scholarly journals Early Breast Cancer Prediction using Artificial Intelligence Methods

2020 ◽  
pp. 48-54
Author(s):  
Shawni Dutta ◽  
Samir Kumar Bandyopadhyay
Keyword(s):  
Breast Cancer ◽  
Health Care ◽  
Early Detection ◽  
Health Care Systems ◽  
Support Vector ◽  
Kappa Score ◽  
Cancer Disease ◽  
Care Systems ◽  
Detection And Diagnosis ◽  
Automated Tool

In India, the death toll due to breast cancer is increasing at a rapid pace. Only early detection and diagnosis is the way of control but it is a major challenge in India due to lack of awareness and lethargy of Indian womentowards health care and regular check-up. But the major obstacle in India is expensive health care system and unavailability of proper infrastructure, especially in breast cancer treatment. This paper aims in obtaining an automated tool that will exploit patient’s health records and predict the tendency of being affected in breast cancer. Gradient Boost classifier is used as an automated tool that predicts the chance of being affected in breast cancer disease. Early detection of this disease will assist health care systems to provide counter measures in order to save patients’ life. The proposed model is evaluated against other peer classifiers such as Support Vector Machine (SVM) and K-Nearest Neighbour (K-NN), Naïve bayes classifier, Adaboost classifier, Decision Tree (DT) classifier, and Random Forest (RF) Classifier. The proposed method achieves encouraging result with an accuracy of 97.34%, F1-Score of 0.97 Cohen-Kappa Score of 0.94 and MSE of 0.0266. The Gradient Boost algorithm attains the lowest error rate along with highest efficiency which might be the best choice of algorithm for this problem and prediction of disease.

scholarly journals AN IN-DEPTH ANALYSIS OF THE IDENTIFIED ALGORITHMS AND THEIR COMPARATIVE STUDY IN THE EARLY DETECTION AND DIAGNOSIS OF BREAST CANCER

2021 ◽  
Vol 12 (1) ◽  
Author(s):  
Mridul Sharma
Keyword(s):  
Breast Cancer ◽  
Artificial Intelligence ◽  
Early Detection ◽  
Healthcare Workers ◽  
State Of The Art ◽  
Machine Learning Algorithms ◽  
Support Vector ◽  
Depth Analysis ◽  
Detection And Diagnosis ◽  
Early Detection And Diagnosis

These days one of the major inevitable ailments for females is bosom malignancy. The appropriate medication and early findings are important stages to take to thwart this ailment. Although, it's not easy to recognize due to its few vulnerabilities and lack of data. Can use artificial intelligence to create devices that can help doctors and healthcare workers to early detection of this cancer. In This research, we investigate three specific machine learning algorithms widely used to detect bosom ailments in the breast region. These algorithms are Support vector machine (SVM), Bayesian Networks (BN) and Random Forest (RF). The output in this research is based on the State-of-the-art technique.

Use of imaging for staging of early breast cancer in two integrated health care systems.

2014 ◽  
Vol 32 (30_suppl) ◽  
pp. 184-184
Author(s):  
Erin Elizabeth Hahn ◽  
Tania Tang ◽  
Janet S. Lee ◽  
Corrine Munoz-Plaza ◽  
Joyce O Adesina ◽  
...  
Keyword(s):  
Breast Cancer ◽  
Health Care ◽  
Cancer Patients ◽  
Early Stage ◽  
Health Care Systems ◽  
Integrated Health Care ◽  
Low Risk ◽  
Breast Cancer Patients ◽  
Chart Abstraction ◽  
Care Systems

184 Background: The initial ASCO “Top 5” list, created as part of the Choosing Wisely campaign, recommends against use of imaging for staging of early stage breast cancer in asymptomatic women at low risk for metastasis. The objective of this study was to measure and compare use of imaging for staging in two large integrated health care systems, Kaiser Permanente (KP) and Intermountain Healthcare (IH). We also sought to distinguish whether imaging was used for routine staging or for diagnostic purposes. Methods: We identified stage 0-IIB breast cancer patients diagnosed between January 1, 2010 and December 31, 2012 with first primary malignancy from tumor registries in three KP regions (Southern California, Northwest, and Mid-Atlantic) and IH. Using the KP and IH electronic health records, we identified use of imaging tests (PET, CT, bone scan) during the staging window (30 days prior to diagnosis up to initial surgery). We performed chart abstraction on a random sample of patients who received an imaging test to identify indication. Results: For the total sample of 10,014, mean age at diagnosis was 60 (range 22-99); with 21% stage 0, 47% stage I, 32% stage II. Overall, 8% of patients (792 patients) received at least one imaging test during the staging window, including 8% at KP and 6% at IH (p=0.0005). Chart abstraction (N=129) revealed that overall, almost half of all imaging tests (48%) were performed to evaluate a symptom, sign or prior imaging finding, including 55% at KP and 32% at IH. Conclusions: Use of imaging for staging of low-risk breast cancer was very low in both health care systems, with clinically trivial differences between them. Approximately half of imaging services were in response to a sign or symptom. Strategies to reduce use of imaging at staging for early stage breast cancer patients within these health care systems are unlikely to yield meaningful improvement. [Table: see text]

