MIMIC II LARGE SCALE DATABASE TO SUPPORT MULTIPARAMETER INTELLIGENT MONITORING

本子项目是利用由NIH/NCRR资助的中心赠款提供的资源的众多研究子项目之一。子项目和研究者（PI）可能已经从另一个NIH来源获得了主要资金，因此可以在其他CRISP条目中表示。列出的机构是中心的，不一定是研究者的机构。为了支持下一代ICU患者监护智能患者监测系统的开发，我们正在开发一个规模空前的ICU患者海量临时医学数据库（MIMIC-II）。使用现代网络和数据库技术，我们正在归档患者记录，包括几个医疗参数通道（心率、血压）、波形（心电图、血压）和所有来自临床信息系统的可用数据（体液平衡、药物、实验室结果、护士文本笔记）。迄今为止，我们已经收集了超过120千兆字节的数据，包括近700名患者的个人记录。患者记录可能从几个小时到200小时或更长时间；从ICU住院到出院我们目前正在创建一个用户友好的关系数据库，以便简化MIMIC-II的搜索和索引。我们已经开发了新的时态查询抽象，它将有效地支持各种查询，以及数据挖掘和知识发现研究。使用MIMIC-II，我们目前正在评估我们最近开发的新型智能监控算法和显示框架。

This subproject is one of many research subprojects utilizing the resources provided by a Center grant funded by NIH/NCRR. The subproject and investigator (PI) may have received primary funding from another NIH source, and thus could be represented in other CRISP entries. The institution listed is for the Center, which is not necessarily the institution for the investigator. To support the development of next-generation intelligent patient monitoring systems for ICU patient care, we are developing a massive temporal medical database of unprecedented size from ICU patients (MIMIC-II). Using modern networking and database technologies, we are archiving patient records that include several channels of medical parameters (heart rate, blood pressures), waveforms (ECG, blood pressures), and all the available data from clinical information systems (fluid balance, medications, lab results, nurse text notes). We have hitherto collected over 120 gigabytes of data, including nearly 700 individual patient records. A patient record may span from a few hours to 200 or more hours; from an ICU admission to a discharge. We are currently creating a user-friendly relational database to allow for simplified searching and indexing of MIMIC-II. We have developed novel temporal query abstractions that will efficiently support a wide variety of queries, as well as data mining and knowledge-discovery research. Using MIMIC-II, we are currently evaluating novel intelligent monitoring algorithms and display frameworks that we have recently developed.