It’s Not Adding Up: How Interval Monitoring Creates Gaps in the Sepsis Storyline
However, the emergence of advanced analytics may prove to be decisive. In this installment, I explore how advanced analytics—surfaced through multi-variate real-time data and continuous surveillance—can enhance existing sepsis detection tools, specifically, Early Warning Scores.
Early Warning Scores and Their Limitations
Early Warning Scores (EWS) are widely used in hospitals and health systems around the world. These are simple and cost-effective tools to help clinicians identify how sick a patient really is—and their risk for further deterioration.
Many EWS provide reasonable predictions of sepsis, usually within 48 hours. EWS track variations in multiple physiological parameters, such as respiratory rate, heart rate and SpO2.
It’s a matter of debate regarding the optimal criteria for the timely identification of sepsis. However, there is consensus that real-time data are essential to the predictive accuracy of EWS calculations. Downey et al., note that EWS “are limited by their intermittent and user-dependent nature, which can be partially overcome by automation and new continuous monitoring technologies.”
Combining real-time data from physiologic devices and historical data stored in the EHR enables the identification of potential deterioration, as well as timely notification to the appropriate clinical team. Crucially, this allows clinicians to initiate diagnosis and treatment before the patient reaches a critical state.
Why Real-Time Data Matters
Interval monitoring is like watching a movie where every few minutes the film suddenly cuts to a new scene that picks up the story at a later point in time. An eagle-eyed viewer may be able to fill in the blanks, but critical plot points may have been lost due to those abrupt edits.
In healthcare, continuous clinical surveillance solutions that analyze real-time patient data can identify clinically relevant trends, sustained conditions, reoccurrences and combinatorial indications tells a more complete story.
For example, tachycardia or bradycardia occurring at a sustained duration of 15 to 20 seconds may not be captured if discrete heart rate measurements are on one-minute or five-minute intervals. In this case, identifying a patient at risk for sepsis is a matter of luck.
In short, the analytics with the most data inputs is often the best analytics. The combination of high-fidelity data with multivariate, EHR information provides a holistic and complete source of objective information on a patient that can be used for prediction and clinical decision making.
All sources of data, from episodic to real-time, provide a rich source for clinical decision making and optimized EWS. As healthcare systems complete the process of implementing EHR systems involving integrated data from medical devices, the next step in the process is combining these data points (historical and real-time) to bring about added clinical value.
The Challenges of Real-Time Data
Pullen notes that “having an early warning system and being able to use it to alter clinical care are two different challenges. Currently, few hospitals have the capacity for the latter…” The challenge real-time data presents to hospitals are both technical (achieving continuous surveillance) and human-based (adjusting workflow to accommodate early intervention).
Additionally, concerns over adding to clinician alarm fatigue and contributing to an increasingly noisy hospital environment are significant obstacles. Hospitals need to take a system-wide inventory of alarms, apply analytics to understand their value and convene project teams to embark on a technology transformation.
This transformation should include the perspectives of frontline clinicians and should respect the significance of disrupting workflows. Hospitals should employ smart technologies to ensure only actionable alarm signals are sent to clinical staff. The deployment of continuous clinical surveillance requires a careful investment of time and money in addition to workflow considerations to ensure the highest level of patient safety. Fortunately, the positive returns from these investments are significant for clinical and operational outcomes. (Read the eBook “A Business and Clinical Case for Creating the Foundation for Real-Time Healthcare”)
By providing timely, patient-centered care and making sepsis care more affordable through early intervention, this measure can result in reduced use of resources and lower rates of complications, according to CMS Core Measure for sepsis.
In the next installment, I will explore the use of real-time data and EHRs.