S Sountharrajan, M Karthiga, E Suganya, C Rajan
Department of Computer Science and Engineering, Bannari Amman Institute of Technology, India.Email:
Asian Pac J Cancer Prev. 2017 Sep 27;18(9):2541-2544. doi: 10.22034/APJCP.2017.18.9.2541.
Breast Cancer one of the appalling diseases among the middle-aged women and it is a foremost threatening death possibility cancer in women throughout the world. Earlier prognosis and preclusion reduces the conceivability of death. The proposed system beseech various data mining techniques together with a real-time input data from a biosensor device to determine the disease development proportion. Surface acoustic waves (SAW) biosensor empowers a label-free, worthwhile and straight detection of HER-2/neu cancer biomarker. The output from the biosensor is fed into the proposed system as an input along with data collected from Winconsin dataset. The complete dataset are processed using data mining classification algorithms to predict the accuracy. The exactness of the proposed model is improved by ranking attributes by Ranker algorithm. The results of the proposed model are highly gifted with an accuracy of 79.25% with SVM classifier and an ROC area of 0.754 which is better than other existing systems. The results are used in designing the proper drug thereby improving the survivability of the patients.
乳腺癌是中年女性中令人震惊的疾病之一，并且是全球女性中最具威胁生命可能性的癌症。早期的预后和预防可降低死亡的可能性。所提出的系统运用了各种数据挖掘技术以及来自生物传感器设备的实时输入数据，以确定疾病的发展程度。表面声波（SAW）生物传感器能够对HER-2/neu癌症生物标志物进行无标记、高效且直接的检测。生物传感器的输出作为输入与从威斯康星数据集收集的数据一起被输入到所提出的系统中。使用数据挖掘分类算法对完整的数据集进行处理以预测准确性。通过使用排序算法对属性进行排序，提高了所提出模型的准确性。所提出模型的结果非常出色，使用支持向量机分类器时准确率为79.25%，ROC面积为0.754，优于其他现有系统。这些结果被用于设计合适的药物，从而提高患者的生存率。
