Grand challenges in clinical decision support

Abstract

There is a pressing need for high-quality, effective means of designing, developing, presenting, implementing, evaluating, and maintaining all types of clinical decision support capabilities for clinicians, patients and consumers. Using an iterative, consensus-building process we identified a rank-ordered list of the top 10 grand challenges in clinical decision support. This list was created to educate and inspire researchers, developers, funders, and policy-makers. The list of challenges in order of importance that they be solved if patients and organizations are to begin realizing the fullest benefits possible of these systems consists of: improve the human-computer interface; disseminate best practices in CDS design, development, and implementation; summarize patient-level information; prioritize and filter recommendations to the user; create an architecture for sharing executable CDS modules and services; combine recommendations for patients with co-morbidities; prioritize CDS content development and implementation; create internet-accessible clinical decision support repositories; use freetext information to drive clinical decision support; mine large clinical databases to create new CDS. Identification of solutions to these challenges is critical if clinical decision support is to achieve its potential and improve the quality, safety and efficiency of healthcare.

SeDeLo: Using Semantics and Description Logics to Support Aided Clinical Diagnosis

“…The work of many authors supports the evidence that decision support systems can be extremely effective in improving the quality and safety of healthcare (e.g. [3,[7][8][9][10]). The most famous expert systems were built as diagnosis assistants and therapy advisors in different medical areas (MYCIN [11], ONCOCIN [12], etc.)…”

Lessons learned from implementing service-oriented clinical decision support at four sites: A qualitative study

“…(3,11,12) Second, institutions that have developed their own libraries have had considerable difficulty in managing this content and keeping it up-to-date. (11)(12)(13) It has also been difficult to resolve ambiguities in clinical guidelines, and to account for clinical realities such as co-morbidity. (11) Third, a patient's data may be housed at several sites with no complete record of all data 4 available at any one institution.…”

“…Fourth, the evidence-base for the true effectiveness of CDS outside of a limited number of academic universities is limited. (11,12) Finally, there are significant limitations in retrieving data to make inferences: implementing decision support in existing EHR platforms is challenging. (11,12,14) In order to surmount these challenges, better guidelines (15,16) and an improved understanding of EHR workflow and usability are needed.…”

“…(11,12) Finally, there are significant limitations in retrieving data to make inferences: implementing decision support in existing EHR platforms is challenging. (11,12,14) In order to surmount these challenges, better guidelines (15,16) and an improved understanding of EHR workflow and usability are needed. (17) However, another key advance needed to enable wider use of effective CDS is the ability to share actionable CDS content across sites.…”

“…(17) However, another key advance needed to enable wider use of effective CDS is the ability to share actionable CDS content across sites. (11)(12)(13)(14) Past efforts have focused on sharing CDS among institutions with the same EHR vendor using internet-based libraries (18), which limits the scalability of CDS, or moving decision support artifacts from an institution with one EHR to another with a different EHR as structured logic representations. (19)(20)(21) Though numerous standards have been developed to facilitate guideline-sharing, the benefits have been counterbalanced by timeintensive efforts to resolve local terminology issues (e.g., Arden's "curly braces problem") (22), and a lack of consensus about which of the many standards to use.…”