Predicting Complications in Critical Care Using Heterogeneous Clinical Data
Predicting Complications in Critical Care Using Heterogeneous Clinical Data
复制标题
DOI：
10.1109/access.2016.2618775
复制
发表时间：
2016-01-01
期刊：
影响因子：
3.9
通讯作者：
Reddy, Chandan K.
中科院分区：
文献类型：
--
作者：
Huddar, Vijay;Desiraju, Bapu Koundinya;Reddy, Chandan K.
住院患者，特别是重症监护患者，容易发生许多影响发病率和死亡率的并发症。电子病历中的数字化临床数据可以有效地用于开发机器学习模型，以早期识别有并发症风险的患者，并提供优先护理以预防并发症。然而，来自医院内异构来源的临床数据构成了重大的建模挑战。特别是，非结构化的临床笔记是一个有价值的信息来源，包含定期评估病人的病情，但包含不一致的缩写，并缺乏正式文件的结构。我们在本文中的贡献是双重的。首先，我们提出了一种新的预处理技术，用于从非正式的临床笔记中提取特征，这些特征可用于分类模型中，以识别有并发症风险的患者。其次，我们探索使用集体矩阵分解，多视图学习技术，结合其他测量，如临床调查，合并症，bidites，和人口统计数据的异构临床数据基于文本的功能建模。我们使用MIMIC II数据库中的700多例患者记录对术后呼吸衰竭进行了详细的病例研究。我们的实验证明了我们的预处理技术在从临床笔记中提取歧视性特征方面的有效性，以及多视图学习将联合收割机临床测量与文本数据相结合以预测并发症的益处。
Patients in hospitals, particularly in critical care, are susceptible to many complications affecting morbidity and mortality. Digitized clinical data in electronic medical records can be effectively used to develop machine learning models to identify patients at risk of complications early and provide prioritized care to prevent complications. However, clinical data from heterogeneous sources within hospitals pose significant modeling challenges. In particular, unstructured clinical notes are a valuable source of information containing regular assessments of the patient's condition but contain inconsistent abbreviations and lack the structure of formal documents. Our contributions in this paper are twofold. First, we present a new preprocessing technique for extracting features from informal clinical notes that can be used in a classification model to identify patients at risk of developing complications. Second, we explore the use of collective matrix factorization, a multi-view learning technique, to model heterogeneous clinical data text-based features in combination with other measurements, such as clinical investigations, comor-bidites, and demographic data. We present a detailed case study on postoperative respiratory failure using more than 700 patient records from the MIMIC II database. Our experiments demonstrate the efficacy of our preprocessing technique in extracting discriminatory features from clinical notes as well as the benefits of multi-view learning to combine clinical measurements with text data for predicting complications.