Abstract
Clinical data management systems typically provide caregiver teams with useful information, derived from large, sometimes highly heterogeneous, data sources that are often changing dynamically. Over the last decade there has been a significant surge in interest in using these data sources, from simply re-using the standard clinical databases for event prediction or decision support, to including dynamic and patient-specific information into clinical monitoring and prediction problems. However, in most cases, commercial clinical databases have been designed to document clinical activity for reporting, liability and billing reasons, rather than for developing new algorithms. With increasing excitement surrounding “secondary use of medical records” and “Big Data” analytics, it is important to understand the limitations of current databases and what needs to change in order to enter an era of “precision medicine.” This review article covers many of the issues involved in the collection and preprocessing of critical care data. The three challenges in critical care are considered: compartmentalization, corruption, and complexity. A range of applications addressing these issues are covered, including the modernization of static acuity scoring; on-line patient tracking; personalized prediction and risk assessment; artifact detection; state estimation; and incorporation of multimodal data sources such as genomic and free text data.
Highlights
THE intensive care unit (ICU) treats acutely ill patients in need of radical, life saving treatments
These measurements range from laboratory measurements performed on blood samples, real time monitoring devices quantifying vital signs, billing codes for health care visits, procedure codes for services provided within health care environments, and more
The US has recently passed the Health Information Technology for Economic and Clinical Health (HITETCH) act, enforcing interoperability among various systems and partly addressing this issue. The consequences of this have been immediately apparent in the uptake of electronic health records (EHRs): in 2008 the number of US hospitals with EHRs was 9.4%, while in 2014 it had grown to 75.5% [25]
Summary
THE intensive care unit (ICU) treats acutely ill patients in need of radical, life saving treatments. The majority of the information required to optimally diagnose, treat and discharge a patient are present in modern ICU databases. Critical care data has historically been compartmentalized, with many distinct measurements of patient health being stored separately, even within the same institution. These data warehouses have been likened to silos, and the integration of data across these silos is a crucial first step before any insight can be gleaned. It illustrates how this article is organised along the lines of the three key challenges (the three data “C's”) in the field: Compartmentalization, Corruption and Complexity
Talk to us
Join us for a 30 min session where you can share your feedback and ask us any queries you have