METHODS: A large hospital-based breast cancer dataset retrieved from the University Malaya Medical Centre, Kuala Lumpur, Malaysia (n = 8066) with diagnosis information between 1993 and 2016 was used in this study. The dataset contained 23 predictor variables and one dependent variable, which referred to the survival status of the patients (alive or dead). In determining the significant prognostic factors of breast cancer survival rate, prediction models were built using decision tree, random forest, neural networks, extreme boost, logistic regression, and support vector machine. Next, the dataset was clustered based on the receptor status of breast cancer patients identified via immunohistochemistry to perform advanced modelling using random forest. Subsequently, the important variables were ranked via variable selection methods in random forest. Finally, decision trees were built and validation was performed using survival analysis.
RESULTS: In terms of both model accuracy and calibration measure, all algorithms produced close outcomes, with the lowest obtained from decision tree (accuracy = 79.8%) and the highest from random forest (accuracy = 82.7%). The important variables identified in this study were cancer stage classification, tumour size, number of total axillary lymph nodes removed, number of positive lymph nodes, types of primary treatment, and methods of diagnosis.
CONCLUSION: Interestingly the various machine learning algorithms used in this study yielded close accuracy hence these methods could be used as alternative predictive tools in the breast cancer survival studies, particularly in the Asian region. The important prognostic factors influencing survival rate of breast cancer identified in this study, which were validated by survival curves, are useful and could be translated into decision support tools in the medical domain.
MATERIALS AND METHODS: A cross-sectional study was conducted among 508 women aged 18 to 55 years from four non-governmental organizations (NGO) in Baghdad city, Iraq. A self-administered questionnaire on breast cancer knowledge and practice was distributed to participants during weekly activity of the NGO.
RESULTS: A total of 61.2% of the respondents had poor knowledge, only 30.3% performed breast self-examination (BSE) and 41.8% said that they did not know the technique to perform BSE. Associations between knowledge and marital status and age were significant. For practice, working status, education, age and family income were significant. After controlling for cofounders, the most important contributing factors for poor knowledge among respondents were marital status and not performing BSE, with adjusted odds ratio of 1.6 and 1.8 respectively.
CONCLUSIONS: Breast cancer knowledge and practice of BSE are poor among women in Baghdad city, Iraq. More promotion regarding breast cancer signs and symptoms and also how to perform BSE should be conducted using media such as television and internet as these constituted the main sources of information for most women in our study.
METHODS: Using data from 272,098 women participating in the European Prospective Investigation into Cancer and Nutrition (EPIC) study, we assessed dietary intake of 92 foods and nutrients estimated by dietary questionnaires. Cox regression was used to quantify the association between each food/nutrient and risk of breast cancer. A false discovery rate (FDR) of 0.05 was used to select the set of foods and nutrients to be replicated in the independent Netherlands Cohort Study (NLCS).
RESULTS: Six foods and nutrients were identified as associated with risk of breast cancer in the EPIC study (10,979 cases). Higher intake of alcohol overall was associated with a higher risk of breast cancer (hazard ratio (HR) for a 1 SD increment in intake = 1.05, 95% CI 1.03-1.07), as was beer/cider intake and wine intake (HRs per 1 SD increment = 1.05, 95% CI 1.03-1.06 and 1.04, 95% CI 1.02-1.06, respectively), whereas higher intakes of fibre, apple/pear, and carbohydrates were associated with a lower risk of breast cancer (HRs per 1 SD increment = 0.96, 95% CI 0.94-0.98; 0.96, 95% CI 0.94-0.99; and 0.96, 95% CI 0.95-0.98, respectively). When evaluated in the NLCS (2368 cases), estimates for each of these foods and nutrients were similar in magnitude and direction, with the exception of beer/cider intake, which was not associated with risk in the NLCS.
CONCLUSIONS: Our findings confirm a positive association of alcohol consumption and suggest an inverse association of dietary fibre and possibly fruit intake with breast cancer risk.