Apr 01 2022
Data Analytics

How Clinical Decision Support Systems Improve Outcomes

CDSSs help care teams make more informed care decisions with evidence-based recommendations, especially when time is of the essence.

Clinical decision support systems have come a long way from their early implementations in the 1970s. As stand-alone systems that were expensive to build and difficult to use — and given the legal and ethical resistance at the time to using computers to practice medicine — CDSSs tended to be restricted to “academic pursuits,” as a Nature article put it.

Decades later, these systems integrate with other clinical applications, run in browsers or on mobile devices, and support clinical teams in a variety of care settings, from the intensive care unit to primary care.

Two trends have pushed the industry to adopt clinical decision support, says Kevin Phillips, vice president of product management for Philips Capsule. One is near-universal adoption of electronic medical records and computerized physician order entry systems. The other is the push in the 21st Century Cures Act and the Interoperability and Patient Access Final Rule to make it easier to extract data from clinical systems

“The deployment of technology has raised awareness of the value of data in healthcare,” Phillips says. “Getting data from the EMR system as well as FDA-approved medical devices to develop decision support rules has never been easier.”

Click the banner below for access to exclusive HealthTech content and a customized experience.

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, an 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’s a health IT solution that provides clinicians or patients with person-specific information and intelligence to offer recommendations in a timely fashion that improve care outcomes and reduce medical or medication errors,” he says.

Broadly speaking, clinical decision support systems are classified as either knowledge-based or non-knowledge-based.

Knowledge-based systems rely on a series of rules, written as if-then statements, to look at the patient data (the system’s input) and generate a recommended action (the output). These comprise the majority of clinical decision support systems — and the transparency of rules helps to drive adoption, Phillips says: “Clinical teams understand the data that’s going in and the rules that are generating 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 regulatory requirements from the U.S. Food and Drug Administration for medical products that use AI to drive medical decision-making.

RELATED: Learn how AI helps healthcare organizations reduce avoidable 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, physicians would manually enter patient data, from medical history and vital signs to lab results, and MYCIN would run the data against approximately 600 rules to diagnose an infectious disease and recommend the right antibiotic. MYCIN was used for research at Stanford Medical School but never made it into clinical practice, in part because it took more than 30 minutes to enter patient data.

Today’s tools are able to collect and analyze data in real time, with use cases and benefits in a variety of care settings.

For care at home, clinical decision support systems can provide a “tap-on-the-shoulder notification” based on data about medication adherence or vital signs gathered from remote monitoring devices, Phillips says.

In primary care, clinics may use decision support tools to facilitate conversations and interventions in areas such as cardiovascular disease prevention. Here, physicians may receive reminders to screen for common risk factors, log cases of high cholesterol or high blood pressure, recommend lifestyle changes, and discuss medication or other treatment protocols.

For general care within the hospital, clinical teams may monitor a patient recovering from surgery for, say, their reaction to pain medication. Or, at discharge, nursing staff may receive an alert that a patient is a high risk for hospital readmission based on certain clinical or nonclinical factors; this may prompt additional interventions or referrals for follow-up care before a patient is sent home.

In intensive care, where patients are under continuous monitoring, clinical decision support systems are set up to identify changes in heartbeat or breathing that may signal a sudden change in a patient’s condition. “Patients depend on technology for their survival. There are a lot of devices caring for the patient,” Phillips says. “To give frontline caregivers more efficient guidance, we use technology to help them identify which patients are deteriorating.”

Clinical decision support is of greater value in high-acuity settings, when clinical staff must make decisions quickly, Khairat says. But this can come at a cost. Phillips notes that the average patient in the ICU generates 350 alarms over a 24-hour period, while research from Khariat and his colleagues concluded that most ICU physicians experience alert or alarm fatigue within just 22 minutes of using the EMR system.

“We have to create more insightful notifications to reduce alarm fatigue,” Phillips says. “We have to send alerts seamlessly to end users in the way they want to be notified.”

Click the banner below to discover the top health tech trends for 2022.

Off-the-Shelf vs. Custom-Built Clinical Decision Support Systems

For most hospitals and health systems, acquiring the high-compute and high-throughput resources necessary to run clinical decision support systems tends not to be an issue, Khariat says. “They invest a lot in infrastructure and computing power and storage already.”

The bigger question is how to get started. Homegrown solutions are not uncommon in health systems that want to begin by automating a small number of manual processes. One example is the early warning score. Using seven vital signs, inpatient care teams can identify patients at risk of deterioration during a hospital stay and in need of further intervention. Here, a plug-in assessing EMR data can calculate a score and provide alerts.

On the other hand, there are two scenarios where organizations will want to explore off-the-shelf solutions, Phillips says. One is when decision support increasingly relies on livestreaming data from medical devices that are subject to FDA regulation. The other is when systems aim to provide decision support within a range of clinical workflows.

RELATED: Find out how sharpening clinical communication strategies enables better care.

“There’s a benefit to using technology that’s been validated for specific use cases,” he says. “This helps systems scale the insights they want to deliver to their frontline care teams.”

Health systems also have to decide whether to deploy a clinical decision support system on-premises or in the cloud. Here, preferences may vary. For a hospital that’s already hosting its EMR in the cloud and has invested in network redundancy and security infrastructure, running decision support in the cloud doesn’t come with a steep learning curve or additional costs. On the other hand, systems that expect to experience prolonged internet outages — due to bad weather, for example — may opt to keep decision support on-premises.

6 Elements of Successful Clinical Decision Support Systems

According to Phillips, there are five elements of decision support:

  • Access to data from various clinical applications and medical devices
  • A platform for deploying decision support rules, preferably configurable to the end user
  • Seamless connection between the clinical decision support system and the end user for real-time alerts
  • The ability to look at key performance indicators, as metrics such as adverse events, care escalations, patient length of stay, or the number of alarms nurses receive at a time can illustrate where decision support is working or may need improvement
  • A documented process for migrating from manual workflows to the most progressive decision support use cases

Khariat mentioned an additional important element: clinician engagement. This must occur long before system implementation, he says. Ideally, engagement begins at the design phase and continues through the process of choosing an off-the-shelf product.

“That will increase the likelihood that a tool is used,” he says. “If you get buy-in from clinicians, you’ll get better outcomes. It’s worth taking the extra step.”

metamorworks/Getty Images

Become an Insider

Unlock white papers, personalized recommendations and other premium content for an in-depth look at evolving IT