How do clinical decision support systems work?
At its core, clinical decision support is about helping clinicians and the patients they care for, says Saif Khairat, associate professor of health informatics and health services research at the University of North Carolina at Chapel Hill. The most common uses for decision support are medical diagnosis, care alerts and reminders, medication management, and chronic disease management.
“It is a health informatics solution that provides clinicians or patients with person-specific information and intelligence to offer timely recommendations that improve care outcomes and reduce medical or medication errors,” he said.
Broadly speaking, clinical decision support systems are categorized as knowledge-based or not.
Knowledge-based systems rely on a series of rules, written as if-then statements, to examine patient data (the input to the system) and generate a recommended action (the output). These comprise the majority of clinical decision support systems — and rule transparency helps drive adoption, says Phillips: “Clinical teams understand the data that’s coming in and the rules that drive the alerts.”
Non-knowledge based systems also evaluate data, but these systems use artificial intelligence algorithms or statistical pattern recognition to generate recommendations. These systems are less widespread; as Pew Research points out, they are subject to strict US Food and Drug Administration regulatory requirements for medical products that use AI to guide medical decision-making.
RELATED: Find out how AI is helping healthcare organizations reduce preventable patient harm.
How are clinical decision support systems used?
One of the first clinical decision support systems ever developed, known as MYCIN, was a rules-based diagnostic tool developed in the early 1970s. As described in the British Columbia Medical Journal, doctors manually entered patient data, from medical history and vital signs to lab results, and MYCIN compared the data against approximately 600 rules for diagnosing an infectious disease and recommending the correct antibiotic. MYCIN was used for research at Stanford Medical School but never made it into clinical practice, in part because it took over 30 minutes to enter patient data.
Today’s tools are capable of collecting and analyzing real-time data, with use cases and benefits in a variety of care settings.
For Home Careclinical decision support systems can provide “instant notification” based on medication adherence or vital signs data collected from remote monitoring devices, Phillips says.
In first aid, clinics can use decision support tools to facilitate conversations and interventions in areas such as cardiovascular disease prevention. Here, doctors can receive reminders to screen for common risk factors, log cases of high cholesterol or high blood pressure, recommend lifestyle changes, and discuss medications or other treatment protocols.
For general care Within the hospital, clinical teams can monitor a patient recovering from surgery for, for example, their reaction to painkillers. Or, upon discharge, nurses may receive an alert that a patient is at high risk for hospital readmission due to certain clinical or non-clinical factors; this may result in additional interventions or referrals for follow-up care before a patient is discharged home.
In intensive care, where patients are under continuous monitoring, clinical decision support systems are implemented to identify changes in heart rate or breathing that may signal a sudden change in a patient’s condition. “Patients depend on technology for their survival. There are many devices that take care of the patient,” says Phillips. “To give frontline caregivers more effective guidance, we’re using technology to help them identify deteriorating patients.”
Clinical decision support is of greatest value in high-acuity settings, when clinical staff need to make decisions quickly, Khairat says. But it can come at a cost. Phillips notes that the average ICU patient generates 350 alarms over a 24-hour period, while research by Khariat and colleagues found that most ICU physicians experience alert or alarm fatigue in 22 minutes after using the EMR system.
“We need to create more insightful notifications to reduce alarm fatigue,” Phillips says. “We need to transparently send alerts to end users how they want to be notified.”
Click on the banner below to discover the main health technology trends for 2022.