scholarly journals Use of Gene Expression Profiling and Chemotherapy in Early-Stage Breast Cancer: A Study of Linked Electronic Medical Records, Cancer Registry Data, and Genomic Data Across Two Health Care Systems

2016 ◽  
Vol 12 (6) ◽  
pp. e697-e709 ◽  
Author(s):  
Anosheh Afghahi ◽  
Maya Mathur ◽  
Caroline A. Thompson ◽  
Aya Mitani ◽  
Joseph Rigdon ◽  
...  
Keyword(s):  
Breast Cancer ◽  
Health Care ◽  
Cancer Registry ◽  
Odds Ratio ◽  
Care Setting ◽  
Health Care Systems ◽  
Multivariable Analysis ◽  
Health Care Setting ◽  
Dual Use ◽  
Care Systems

Purpose: The 21-gene recurrence score (RS) identifies patients with breast cancer who derive little benefit from chemotherapy; it may reduce unwarranted variability in the use of chemotherapy. We tested whether the use of RS seems to guide chemotherapy receipt across different cancer care settings. Methods: We developed a retrospective cohort of patients with breast cancer by using electronic medical record data from Stanford University (hereafter University) and Palo Alto Medical Foundation (hereafter Community) linked with demographic and staging data from the California Cancer Registry and RS results from the testing laboratory (Genomic Health Inc., Redwood City, CA). Multivariable analysis was performed to identify predictors of RS and chemotherapy use. Results: In all, 10,125 patients with breast cancer were diagnosed in the University or Community systems from 2005 to 2011; 2,418 (23.9%) met RS guidelines criteria, of whom 15.6% received RS. RS was less often used for patients with involved lymph nodes, higher tumor grade, and age < 40 or ≥ 65 years. Among RS recipients, chemotherapy receipt was associated with a higher score (intermediate v low: odds ratio, 3.66; 95% CI, 1.94 to 6.91). A total of 293 patients (10.6%) received care in both health care systems (hereafter dual use); although receipt of RS was associated with dual use (v University: odds ratio, 1.73; 95% CI, 1.18 to 2.55), there was no difference in use of chemotherapy after RS by health care setting. Conclusion: Although there was greater use of RS for patients who sought care in more than one health care setting, use of chemotherapy followed RS guidance in University and Community health care systems. These results suggest that precision medicine may help optimize cancer treatment across health care settings.

scholarly journals Use of Imaging for Staging of Early-Stage Breast Cancer in Two Integrated Health Care Systems: Adherence With a Choosing Wisely Recommendation

2015 ◽  
Vol 11 (3) ◽  
pp. e320-e328 ◽  
Author(s):  
Erin E. Hahn ◽  
Tania Tang ◽  
Janet S. Lee ◽  
Corrine Munoz-Plaza ◽  
Joyce O. Adesina ◽  
...  
Keyword(s):  
Breast Cancer ◽  
Health Care ◽  
Early Stage ◽  
Health Care Systems ◽  
Integrated Health Care ◽  
Low Risk ◽  
Choosing Wisely ◽  
Early Stage Breast Cancer ◽  
Care Systems ◽  
Risk Breast Cancer

Use of imaging for staging of low-risk breast cancer was similar in both systems, and slightly lower than has been reported in the literature.

scholarly journals Clinical Predictive Models for COVID-19: Systematic Study (Preprint)

2020 ◽  
Author(s):  
Patrick Schwab ◽  
August DuMont Schütte ◽  
Benedikt Dietz ◽  
Stefan Bauer
Keyword(s):  
Machine Learning ◽  
Health Care ◽  
Intensive Care ◽  
Clinical Data ◽  
Predictive Models ◽  
Health Care Systems ◽  
Gradient Boosting ◽  
Support Vector ◽  
Care Systems ◽  
To Receive

