How effective are clinical decision support systems?

Journal ArticleIn a recent editorial in BMJ, Urmimala Sarkar, MD and Samal Lipika, MD recommend a change in approach after reviewing a meta-analysis (doi:10.1136/bmj.m3216) by Kwan and colleagues of 122 trials of clinical decision support systems embedded in electronic health records.  Kwan and colleagues analysis showed modest improvements in care processes overall, and no significant improvement in clinical outcomes in the subset of 30 trials that included them. 

Sarkar and Lipika write the lack of efficacy likely reflects the challenges of developing innovative, safe, and effective clinical decision support systems within commercial electronic health record platforms.  

This study still has important implications. First, the premise that clinical decision support systems alone will improve clinical care should be re-examined. In the outpatient setting, where most of the included trials occurred, there are many substantial barriers to providing guideline recommended care.  Clinical decision support systems should be considered only one part of an integrated approach to closing quality gaps in medical care, rather than a stand-alone solution. 
The authors recommend a multifaceted strategy to enhance the effectiveness of clinical decision support systems in practice. First, vendors should remove barriers to creating, implementing, and sharing clinical decision support systems approaches that can be integrated within electronic health records so that the most usable, feasible, and effective solutions can be identified and scaled up. “At this point the incentives for vendors to integrate these changes is that it’s the right thing to do,” said Sarkar.

Second, the design should arise from a collaborative, multidisciplinary, understanding of clinician and team workflows, informed by human factors engineering. Third, implementation of decision support systems must occur alongside co-interventions to influence clinicians’ behavior. Strategies such as clinician education and training and behavioral “nudges” such as default orders for recommended care options should be tested during implementation. 

“If decision support were more effective, it could close some gaps in care,” said Sarkar, “like making sure people get needed preventive care (vaccines, cancer screening), and monitoring or follow-up - like laboratory testing needed for long-term medications or recommended follow-up of abnormal results.”

Fourth, further research is needed to integrate decision support systems with patient engagement strategies ranging from education and shared-decision-making aids to self-scheduling. Fifth, these systems can and should evolve, using machine learning and artificial intelligence, to develop tailored and relevant decision support that minimize alert fatigue. 

Finally, Sarkar and Lipika agree with Kwan and colleagues that evaluation of clinical decision support systems should include context specific implementation measurements, such as the number of dismissed alerts, the time required to address recommendations, and clinician satisfaction. 

Clinical decision support systems will continue to be an area of innovation and research, and we will only realize their true potential to improve healthcare and patient outcomes if we learn what does not work, as well as looking for what does. 

Urmimala SarkarUrmimala Sarkar, MD, MPH

Urmimala Sarkar MD, MPH is professor of medicine in the Division of General Internal Medicine, Associate Director of the UCSF Center for Vulnerable Populations, PRL-IHPS associated faculty and a primary care physician at Zuckerberg San Francisco General Hospital’s Richard H. Fine People's Clinic. Her work centers on innovating for health equity, to improve the safety and quality of outpatient care for everyone, especially low-income and diverse populations. In addition to her grant-funded research, Dr. Sarkar engages with a range of digital health stakeholders to advocate for tools and approaches that are inclusive of, and effective for, diverse patient populations. 

How effective are clinical decision support systems?
Sarkar U, Samal L.BMJ. 2020 Sep 17;370:m3499. doi: 10.1136/bmj.m3499.