IEEE J Biomed Health Inform. 2018 Mar;22(2):588-596. doi: 10.1109/JBHI.2017.2684121. Epub 2017 Mar 17.
With the passage of recent federal legislation, many medical institutions are now responsible for reaching target hospital readmission rates. Chronic diseases account for many hospital readmissions and chronic obstructive pulmonary disease has been recently added to the list of diseases for which the United States government penalizes hospitals incurring excessive readmissions. Though there have been efforts to statistically predict those most in danger of readmission, a few have focused primarily on unstructured clinical notes. We have proposed a framework, which uses natural language processing to analyze clinical notes and predict readmission. Many algorithms within the field of data mining and machine learning exist, so a framework for component selection is created to select the best components. Naïve Bayes using Chi-Squared feature selection offers an AUC of 0.690 while maintaining fast computational times.
随着最近联邦立法的通过，许多医疗机构现在负责达到目标医院再入院率。慢性病是许多医院再入院的原因，慢性阻塞性肺疾病最近也被列入美国政府惩罚过度再入院的疾病之列。尽管已经有努力从统计学上预测那些最有可能再次入院的人，但很少有人主要关注非结构化的临床记录。我们提出了一个使用自然语言处理来分析临床记录并预测再入院的框架。数据挖掘和机器学习领域有许多算法，因此创建了一个组件选择框架来选择最佳组件。朴素贝叶斯使用卡方特征选择提供了 0.690 的 AUC，同时保持快速的计算时间。