BACKGROUND COVID-19 is a rapidly emerging respiratory disease caused by SARS-CoV-2. Due to the rapid human-to-human transmission of SARS-CoV-2, many health care systems are at risk of exceeding their health care capacities, in particular in terms of SARS-CoV-2 tests, hospital and intensive care unit (ICU) beds, and mechanical ventilators. Predictive algorithms could potentially ease the strain on health care systems by identifying those who are most likely to receive a positive SARS-CoV-2 test, be hospitalized, or admitted to the ICU. OBJECTIVE The aim of this study is to develop, study, and evaluate clinical predictive models that estimate, using machine learning and based on routinely collected clinical data, which patients are likely to receive a positive SARS-CoV-2 test or require hospitalization or intensive care. METHODS Using a systematic approach to model development and optimization, we trained and compared various types of machine learning models, including logistic regression, neural networks, support vector machines, random forests, and gradient boosting. To evaluate the developed models, we performed a retrospective evaluation on demographic, clinical, and blood analysis data from a cohort of 5644 patients. In addition, we determined which clinical features were predictive to what degree for each of the aforementioned clinical tasks using causal explanations. RESULTS Our experimental results indicate that our predictive models identified patients that test positive for SARS-CoV-2 a priori at a sensitivity of 75% (95% CI 67%-81%) and a specificity of 49% (95% CI 46%-51%), patients who are SARS-CoV-2 positive that require hospitalization with 0.92 area under the receiver operator characteristic curve (AUC; 95% CI 0.81-0.98), and patients who are SARS-CoV-2 positive that require critical care with 0.98 AUC (95% CI 0.95-1.00). CONCLUSIONS Our results indicate that predictive models trained on routinely collected clinical data could be used to predict clinical pathways for COVID-19 and, therefore, help inform care and prioritize resources.

scholarly journals Pilot Project - Ambassadors: Women in Defense of Breast Health

2018 ◽  
Vol 4 (Supplement 2) ◽  
pp. 173s-173s
Author(s):  
A.L. Gomes ◽  
F. Mattos ◽  
M. Caleffi
Keyword(s):  
Public Health ◽  
Breast Cancer ◽  
Health Care ◽  
Health Care Systems ◽  
Scientific Information ◽  
Training Session ◽  
Pilot Project ◽  
Public Health Care ◽  
The Public ◽  
Care Systems

Background and context: The estimate of new cases of breast cancer in Brazil in 2017 totaled 57,960 cases (INCA - National Cancer Institute). In addition to this estimate, we know that 75% of Brazilians are public health care users, which include patients fighting BC, who face several problems ranging from lack of early diagnosis to the lack of access to quick and appropriate treatments. BC is the deadliest neoplasia for women in the country, being responsible to approximately 18% of female deaths caused by cancer. Most of the time, patients are not provided with scientific information about the disease, health care systems, and applicable laws. Therefore, they do not take advantage of the opportunities to publicly fight for the cause and express themselves in an assertive way to assure and expand their rights. Thus, this project aims at training and educating these patients, so that they can become ambassadors of BC. Aim: Contribute to the training and education of BC patients and volunteers, encouraging the development of their leaderships and representation skills regarding the defense of Federação Brasileira de Instituições Filantrópicas de Apoio à Saúde da Mama’s (FEMAMA´s) cause. Strategy/Tactics: Organization of a pilot project in a given Brazilian state, aiming at training and educating at least 20 women on topics related to BC, advocacy and media training so they can become representatives of the cause. Program/Policy process: Planning: Preparation of a tool kit (folder with the contents of the training sessions, key messages and instructions on how to address the public) and training. Engagement: Engagement of BC patients and volunteers at NGOs so they can be trained. Implementation: Organization of a 40-hour training session on topics such as: causes and symptoms, diagnosis, treatments, principles and operations of private and public health care systems, on-site visits to public and private reference units in BC treatments, patient rights, advocacy, media training, etc. Feedback: searching opportunities for trained women to address the topics learned in lectures and interviews. Outcomes: 40 hours of training; 25 qualified ambassadors; a 25% increase in the number or correct answers in knowledge tests, when compared with pretests and posttests; holding lectures at companies and speeches at social control bodies by the ambassadors; two additional lectures for the continuing education of the ambassadors on biosimilar products and the assessment of health care technologies, after the end of the main training session; and approval of the project´s main sponsor to expand the project to 3 other Brazilian states. What was learned: There were no indications of breast cancer patients being treated in the public health care system to participate in the project, according to the hospitals themselves, as they did not want their patients to be empowered and give rise to demands that the hospitals could not meet. Therefore, we had to focus on our associate NGOs when searching for women to participate in the project.

