- Mayo Clinic is using a new EHR interface powered by ambient intelligence applications to strip away excess EHR data and deliver meaningful information to clinicians for improved clinical decision-making.
Herasevich, MD, et al. noted that EHR data overload has become a growing problem in fast-paced, complex care settings such as intensive care units (ICUs) and emergency departments. The team sought to develop a way to streamline clinicians’ ability to quickly obtain and utilize only necessary data.
“Individual clinicians may have to sift through more than 50,000 data points to find key information,” wrote the three Mayo Clinic clinicians and professors in Harvard Business Review. “This proliferation of data (both meaningful and meaningless) and the workload created by EHR systems have been key drivers of clinician burnout and, paradoxically, introduced new threats to patient safety.”
The group convened a multidisciplinary team of clinicians, researchers, and clinical informatics experts to test IT tools leveraging ambient intelligence capable of understanding the way clinicians work and the environmental factors that affect patient care delivery. Ambient intelligence denotes a set of decision-making tools that use data analytics and insights about clinician’s goals, work environments, strengths, and performance constraints to deliver needed information in a form clinicians can use quickly and effectively at the point of care.
Researchers identified clinicians with a high cognitive workload who need to filter important information out of a cluttered environment using a NASA Task Load Index. Next, the team conducted 1,500 interviews with Mayo Clinic ICU clinicians nationwide over a two-year period to gain insight into the types of data that are useful in patient care delivery and the types of data that are not.
“With these insights, we identified that out of tens of thousands of pieces of data pouring through EHR, roughly only 60 pieces are crucial patient information that clinicians needed to access quickly and easily for effective care,” wrote researchers.
“This information included both expected data points, such as blood pressure and medications, as well as less obvious but critical information such as cough strength or previous difficulty with endotracheal intubation,” they continued.
The team then built an EHR interface specific to clinicians in the ICU called Ambient Warning and Response Evaluation (AWARE). In 2012, researchers offered AWARE to clinicians at the Mayo Clinic ICU in Rochester, MN. Two years later, researchers introduced the technology to clinicians at its Phoenix and Scottsdale, AZ and Jacksonville, FL campuses.
“A rules-based, ambient-intelligence application, AWARE filters out the meaningless data and delivers context-specific, high-value information to clinicians in real time,” stated researchers. “It contains over 1,000 rules that run continuously through data and enrich it with insights from clinicians and patients. Data is organized around familiar clinical concepts needed for timely and accurate decision making.”
The AWARE EHR interface emphasizes data points such as hemoglobin, platelet, and coagulation factors with color coding to signal differing levels of severity or urgency for corrective intervention. By prioritizing critical information, the EHR display helps clinicians quickly identify ICU patients at risk of severe bleeding complications, as well as other high-risk complications.
AWARE also offers a real-time overview of every ICU in the Mayo Clinic system with visual displays that streamline clinicians’ ability to scan and identify patients in need of urgent intervention.
“Each patient is represented by a square with icons that represent the status of required tests, scans, and procedures,” wrote Mayo Clinic researchers. “It provides a quick picture of overall acuity, and clinicians can drill down into each patient’s data — down to each organ system.”
AWARE also delivers EHR alerts integrated directly into clinician workflows.
“They notify the clinician of potential omissions only if the clinician’s actions do not match the patient condition, minimizing the chance of harmful interruptions,” stated researchers.
The EHR interface includes apps that enable automated ventilator setting surveillance, as well as timely sepsis diagnosis and treatment best practices implementation, among other apps.
The EHR interface saves users between three and five minutes on chart review per patient per day, researchers stated.
“With an average ICU clinician workload of 15 patients per day, the savings mean that more than one hour of additional clinician time can be devoted to patient bedsides, improving often-inadequate shared decision making,” they wrote.
AWARE serves as an example of the importance of incorporating human insights and creativity into health IT development.
“Advancing ambient-intelligence applications and combined human-computer partnerships has the potential to help solve some of our most meaningful and challenging health care problem,” researchers concluded.