Researchers leverage EHR data to reduce alarm fatigue

Hospitals are places where clinicians are typically bombarded with a variety of alarms sounding from medical devices. However, the noise has become a serious distraction for clinicians who are being bombarded daily with thousands of alarms—the vast majority of which are false or not clinically actionable. All that noise is impacting patient safety, critics say.

Not surprisingly, providers have become desensitized to these alarms, a phenomenon known as alarm fatigue. To help address the problem, a 2014 Joint Commission National Patient Safety Goal urged hospitals to prioritize alarm system safety and to develop policies and procedures to manage alarms and alarm fatigue. Yet, progress has been slow.

“There are tens of thousands of alarms that go off every single day at individual hospitals, and providers are expected to triage all of those stimuli on a moment-to-moment basis when they’re trying to care for patients,” says Veena Goel, MD, a pediatric hospitalist for the Palo Alto Medical Foundation and adjunct clinical assistant professor at Stanford Medicine.

Now, a team of researchers has devised an approach for mitigating alarm fatigue for clinicians treating pediatric patients in a hospital setting. It is a particularly complex problem when dealing with children, contends Goel, because hospitalized children’s vital signs vary and change with age.

In their study, Goel and her colleagues set out to create and validate heart and respiratory rate percentiles for hospitalized children, and to analyze the safety of replacing current vital sign reference ranges with proposed data-driven physiologic alarm parameters.

“We took an entire year’s worth of data from our electronic health record and analyzed it to get a sense of what the heart rates and respiratory rates are for children who are in the hospital, acutely sick and across all different ages,” she says.

Specifically, researchers leveraged EHR-documented data for more than 7,000 pediatric patients—including more than 62,000 vital sign measurements—to estimate the performance of new physiologic monitor settings that could be used to modify alarm limits without sacrificing the ability to identify children who are experiencing a serious medical event.

“Our new data-driven alarm parameters for hospitalized children provide a potentially safe means by which to modify physiologic bedside monitor alarm limits, a first step toward customization of alarm limit settings in an effort to mitigate alarm fatigue,” concluded the study published in the Journal of Hospital Medicine.

In fact, researchers found that safety evaluation of data-driven alarm limits suggests they are as safe as those currently used.

“Although these calculated vital sign parameters were not implemented clinically, they called into question reference ranges that are currently widely accepted and used as parameters for electronic health record (EHR) alerts, early warning scoring systems, and physiologic monitor alarms,” states the article.

As an editorial in the same issue of the journal points out, these out-of-range vital signs “often generate alerts in the electronic health record and alarms on physiologic monitors that can disrupt patients’ sleep, generate concern in parents, lead to unnecessary testing and treatment by physicians, interrupt nurses during important patient care tasks, and lead to alarm fatigue.”

The editorial commends Goel and her colleagues for an important contribution to “knowledge about the ranges of expected vital signs in hospitalized children” whose findings “can be immediately used to guide EHR decision support.”

Goel concludes that the findings of the study could also be applied to healthcare settings outside of pediatric hospitals.

“In this era of big data where we have so much technology and are collecting tremendous amounts of information, our work is only one example of using that data to better understand our patient care population,” she adds. “Those lessons learned could be applied to many aspects of healthcare other than pediatrics.”