A Natural Language Processing Framework for Assessing Hospital Readmissions for Patients With COPD
A Natural Language Processing Framework for Assessing Hospital Readmissions for Patients With COPD
复制标题
DOI：
10.1109/jbhi.2017.2684121
复制
发表时间：
2018-03-01
影响因子：
7.7
通讯作者：
Zhu, Xingquan
中科院分区：
文献类型：
--
作者：
Agarwal, Ankur;Baechle, Christopher;Zhu, Xingquan
随着最近联邦立法的通过，许多医疗机构现在有责任达到目标医院再入院率。慢性病是许多再入院的原因，而慢性阻塞性肺疾病最近已被添加到美国政府对再入院过多的医院进行处罚的疾病清单中。尽管人们一直在努力统计预测那些最有可能再次入院的人，但有些人主要关注非结构化的临床记录。我们提出了一个框架，它使用自然语言处理来分析临床记录并预测再入院。数据挖掘和机器学习领域存在许多算法，因此创建了组件选择框架来选择最佳组件。使用卡方特征选择的朴素贝叶斯提供了 0.690 的 AUC，同时保持快速的计算时间。
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. Naive Bayes using Chi-Squared feature selection offers an AUC of 0.690 while maintaining fast computational times.