Breast cancer is the most common cancer in women occurring worldwide. Some of the procedures used to diagnose breast cancer are mammogram, breast ultrasound, biopsy, breast magnetic resonance imaging, and blood tests such as complete blood count. Detecting breast cancer at an early stage plays an important role in diagnostic and curative procedures. This paper aims to develop a predictive model for detecting the breast cancer using blood samples data containing age, body mass index (BMI), glucose, insulin, homeostasis model assessment (HOMA), leptin, adiponectin, resistin, and chemokine monocyte chemoattractant protein 1 (MCP-1).The two main challenges encountered in this process are identification of biomarkers and the precision of disease prediction accuracy. The proposed methodology employs principal component analysis in a peculiar approach followed by random forest tree prediction model to discriminate between healthy and breast cancer patients. This approach extracts high communalities, a linear combination of input attributes in a systematic procedure as principal axis elements. The iteratively extracted principal axis elements combined with minimum number of input attributes are able to predict the disease with higher accuracy of classification with increased sensitivity and specificity score. The results proved that the proposed approach generates a higher predictor performance than the previous reported results by opting relevant extracted principal axis elements and attributes that commend the classifier with increased performance measures.

乳腺癌是全世界女性中最常见的癌症。一些用于诊断乳腺癌的程序包括乳房 X 光检查、乳房超声检查、活检、乳房磁共振成像和血液检查，例如全血细胞计数。早期检测乳腺癌在诊断和治疗过程中起着重要作用。本文旨在开发一种使用包含年龄、体重指数 (BMI)、葡萄糖、胰岛素、稳态模型评估 (HOMA)、瘦素、脂联素、抵抗素和趋化因子单核细胞趋化蛋白 1 的血样数据检测乳腺癌的预测模型。 (MCP-1)。这个过程中遇到的两个主要挑战是生物标志物的识别和疾病预测准确度的精确度。所提出的方法在一种特殊的方法中采用主成分分析，然后是随机森林树预测模型来区分健康和乳腺癌患者。这种方法提取高公共性，系统程序中输入属性的线性组合作为主轴元素。迭代提取的主轴元素与最少数量的输入属性相结合，能够以更高的分类准确度和更高的灵敏度和特异性评分来预测疾病。结果证明，通过选择相关提取的主轴元素和属性，所提出的方法产生了比以前报告的结果更高的预测器性能，这些主轴元素和属性对分类器具有更高的性能度量。