Using Real-Time Data to Impede the ‘Quiet Killer’

by John Zaleski, Ph.D., CAP, CPHIMS
Chief Analytics Officer

A 38-year-old male patient with a history of atrial fibrillation presents with a low-grade fever and congestion. The nurse on duty notes slightly hypotensive blood pressure, but the patient’s heart rate is within the normal range. Blood oxygenation level is slightly low and respiratory rate is slightly high.

It could be a urinary tract infection, she thinks. Maybe pneumonia.

The care team provides prescribed antibiotics to treat the main infection. Unfortunately, they missed—or misinterpreted—the subtle, early signs of sepsis. Suddenly, a patient who “looks pretty good” is in mortal danger.

The ‘Quiet Killer’

Every year more than 1.5 million Americans are diagnosed with severe sepsis, according to the Centers for Disease Control and Prevention. Of those, 250,000 don’t survive.

The Agency for Healthcare Research and Quality cites sepsis as the most costly illness treated in hospitals—more than $24 billion annually. Sepsis often requires prolonged and pricey hospital stays in intensive care units (ICUs). It also is a leading cause of frequent, unplanned readmissions, more than double of such conditions as acute myocardial infarction, heart failure, COPD and pneumonia.

Hospitals have employed multiple strategies and tools in their battle against sepsis. Improved training for clinicians, better screening tools and the implementation of sepsis programs have reduced mortality. Sadly, sepsis remains an urgent problem in need of a real-time solution.

Solve Sepsis by Solving Data

Early intervention of sepsis is critical to patient outcomes that are both life-saving and cost-effective. However, early intervention requires holistic data, actionable and consistently routed to the right clinicians at the right time. Therein lies the problem.

The 20-year quest to digitize data has provided clinicians with a deep portrait of a patient’s condition. The emerging use of real-time data is adding even richer and more holistic detail to the patient’s story.

However, the discrete data collected from EHRs, medical devices, software apps and other automated technologies has presented distinct challenges:

  • The sheer amount of data collected from a patient during a hospital stay can easily overwhelm even the most vigilant clinician;
  • Much of the data collected is never seen or used, leaving gaps in the patient’s story that may be critical to a positive outcome; and
  • The interpretation of the data—through improperly set or reliance on default alarm parameters—can lead to excess and spurious notifications than can cause fatigue in nurses.

Connecting the Dots

The use of continuous clinical surveillance to yield predictive analytics offers clinicians a quantitative estimate of whether a patient’s status is going to get worse over time.

One of the goals of analytics is to connect the dots from among seemingly unrelated, individual data sources. This ability enables clinicians to observe a potentially adverse course in the patient’s condition over time, prior to the violation of the limit threshold of any individual parameter, and respond before costly interventions are required. Also, data collected continuously, rather than in intervals, is much more granular.

Analytics based on multiple sources of data also can help offset the problem of alarm fatigue by filtering out false or artifact signals that typically invade the high-fidelity data at the core of continuous surveillance.

An advanced, multi-variate rules-based analytics engine would help with early identification of changes to the patient’s state. The system leverages protocol-driven measures for sepsis detection and data from the EHR. Further, it notifies the appropriate care team members.

Continuous monitoring is largely standardized in ICUs and critical care units. However, there is strong case to be made that patients on the general care floor also will benefit from continuous clinical surveillance. Some of those patients may be sicker than periodic spot checks may indicate.

By providing timely, patient-centered care and making sepsis care more affordable through early intervention, the results are improved patient safely and reduced patient mortality, reduced use of resources and lower rates of complications.

About the Author:
john zaleski

John Zaleski,
Chief Analytics Officer

Dr. Zaleski brings more than 25 years of experience in researching and ushering to market devices and products to improve health care. He received his PhD from the University of Pennsylvania, with a dissertation that describes a novel approach for modeling and prediction of post-operative respiratory behavior in post-surgical cardiac patients. Dr. Zaleski has a particular expertise in designing, developing and implementing clinical and non-clinical point of care applications for hospital enterprises. Dr. Zaleski is the named inventor or co-inventor on seven issued patents related to medical device interoperability and has authored three seminal texts on integrating medical device data with electronic health record systems and using medical device data for real-time clinical decision making. View John’s profile on Linkedin.