BackgroundThe goal of this exploratory study was to develop and assess a prediction model which can potentially be used as a biomarker of breast cancer, based on anthropometric data and parameters which can be gathered in routine blood analysis.MethodsFor each of the 166 participants several clinical features were observed or measured, including age, BMI, Glucose, Insulin, HOMA, Leptin, Adiponectin, Resistin and MCP-1. Machine learning algorithms (logistic regression, random forests, support vector machines) were implemented taking in as predictors different numbers of variables. The resulting models were assessed with a Monte Carlo Cross-Validation approach to determine 95% confidence intervals for the sensitivity, specificity and AUC of the models.ResultsSupport vector machines models using Glucose, Resistin, Age and BMI as predictors allowed predicting the presence of breast cancer in women with sensitivity ranging between 82 and 88% and specificity ranging between 85 and 90%. The 95% confidence interval for the AUC was [0.87, 0.91].ConclusionsThese findings provide promising evidence that models combining age, BMI and metabolic parameters may be a powerful tool for a cheap and effective biomarker of breast cancer.Electronic supplementary materialThe online version of this article (10.1186/s12885-017-3877-1) contains supplementary material, which is available to authorized users.
our data provides evidence of a greater benefit with a combination of atorvastatin and metformin in improving liver injury in type 2 diabetes with hyperlipidaemia.
Breast cancer is the most common malignancy among women worldwide. There is extensive literature on the relationship between body weight and breast cancer risk but some doubts still remain about the role of adipokines per se, the role of insulin and glucose regardless of obesity, as well as the crosstalk between these players. Thus, in this study, we intend to determine the relation between body mass index (BMI), glycaemia, insulinemia, insulin-resistance, blood adipokine levels and tumour characteristics in a Portuguese group of pre- and postmenopausal overweight/obese women with breast cancer. We evaluated clinical and biochemical data in 154 participants, divided in 4 groups: (1) control with BMI <25 kg/m(2), n = 29 (CT); (2) control with BMI >25 kg/m(2), n = 48 (CTOb); (3) breast cancer with BMI <25 kg/m(2), n = 30 (BC); and (4) breast cancer with BMI >25 kg/m(2), n = 47 (BCOb). In women with breast cancer, we also performed tumour characterization. We found that BCOb present increased fasting blood glucose, insulin, resistin and monocyte chemoattractant protein 1, insulin resistance and more aggressive tumours. Notably, this profile is not correlated with BMI, proposing the involvement of other processes than adiposity. Altogether, our results suggest that glucose dysmetabolism, insulin resistance and changes in adipokine secretion, in particular resistin, may be involved in the development and progression of breast cancer in overweight/obese pre- and postmenopausal women.
scite is a Brooklyn-based organization that helps researchers better discover and understand research articles through Smart Citations–citations that display the context of the citation and describe whether the article provides supporting or contrasting evidence. scite is used by students and researchers from around the world and is funded in part by the National Science Foundation and the National Institute on Drug Abuse of the National Institutes of Health.