Interaction Among Parameters of Breast Cancer at Wisconsin Diagnostic Centre Using Large Data

Abstract

This study applied a binary logistic regression model to determine the effect among some selected variables of breast cancer data collected from Wisconsin (diagnostic data). The data set is made of 569 observations and 25 variables. In this research, we examined the above mentioned data using python programming. The critical examination of the chart of the two diagnosis stages   malignant and benign, revealed high levels of benign and low levels of malignant among the patients diagnosed with breast cancer. The covariance matrix between the variables shows a strong positive relationship between the variables with correlation value of +1. The normal distribution curve was determined in two stages with outliers and without outliers. The Coefficient of Determination of the binary logistic regression model (R2) is 0.556.  This implies that 55.7% of a high degree of statistical significance emphasizes how well the model performs based on the predictors distinguishing between some selected variable of breast cancer. The binary logistic regression model supports the claim that specific tumour characteristics correlate highly with the tumour's diagnosis. These discoveries have the potential to improve oncology predictive modelling and clinical decision-making, which could improve patient outcomes and diagnostic accuracy.