Identify the Association between Clinicopathologic Variables in Breast Cancer Overall Survival using Biogeography-Based Optimization

• Main Authors: Guang-Yu Chen, 陳廣育
• Other Authors: Cheng-Hong Yang
• Format: Others
• Language: en_US
• Published: 2018
• Online Access: http://ndltd.ncl.edu.tw/handle/4jqh8u

碩士 === 國立高雄應用科技大學 === 電子工程系 === 106 === Breast cancer is the most common cancer among women worldwide and has been regarded as an important public health issue in global. It is estimated 1.67 million newly diagnosed cases each year, ranking second for cancer incidence rate and fifth for cause of death from cancer. Biogeography-based optimization (BBO) is a novel meta-heuristic algorithm, inspired from the science of biogeography. This study aimed to analyze the relationship between clinicopathologic variables of breast cancer using Cox proportional hazard regression (Cox PH) based on BBO algorithm. The dataset is prospectively maintained by the Breast Surgery Division in Kaohsiung Medical University Hospital. Total 1,896 breast cancer patients were included and tracked from 2005 to 2017. Fifteen general breast cancer clinicopathologic variables were collected. We used the BBO algorithm to select the clinicopathologic variables which could potentially contribute to the breast cancer prognosis estimation. Afterward, the Cox PH regression analysis was used to demonstrate the association between overall survival and selected clinicopathologic variables. The C-statistics were used to examine predictive accuracy and concordance of various survival models. The BBO selected clinicopathologic variables model obtained the highest C-statistic value of 80% for predicting breast cancer overall survival. This study revealed the BBO algorithm was able to select only eight clinicopathologic variables, which are the minimum discriminators needed for optimal discriminant for breast cancer overall survival model with an acceptable prediction result. This survival prediction model might contribute to breast cancer disease follow-up and further management based on the clinicopathologic variables.