CDS EHR Integration Boosts Contextualized Care Delivery

The use of clinical decision support (CDS) EHR integration increased the likelihood that a clinician would address relevant patient life context in their care plan, according to a study published in JAMA Network Open.

Researchers performed the randomized clinical trial at the primary care clinics of two academic medical centers.

Patients completed a pre-visit questionnaire that elicited contextual red flags in the clinician’s note template in a contextual care box. The EHR integration also pulled red flags from the medical record, used passive and interruptive alerts, and proposed relevant orders.

While clinician use of the CDS tool did not improve patient outcomes, the EHR integration increased the likelihood that a physician would address relevant patient life context in their care plan.

Previous research shows that contextualized care plans are more likely to result in improved prospectively defined patient outcomes.

“Just as CDS can guide biomedically focused decision-making by drawing on data from evidence-based guidelines, it can also guide contextually informed decision-making by drawing on data specific to the life circumstances and behaviors of individual patients,” the study authors wrote.

“Contextualized CDS can serve as a corrective to biomedical bias in which clinicians prioritize biomedical information over contextual information, even when they have comparable implications for a patient’s clinical state,” they continued.

For instance, previous research has documented examples of the value of contextualized CDS.

In one study, a patient had three unnecessary visits to the emergency department with acute illness because she missed her hemodialysis, and no one asked her why. It turned out that she was trapped in a situation beyond her control and a social worker was able to resolve the problem easily.

The study has some limitations. Although the disposition of some red flags, such as the number of missed appointments, could be coded objectively, other outcomes, such as a patient’s report of whether they are exercising more, are subjective.

Since coders were blinded as to the study group, so this limitation should not skew the results. However, it was impossible to blind clinicians to study group because they could tell when they received contextualized CDS.

“It is possible that clinicians try harder in the intervention, independent of the CDS,” the researchers explained. “We attempted to mitigate any effect by explaining to clinicians that there would be no analysis of how they individually perform.”

Additionally, the real effect of the intervention may be larger than what the researchers found because patients in both study groups completed the questionnaire, which may have primed those in the control group to raise contextual red flags and factors.

“We designed the study this way so we would not attribute impact to the CDS that was really from the questionnaire,” the authors wrote.