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. Mimic II is a large database collected from patients in intensive care units. The data it contains includes nurses' notes, lab tests, ventilator settings, measurements of cardiac function, IV medications, and fluid balance. The database also includes unverified, one-minute trend signals in addition to the verified ones for some signals such as heart rate and blood pressure. There are also high rate 125hz signals for several leads of ECG, blood pressure and respiration. The database must be carefully annotated by expert clinicians to provide an analysis of the dynamic trajectory of the physiologic state of the patients. The objective of this project is to develop a tool called the 'Annotation Station' that allows physicians to manually annotate this large database of widely varied signals. A sophisticated graphical user interface has been designed that conveniently displays the data as time series to provide the annotator with a compact overview of the patient's clinical course. Tools have been developed that support the annotation and coding of significant clinical events, and the specific evidence that supports the annotation.
Showing the most recent 10 out of 109 publications
