Lung cancer is one of the most common diseases for human beings everywhere throughout the world. Early identification of this disease is the main conceivable approach to enhance the possibility of patients’ survival. In this paper, a k-Nearest-Neighbors technique, for which a genetic algorithm is applied for the efficient feature selection to reduce the dataset dimensions and enhance the classifier pace, is employed for diagnosing the stage of patients’ disease. To improve the accuracy of the proposed algorithm, the best value for k is determined using an experimental procedure. The implementation of the proposed approach on a lung cancer database reveals 100% accuracy. This implies that one could use the algorithm to find a correlation between the clinical information and data mining techniques to support lung cancer staging diagnosis efficiently.

肺癌是全世界人类最常见的疾病之一。尽早发现这种疾病是增加患者生存可能性的主要方法。在本文中，采用k最近邻技术来诊断患者疾病的阶段，该技术采用遗传算法进行有效的特征选择，以减少数据集的维数并提高分类速度。为了提高所提出算法的准确性，使用实验程序确定k的最佳值。肺癌数据库中拟议方法的实施显示出100％的准确性。这意味着可以使用该算法在临床信息和数据挖掘技术之间找到关联，以有效地支持肺癌分期诊断。