Electronic health records (EHRs) have begun to permeate the healthcare system, often replacing the traditional file room in hospitals and physician offices with electronic repositories of data. While leaders from all facets of the healthcare industry have discussed the enormous benefits of digitized healthcare information, much is yet to be realized from this shift.

The reason? Integrating and analyzing data from existing EHRs has been a significant challenge. Often, existing EHR systems are intended to facilitate the care of an individual patient just as care was provided before the electronic record existed, rather than to optimize care. In addition, the complexity of the data, and of the questions that need to be asked of that data, significantly complicate the ultimate goal – to gain knowledge to support the best, and most efficient care for each patient.

[See also: How the big data tools ACA, HITECH enable will improve care, cut waste.]

Recently, Booz Allen Hamilton sought to understand how this rich data that is being compiled by hospitals and healthcare providers could become an asset for patient care – by leveraging advanced data collection and analysis to reduce patient risks and improve care.

Starting in 2010, we wanted to see how analytics could utilize “big data” to address a costly condition in the healthcare system – severe sepsis and septic shock (S4). Sepsis, an acute body-wide inflammatory state in the presence of a known or suspected infection, affects hundreds of thousands of patients annually, particularly those in Intensive Care Units (ICUs), with a mortality rate of 30-60 percent. In addition to the human cost, sepsis places a huge burden on hospitals. Annually, it costs hospitals an estimated $28 billion to $33 billion a year.

Working with our partner Mercy Health, a St. Louis-based healthcare delivery system, we wanted to understand how data could be leveraged to design better approaches to address severe sepsis and improve patient care. Booz Allen and Mercy Health created the Sepsis Intervention Outcomes Research (SIOR) project, which sought to analyze patient EHR records to understand compliance with treatment guidelines and identify indicators that could lead to early detection.

Working together, Booz Allen and Mercy Health led an integrated effort that tapped analytical, clinical, administrative, and business expertise across both organizations. SIOR analyzed medical workers’ compliance with international standards of care for S4, and compared that compliance with patient outcomes. Booz Allen and Mercy Health developed a unique analytical framework to allow for more efficient computation and discovery of underlying relationships for this condition.

We found that on average in only 17 percent of S4 cases hospitals followed best practices to treat S4 within six hours of diagnosis. Moreover, increased compliance to international guidelines for treatment was found to be strongly correlated with a decrease in patient mortality – with an observed roughly 20 percent decrease in mortality for the hospitals most fully compliant with treatment guidelines versus the least compliant.

In addition, Booz Allen’s advanced analytics experts were able to analyze various forms of data, including unstructured text such as medical personnel notes, to improve early detection of S4, finding important indicators that, in turn, could alert medical staff to potentially escalating situations earlier, buying precious treatment time, and decreasing sepsis-related suffering and mortality. The team found an initial set of clinical indicators that may classify which patients with sepsis are at risk to develop S4. Though preliminary, these results could help to identify high-risk patients and prioritize their care.

[See also: WIth eye on public health, Delaware, Michigan roll out clouds.]

This project provides insights into how hospitals can lower costs from hospital-acquired infections (HAIs), like sepsis, freeing resources for other patient care and other priorities by integrating data and using advanced analytics. SIOR has already become a model for advanced analytics to help fight other HAIs, identify potential discharge-readmission problems, and assist in a range of other healthcare issues.

But, this is only the beginning of analytics in healthcare. The healthcare industry is flush with data – from clinical to financial, imaging, and social media data. We believe the vast amount of data available – whether from EHRs or paper records – has created an unprecedented opportunity to improve patient care, leading to new treatments, better processes, reduced costs – and lives saved.