–4.2, OR=2.2, 95% CI 1.2–4.1, p< 0.05) respectively. Moreover, combinedHER1K497 andHER2V655 variant was detected in 26.6% malignant in comparison to 8.14% of control group (OR=4.1, 95% CI 1.58–10.57), but, no significant association was noticed between both Polymorphisms and clinicopathological features of the disease. As regard HER2 immunohistochemical expression no significant correlation was revealed with HER2 655V polymorphism.CONCLUSIONS: Our findings suggest thatHER1497K andHER2655V polymorphisms are potential risk factor for development of breast cancer.

scholarly journals Application and Effect of the Gymnastic Exercise Mode during Chemotherapy for Breast Cancer Patients

2020 ◽  
Vol 2020 ◽  
pp. 1-9
Author(s):  
Feifei Xie
Keyword(s):  
Breast Cancer ◽  
Cancer Patients ◽  
Incidence Rate ◽  
Evaluation System ◽  
Malignant Tumors ◽  
Treatment Plan ◽  
Breast Cancer Surgery ◽  
Breast Cancer Patients ◽  
Rehabilitation Training ◽  
Cancer Related Fatigue

Breast cancer is one of the most common malignant tumors in women, which seriously threatens the health of women. With the improvement of living standards, the incidence rate of breast cancer is also rising. In the past ten years, the incidence rate of breast cancer in China’s major cities has increased by 37%, far higher than that in Europe and America. At present, chemotherapy and radiotherapy are the main treatment methods for breast cancer, but many patients will have cancer-related fatigue after surgery. Some studies believe that appropriate sports can improve cancer-related fatigue, but there is no specific research in this area. In view of this problem, this paper puts forward a rehabilitation training method based on gymnastics for breast cancer surgery. This paper is divided into three parts. The first part is the basic theory and core concept of breast cancer and cancer-related fatigue. Through the in-depth study of the theory, this paper believes that breast cancer patients paying attention to rehabilitation training can effectively improve cancer-related fatigue and affect the final therapeutic effect. The second part is the rehabilitation training program based on the way of gymnastics. The corresponding experimental model is established by using real cases as samples. In order to ensure the quality of the experiment, this paper gives the treatment plan in detail and establishes a unified evaluation system. In the third part of this paper, the relevant experiments and results analysis are given, and through data analysis, this paper believes that gymnastics can effectively help breast cancer patients with postoperative rehabilitation and continuous recovery of the upper limb function and improve cancer-related fatigue and other issues.

scholarly journals Molecular Imaging in Breast Cancer: From Whole-Body PET/CT to Dedicated Breast PET

2012 ◽  
Vol 2012 ◽  
pp. 1-8 ◽  
Author(s):  
B. B. Koolen ◽  
W. V. Vogel ◽  
M. J. T. F. D. Vrancken Peeters ◽  
C. E. Loo ◽  
E. J. Th. Rutgers ◽  
...  
Keyword(s):  
Breast Cancer ◽  
Malignant Tumors ◽  
Volume Effect ◽  
Whole Body ◽  
Response Monitoring ◽  
Breast Cancer Patients ◽  
Dedicated Breast Pet ◽  
Positron Emission ◽  
Pet Ct ◽  
Elevated Glucose

Positron emission tomography (PET), with or without integrated computed tomography (CT), using 18F-fluorodeoxyglucose (FDG) is based on the principle of elevated glucose metabolism in malignant tumors, and its use in breast cancer patients is frequently being investigated. It has been shown useful for classification, staging, and response monitoring, both in primary and recurrent disease. However, because of the partial volume effect and limited resolution of most whole-body PET scanners, sensitivity for the visualization of small tumors is generally low. To improve the detection and quantification of primary breast tumors with FDG PET, several dedicated breast PET devices have been developed. In this nonsystematic review, we shortly summarize the value of whole-body PET/CT in breast cancer and provide an overview of currently available dedicated breast PETs.

