Abstract:
Hepatitis is among the deadliest diseases on the planet. Machine learning approaches can contribute toward diagnosing hepatitis disease based on a few characteristics. On the UCI dataset, authors assessed distinct classifiers\' performance in order to develop a systematic strategy for hepatitis disease diagnosis. The classifiers used are support vector machine, logistic regression (LR), K-nearest neighbor, and random forest. The classifiers were employed without class balancing and in conjunction with class balancing using SMOTE strategy. Both studies, classification without class balancing and with class balancing, were compared in terms of different performance parameters. After adopting class balancing, the efficiency of classifiers improved significantly. LR with SMOTE provided the highest level of accuracy (93.18%).
摘要:
肝炎是地球上最致命的疾病之一。机器学习方法可以基于一些特征来诊断肝炎疾病。在UCI数据集上,作者评估了不同分类器的性能,以制定肝炎疾病诊断的系统策略。使用的分类器是支持向量机,逻辑回归(LR),K-最近邻,和随机森林。分类器在没有类别平衡的情况下使用,并使用SMOTE策略与类别平衡结合使用。两项研究,没有类平衡和类平衡的分类,在不同的性能参数方面进行了比较。采用类平衡后,分类器的效率明显提高。具有SMOTE的LR提供最高水平的准确度(93.18%)。