scholarly journals Clinical Predictive Models for COVID-19: Systematic Study

10.2196/21439 ◽  
2020 ◽  
Vol 22 (10) ◽  
pp. e21439 ◽  
Author(s):  
Patrick Schwab ◽  
August DuMont Schütte ◽  
Benedikt Dietz ◽  
Stefan Bauer
Keyword(s):  
Machine Learning ◽  
Health Care ◽  
Intensive Care ◽  
Clinical Data ◽  
Predictive Models ◽  
Health Care Systems ◽  
Gradient Boosting ◽  
Support Vector ◽  
Care Systems ◽  
To Receive

Background COVID-19 is a rapidly emerging respiratory disease caused by SARS-CoV-2. Due to the rapid human-to-human transmission of SARS-CoV-2, many health care systems are at risk of exceeding their health care capacities, in particular in terms of SARS-CoV-2 tests, hospital and intensive care unit (ICU) beds, and mechanical ventilators. Predictive algorithms could potentially ease the strain on health care systems by identifying those who are most likely to receive a positive SARS-CoV-2 test, be hospitalized, or admitted to the ICU. Objective The aim of this study is to develop, study, and evaluate clinical predictive models that estimate, using machine learning and based on routinely collected clinical data, which patients are likely to receive a positive SARS-CoV-2 test or require hospitalization or intensive care. Methods Using a systematic approach to model development and optimization, we trained and compared various types of machine learning models, including logistic regression, neural networks, support vector machines, random forests, and gradient boosting. To evaluate the developed models, we performed a retrospective evaluation on demographic, clinical, and blood analysis data from a cohort of 5644 patients. In addition, we determined which clinical features were predictive to what degree for each of the aforementioned clinical tasks using causal explanations. Results Our experimental results indicate that our predictive models identified patients that test positive for SARS-CoV-2 a priori at a sensitivity of 75% (95% CI 67%-81%) and a specificity of 49% (95% CI 46%-51%), patients who are SARS-CoV-2 positive that require hospitalization with 0.92 area under the receiver operator characteristic curve (AUC; 95% CI 0.81-0.98), and patients who are SARS-CoV-2 positive that require critical care with 0.98 AUC (95% CI 0.95-1.00). Conclusions Our results indicate that predictive models trained on routinely collected clinical data could be used to predict clinical pathways for COVID-19 and, therefore, help inform care and prioritize resources.

scholarly journals Quality of life domains affected in women with breast cancer

2015 ◽  
Vol 36 (2) ◽  
pp. 89-96 ◽  
Author(s):  
Sabrina Nunes Garcia ◽  
Michele Jacowski ◽  
Gisele Cordeiro Castro ◽  
Carila Galdino ◽  
Paulo Ricardo Bittencourt Guimarães ◽  
...  
Keyword(s):  
Breast Cancer ◽  
Quality Of Life ◽  
Health Care ◽  
Body Image ◽  
Health Care Systems ◽  
Life Questionnaire ◽  
Private Health Care ◽  
Cancer Data ◽  
Care Systems

OBJECTIVE: This study aimed to investigate the quality of life of women suffering from breast cancer undergoing chemotherapy in public and private health care systems. METHOD: It is an observational, prospective study with 64 women suffering from breast cancer. Data was collected with two instruments: Quality of Life Questionnaire C30 and Breast Cancer Module BR23. By applying Mann Whitney and Friedman's statistical tests, p values < 0.05 were considered statistically significant. RESULTS: The significant results in public health care systems were: physical functions, pain symptom, body image, systemic effects and outlook for the future. In private health care systems, the results were sexual, social functions and body image. Women's quality of life was harmed by chemotherapy in both institutions. CONCLUSION: The quality of life of women has been harmed as a result of the chemotherapy treatment in both institutions, but in different domains, indicating the type of nursing care that should be provided according to the characteristics of each group.

Sign in / Sign up

Export Citation Format

Share Document