scholarly journals GENOME-WIDE ASSOCIATION STUDY OF LOSS OF HETEROZYGOSITY AND METASTASIS-FREE SURVIVAL IN BREAST CANCER PATIENTS

2017 ◽  
Vol 39 (2) ◽  
pp. 145-150 ◽  
Author(s):  
I V Deryusheva ◽  
M M Tsygano ◽  
E Y Garbukov ◽  
M K Ibragimova ◽  
Ju G Kzhyshkovska ◽  
...  
Keyword(s):  
Breast Cancer ◽  
Cancer Patients ◽  
Loss Of Heterozygosity ◽  
Genome Wide Association Study ◽  
Malignant Tumors ◽  
Chromosome Analysis ◽  
Rank Test ◽  
Breast Cancer Patients ◽  
Free Survival ◽  
Genome Wide

One of the factors providing the diversity and heterogeneity of malignant tumors, particularly breast cancer, are genetic variations, due to gene polymorphism, and, especially, the phenomenon of loss of heterozygosity (LOH). It has been shown that LOH in some genes could be a good prognostic marker. Aim: To perform genome-wide study on LOH in association with metastasisfree survival in breast cancer. Materials and Methods: The study involved 68 patients with breast cancer. LOH status was detected by microarray analysis, using a high density DNA-chip CytoScanTM HD Array (Affymetrix, USA). The Chromosome Analysis Suite 3.1 (Affymetrix, USA) software was used for result processing. Results: 13,815 genes were examined, in order to detect LOH. The frequency of LOH varied from 0% to 63%. The association analysis identified four genes: EDA2R, PGK1, TAF9B and CYSLTR1 that demonstrated the presence of LOH associated with metastasis-free survival (log-rank test, p < 0.03). Conclusions: The presence of LOH in EDA2R, TAF9B, and CYSLTR1 genes is associated with metastasis-free survival in breast cancer patients, indicating their potential value as prognostic markers.

scholarly journals Machine Learning Models That Integrate Tumor Texture and Perfusion Characteristics Using Low-Dose Breast Computed Tomography Are Promising for Predicting Histological Biomarkers and Treatment Failure in Breast Cancer Patients

Cancers ◽  
2021 ◽  
Vol 13 (23) ◽  
pp. 6013
Author(s):  
Hyun-Soo Park ◽  
Kwang-sig Lee ◽  
Bo-Kyoung Seo ◽  
Eun-Sil Kim ◽  
Kyu-Ran Cho ◽  
...  
Keyword(s):  
Breast Cancer ◽  
Machine Learning ◽  
Random Forest ◽  
Cancer Patients ◽  
Low Dose ◽  
Random Forest Model ◽  
Breast Cancer Patients ◽  
Learning Models ◽  
Forest Model ◽  
Machine Learning Models

This prospective study enrolled 147 women with invasive breast cancer who underwent low-dose breast CT (80 kVp, 25 mAs, 1.01–1.38 mSv) before treatment. From each tumor, we extracted eight perfusion parameters using the maximum slope algorithm and 36 texture parameters using the filtered histogram technique. Relationships between CT parameters and histological factors were analyzed using five machine learning algorithms. Performance was compared using the area under the receiver-operating characteristic curve (AUC) with the DeLong test. The AUCs of the machine learning models increased when using both features instead of the perfusion or texture features alone. The random forest model that integrated texture and perfusion features was the best model for prediction (AUC = 0.76). In the integrated random forest model, the AUCs for predicting human epidermal growth factor receptor 2 positivity, estrogen receptor positivity, progesterone receptor positivity, ki67 positivity, high tumor grade, and molecular subtype were 0.86, 0.76, 0.69, 0.65, 0.75, and 0.79, respectively. Entropy of pre- and postcontrast images and perfusion, time to peak, and peak enhancement intensity of hot spots are the five most important CT parameters for prediction. In conclusion, machine learning using texture and perfusion characteristics of breast cancer with low-dose CT has potential value for predicting prognostic factors and risk stratification in breast cancer patients.

Sign in / Sign up

Export Citation Format

Share Document