Clinical Decision Support: Why the Right Data is Needed to Drive the Right Outcomes

Estimates show doctors can make more than 150 real-time decisions that impact patient care in an average day – everything from ordering tests and prescribing medication, to recommending procedures and admitting patients to the hospital.

Even with extensive education and vast experience, medical decision-making is challenging given the quantity of data and volume of evidence that exists. An Institute of Medicine study in 2000 titled To Err is Human: Building a Safer Health System put a spotlight on the issue of errors in clinical decision-making, revealing the morbidity and mortality associated with such errors.

Much has changed in the two decades since that study was published. In 2010, the Affordable Care Act (ACA) focused the healthcare market on moving to a model that values outcomes instead of focusing on transactional encounters that have historically driven payments. The ACA also dramatically accelerated the digitization of medical records, with a recent survey showing that more than 89% of physicians currently use an electronic health record (EHR) system.

Designed to take into account all of the data available in an EHR, clinical decision support systems (CDSS) – which have also been around for several decades – have now matured to a point where the data and insights they provide are aiding providers in delivering the right care to the right patient at the right time. Driven in part by the 21st Century Cures Act enabling interoperability in health IT, CDSS can reach its full potential of helping practitioners adhere to guidelines, while further improving patient safety, as well as the quality, efficiency and effectiveness of healthcare.

The Evolution of Clinical Decision Support Systems

Today’s providers are faced with an onslaught of data about each patient – from traditional diagnostic labs and imaging studies to expert interpretations in clinical notes and biometric data captures from patients in the home. Advanced CDSS are designed to take in all of these data sources, analyze the inputs, and present insights to providers to inform decision-making. The insights derived are intelligently curated by the CDSS and presented at the right time in the clinical workflow – often at the point of care – to enhance patient care and outcomes.

For example, CDSS can identify divergence from standard of care treatment, such as prescribing a medication class shown to have superior benefit for a specific patient cohort, and provide recommendations for clinicians to consider. The systems can also offer computerized alerts and reminders to both patients and providers, with condition and context-specific diagnostic recommendations or expert assessment needs, while highlighting both the patient characteristics driving the notification and the reference data behind the recommendation.

To date, CDSS have typically been deployed through EHR solutions, but challenges arise when software systems primarily designed as databases and billing systems are stretched to become clinical workflow optimization engines. One problem in particular is alert fatigue. Providers can receive so many alerts from their various systems, including low-value ones that do not enhance care, which wastes valuable time and contributes to the burnout they’re already experiencing.

Without regular maintenance, review, iteration and optimization programs, clinical decision support also has the potential to become outdated or malfunction. Such challenges often fall on the in-house EHR IT team to build and maintain these systems so that these decision support tools better live up to user experience expectations.

Improving the Experience with Clinical Decision Support Systems

Despite current challenges, providers do see the promise in CDSS. Done right, CDSS can:

• Improve the quality of care and deliver on the goal of enhancing health outcomes
• Drive greater efficiency in care delivery
• Help providers avoid errors and adverse effects
• Improve patient and provider satisfaction

CDSS play an important role in addressing the information overload that providers face, offering a platform to integrate evidence-based knowledge into the care delivery process, and automating many of the mundane tasks that take away from the precious time they can spend with patients. For example, they can improve on existing workflows with better retrieval and presentation of data than EHRs. In addition, CDSS can improve the quality of clinical documentation by providing support for coding, ordering of procedures and tests, and patient triage.

It’s important to remember, however, that one size does not fit all when it comes to CDSS. Practices can be limited if clinical decision support is simply a function of an EHR. Instead, providers must consider how solutions fit into their entire existing workflow to prevent friction and ensure that the CDSS can accommodate the unique needs of each client environment, patient population and practice patterns.

To overcome traditional barriers and deliver on the full promise of clinical decision support, practices should consider cloud-based composable platforms that bring leverage advancements in interoperability – such as SMART on FHIR and CDS Hooks – to enable a more flexible, configurable approach to CDSS. By layering the CDSS engine and experience on top of the EHR, it affords the opportunity to include additional data sources such as remote patient monitoring and patient reported outcomes into the model.

Integrating this flexible platform with existing EHRs will enable providers to close gaps in care according to evidence-based guidelines, identify the right level of intervention and make practices more efficient as their clinical workflows evolve.

Lucienne Marie Ide, M.D., PH.D., is the founder and CEO of Rimidi, a leading clinical management platform designed to optimize clinical workflows, enhance patient experiences and achieve quality objectives.