Grand challenges and opportunities for patient-centered CDS
Dr. Prashila Dullabh is vice president and senior fellow at NORC at the University of Chicago, and Director of NORC’s Health Implementation Science Center. She serves as the Principal Investigator of the Clinical Decision Support Innovation Collaborative Project.
She co-authored this article with Dean Sittig, NORC senior fellow and professor of biomedical informatics at the University of Texas Health Sciences Center and a co-investigator of the CDSiC Project; Dr. David Lobach, vice president of health informatics research at Elimu Informatics and a co-investigator of the CDSiC Project; James Swiger, health scientist administrator in the division of digital healthcare research in the Center for Evidence and Practice Improvement at the Agency for Healthcare Research and Quality; and Dr. Edwin Lomotan, chief of clinical informatics for the Division of Digital Healthcare Research in the Center for Evidence and Practice Improvement at AHRQ.
Providing patient-centered, equitable and evidence-based health care is increasingly recognized as a goal the U.S. healthcare system needs to aspire to and is working towards. Thanks in part to the Department of Health and Human Services, Agency of Healthcare Research and Quality’s efforts, the US healthcare system is transitioning towards being able to provide patients, caregivers and their care teams access to evidence-based recommendations to guide clinical decision-making that incorporates patient needs and preferences.
Since 2016, AHRQ has funded a series of projects focused on defining, refining and improving the uptake of patient-centered outcomes research through technology-enabled clinical decision support tools.
In this Viewpoint we encapsulate the challenges and opportunities facing patient-centered CDS, or PC CDS, by highlighting key findings from the Journal of the American Medical Informatics Association: Challenges and Opportunities for Advancing Patient-Centered Clinical Decision Support: Findings from a Horizon Scan. 
What is patient-centered clinical decision support?
Traditional CDS encompasses digital tools that provide timely information, usually at the point of care, to help clinicians make informed decisions about a patient’s care. Whereas traditional CDS is clinician-facing, PC CDS is patient-facing and the two can be complementary. PC CDS offers new ways to incorporate patient, caregiver and family perspectives into evidence-based care facilitated by digital tools.
PC CDS incorporates patient-provided information – such as data from medical devices, wearables and patient-reported outcome surveys, as well as social determinants of health and patient preference data – directly in the office, home, or other community-based setting. PC CDS also supports patients and providers to engage in a process of shared decision-making that takes into account patient needs and preferences.
The recent COVID-19 pandemic has provided a natural testbed for identifying novel ways that digital tools and technologies, geared toward patients and caregivers, can support patient-centered care.
COVID-19 remote monitoring apps that collect and use patient-reported data (e.g., oxygen saturation, respiratory rate, temperature) to help clinicians manage patient care recommendations are examples of new PC CDS tools. To ensure we have a supportive digital ecosystem to fully realize the benefits of PC CDS, however, we must confront some key challenges.
Key challenges facing PC CDS moving forward
1. Establishing trust and transparency in PC CDS. Putting patients at the center of PC CDS will increase the usefulness of PC CDS tools for both patients and providers. This requires establishing trust. Before they will consistently participate in making PC CDS tools fully functional, patients and providers must trust the underlying research and the prioritization of evidence included in PC CDS tools.
Providers can further benefit from understanding how the evidence used in PC CDS can inform their discussions with patients. Ensuring that health apps and other PC CDS tools meet certain safety and quality criteria will also increase patient and provider confidence in the reliability and validity of these tools, particularly when the apps involve decision-making support.
Finally, patients and providers need assurances that PC CDS tools are regularly updated as evidence changes. Bringing greater transparency to how PC CDS is developed from clinical guidelines can only increase PC CDS adoption and use.
2. Including patient input in all phases of PC CDS development. Understanding the needs, desires, expectations and strengths of the patient is, by definition, crucial to PC CDS development. But achieving this understanding requires patient engagement that is meaningful and sustainable. We must prioritize patient involvement and meaningful patient input throughout the PC CDS development lifecycle – incorporating patient preferences deliberately and in multiple ways.
Patient involvement early, at the research phase, ensures that evidence-based guidelines derived from the research are truly patient-centered and that those guidelines are understood and prioritized in a way that maximizes patient participation in PC CDS. Currently, PC CDS design does not account for the different decision-making processes of patients and providers.
Better understanding of the literature on individual and shared decision-making processes will enable PC CDS developers to target interventions to foster SDM and accurately reflect patients’ goals and preferences. Industry-wide principles and guidelines for safe and effective ways to deliver patient-facing PC CDS that matches patients’ life flow also are needed. We must engage in co-design activities with patients to develop designs that provide the right information at the right time in the right format to ensure patient engagement.
3. Developing technical standards for PC CDS tools. A range of technical standards are necessary to advance PC CDS, spanning semantic (i.e., data content) and syntactic (i.e., exchange standards) interoperability requirements. Currently technical limitations of PC CDS include lack of standards for representing and sharing knowledge, standards for exchanging device/wearable data and standards for capturing patient preferences.
Furthermore, ‘true’ integration of patient-generated health data into electronic health records limits PC CDS tools from being as patient-centered as possible. A critical component of PC CDS is ensuring that guidance is triggered at the appropriate times in the clinician and patient workflows. While specialized, standards-based application program interfaces such as CDS Hooks do exist, EHR developer support and implementation of these standards remain highly variable. We have seen advances in technical standards, but considerable work remains.
4. Improving measures and methods for monitoring PC CDS tools. To ensure PC CDS interventions measurably improve clinician and patient decision-making and health outcomes, we need to accurately measure and monitor the performance of the various forms of PC CDS. Measurement efforts to date have focused largely on assessing PC CDS feasibility and acceptability.
Progress has been made in measuring the “success” of PC CDS in studies that measure knowledge acquisition, patient activation, patient satisfaction and quality of life. But there is a dearth of evidence on what forms of PC CDS work best for different clinical conditions and patient preferences. Relatedly, to inform substantive and targeted evaluations of PC CDS, we need more comprehensive outcome measures that are important to patients.
Addressing the challenges
In September 2021, AHRQ funded the Clinical Decision Support Innovation Collaborative (CDSiC). The CDSiC aims to advance the design, development, dissemination, implementation, use, measurement and evaluation of PC CDS. The CDSiC will support four workgroups focused on scaling and measurement, outcomes, trust and patient-centeredness and standards and regulatory frameworks.
The workgroups will develop tools and products that help address some of the salient challenges of PC CDS by providing guidance and recommendations related to:
- Increasing source credibility of PC CDS
- Incorporating patient-centered inputs into PC CDS and engaging patients in PC CDS co-design
- Addressing gaps in existing PC CDS standards and regulatory frameworks
- Identifying outcome measures and approaches for measuring the effects of PC CDS
The CDSiC Innovation Center will also conduct real-world implementation and research projects to advance standards-based PC CDS. To accomplish its goals, the CDSiC will draw on the expertise of a wide range of stakeholders – including patients, clinicians, researchers, health information technology (health IT) and CDS developers, informaticians, payers and policymakers. The CDSiC gives the field a unique opportunity to tackle the cross-cutting PC CDS technical challenges.
 The JAMIA article is based on an AHRQ-funded horizon scan to explore the current state of PC CDS and to identify future directions for research and development. The scan included a comprehensive literature review, input from a 22-member expert panel and 18 key informant discussions.