Unleashing the EHR with Real-Time Data

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

In my last two posts, I discussed the costly and enduring threat of sepsis, despite improved clinical training, better screening tools and the development of sepsis programs. I also explored the potential of pairing of advanced analytics and continuous surveillance with Early Warning Score systems to enhance timely sepsis detection.

This concluding installment will focus on how real-time data capabilities can be used in conjunction with retrospective data in the electronic health record (EHR) to add even richer and more holistic detail to a patient’s condition.

The Indispensable EHR

According to the Office of the National Coordinator, 96 percent of hospitals own EHR technology.1

Over the past 15 years, the widespread adoption of EHRs has largely resolved the challenges of data capture and have mitigated issues related to clinicians’ access to critical information. The central role the EHR plays in day-to-day clinical operations practically requires that peripheral technologies—ranging from medical devices and telehealth to financial and administrative solutions—integrate with the system. This is also true of continuous clinical surveillance platforms.

According to a 30-hospital survey by Malkary, more than 80 percent of those hospitals that have deployed clinical surveillance solutions are “leveraging their multi-million EHR investments as a starting point [for] early warning risk scoring and sepsis detection.”2

However, EHRs are not a natural repository for real-time continuous data. Based on the 30 clinical informaticists interviews, Malkary reports that “EHR-based [surveillance] solutions are not considered best-of-breed, difficult and time-consuming to deploy, and require significant customization of alerts, templates and tools to mitigate false positive alerts and alert fatigue.”3

EHRs store data on patients that are relatively static—history, observations and treatment. EHRs do not capture moment-to-moment changes in the patient’s condition, such as heart rate or respiration events. When data are not captured and reviewed in real-time, the potential exists for time gaps which can result in the failure to detect significant events that would not normally be visible at data collection frequencies of, say, once an hour or once every several hours.

Patients are at-risk in between nursing rounds/EHR documentation if not continuously monitored and data are not continuously analyzed to detect deteriorating conditions.

Continuous clinical surveillance solutions that analyze real-time patient data can identify clinically relevant trends, sustained conditions, reoccurrences and combinatorial indications which tells a more complete story, especially when evaluated with EHR-stored data. In short, the analytics with the most data inputs are often the best analytics.

The ability to identify events and establish better patient safety standards for patients is the new frontier for EHRs. As noted by Miriovsky, et al., “To fully harness the potential of EHRs, they need to be more than electronic renderings of the traditional paper medical chart.”4

Unleashing the EHR

EHRs should form the foundation of how hospitals approach surveillance. According to Malkary, “real-time clinical surveillance and analytics solutions can collect and aggregate retrospective data from the EHR… and correlate it with real-time streaming data.”5

Additionally, 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.

However, while “EHRs are great repositories of data and can accomplish some low-level data aggregation… these systems were never designed to address the level of data analytics needed to advance care delivery from reactive to proactive.”6

Actionable information is key to minimizing patient risk. Clinicians must have access to the full patient picture that pulls from all of a hospital’s data sources, including admissions/discharge/transfer, laboratories, radiology, surgery, pharmacy, vital signs and medical records, to make informed decisions. Data must also be presented in a way that is meaningful to a particular patient’s care. In other words, if a patient is at risk for developing sepsis, systems need to collect and present clinical indicators specific to that patient’s status in real-time…7

Continuous monitoring from multiple data sources—EKGs, vital signs, laboratory tests—will yield better predictive models than data from a single source. One of the objectives of analytics is to seek interrelationships among seemingly unrelated measurements and sources of data to determine whether these interrelationships can yield the detection of the onset of an adverse event that would not normally be visible by observing a single parameter or multiple parameters individually.

Challenges to overcome include interoperability, standardization, access and development of real-time analytics. However, once these integration and data aggregation gaps are resolved, health systems can “fully maximize EHR investments and align performance with national quality initiatives.”8


Riddle notes, “As the timeline for value-based care marches forward, hospitals and health systems increasingly need access to the wealth of patient data that exists within EHR technology and other clinical systems. Success hinges on the ability of technical infrastructures to work together to unlock critical information and deliver it to clinicians in a meaningful, actionable way.”9

Hospital investments in clinical surveillance and analytics solutions are driven by organizations who are migrating toward value-based care models and are trying to achieve the objectives of value-based care, including improving care quality and outcomes, reducing clinical variation and reducing healthcare costs.10

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.


  1. Office of the National Coordinator for Health Information Technology. Adoption of electronic health record systems among U.S. non-federal acute-care hospitals: 2008-2015. Available at:
  2. Malkary G. Healthcare without bounds: trends in clinical surveillance and analytics. Spyglass Consulting Group. March 2018.
  3. Ibid.
  4. Miriovsky BJ, Shulman LN, Abernethy AP. Importance of electronic health records, and continuously aggregating data to comparative effectiveness research and learning health care. Journal of Clinical Oncology. December 2012. 30(34):4243-4248. Available at:
  5. Malkary G. Healthcare without bounds: trends in clinical surveillance and analytics. Spyglass Consulting Group. March 2018.
  6. Riddle S. Maximizing EHR investments through clinical surveillance. EHR Intelligence. EHR Intelligence. December 4, 2015. Available at:
  7. Ibid.
  8. Ibid.
  9. Ibid.
  10. Malkary G. Healthcare without bounds: trends in clinical surveillance and analytics. Spyglass Consulting Group. March 2018.

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.