Translating an evidence-based clinical pathway into shareable CDS: developing a systematic process using publicly available tools

Michel, Jeremy J.; Flores, Emilia J.; Dutcher, Lauren; Mull, Nikhil K.; Tsou, Amy Y.

doi:10.1093/jamia/ocaa257

Cited by 4 publications

(6 citation statements)

References 26 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Other studies have noted that adopters of standards-based CDS take steps to review CDS logic expressions prior to implementing them independently. 1 28 A collaborative development process that includes guideline developers, standards development experts, patients, 34 and CDS developers can reassure patient and clinician users that CDS artifacts are vetted. CDC's Adapting Clinical Guidelines for the Digital Age Initiative and AHRQ's CDS Connect project have examples of a collaborative translation process that includes input from guideline developers and clinical experts.…”

Section: Discussionmentioning

confidence: 99%

“…Clinical decision support (CDS) facilitates value-based care by increasing adherence to evidence-based practices and supporting patient-centered decision-making. 1 2 CDS uses targeted clinical knowledge and patient health information, can be computerized or not, and can provide patient-specific clinical care recommendations or evidence-based guidance to clinicians or directly to patients. 3 4 Promoting CDS use is, therefore, in the public interest.…”

Section: Background and Significancementioning

confidence: 99%

See 1 more Smart Citation

Lessons Learned from a National Initiative Promoting Publicly Available Standards-Based Clinical Decision Support

et al. 2023

View full text Add to dashboard Cite

Background Clinical decision support (CDS), which provides tools to assist clinical decision-making, can improve adherence to evidence-based practices, prevent medical errors, and support high-quality and patient-centered care delivery. Publicly available CDS that uses standards to express clinical logic (i.e., standards-based CDS) has the potential to reduce duplicative efforts of translating the same clinical evidence into CDS across multiple health care institutions. Yet development of such CDS is relatively new and its potential only partially explored. Objectives This study aimed to describe lessons learned from a national initiative promoting publicly available, standards-based CDS resources, discuss challenges, and report suggestions for improvement. Methods Findings were drawn from an evaluation of the Agency for Healthcare Research and Quality Patient-Centered Outcomes Research CDS Initiative, which aimed to advance evidence into practice through standards-based and publicly available CDS. Methods included literature and program material reviews, key informant interviews, and a web-based survey about a public repository of CDS artifacts and tools for authoring standards-based CDS. Results The evaluation identified important lessons for developing and implementing standards-based CDS through publicly available repositories such as CDS Connect. Trust is a critical factor in uptake and can be bolstered through transparent information on underlying evidence, collaboration with experts, and feedback loops between users and developers to support continuous improvement. Additionally, while adoption of standards among electronic health record developers will make it easier to implement standards-based CDS, lower-resourced health systems will need extra support to ensure successful implementation and use. Finally, although we found the resources developed by the Initiative to offer valuable prototypes for the field, health systems desire more information about patient-centered, clinical, and cost-related outcomes to help them justify the investment required to implement standards-based, publicly available CDS. Conclusion While the standards and technology to publicly share standards-based CDS have increased, broad dissemination and implementation remain challenging.

show abstract

Section: Discussionmentioning

confidence: 99%

Section: Background and Significancementioning

confidence: 99%

Lessons Learned from a National Initiative Promoting Publicly Available Standards-Based Clinical Decision Support

et al. 2023

View full text Add to dashboard Cite

show abstract

“…For the special case of cardiovascular ICU patients who mostly attribute higher complication rates and longer ICU stays (3,4), it becomes even more challenging for the medical staff to spot certain complications or symptoms of patients. Considering the promising impact of artificial intelligence (AI) for clinical decision support (CDS) (5,6), implementing AI into the cardiovascular ICUs could help minimize the number of medical errors by being able to guide the clinician to the correct diagnosis and ultimately to an appropriate therapy.…”

Section: Introductionmentioning

confidence: 99%

Artificial intelligence for clinical decision support for monitoring patients in cardiovascular ICUs: A systematic review

Moazemi

Vahdati

et al. 2023

Front. Med.

View full text Add to dashboard Cite

BackgroundArtificial intelligence (AI) and machine learning (ML) models continue to evolve the clinical decision support systems (CDSS). However, challenges arise when it comes to the integration of AI/ML into clinical scenarios. In this systematic review, we followed the Preferred Reporting Items for Systematic reviews and Meta-Analyses (PRISMA), the population, intervention, comparator, outcome, and study design (PICOS), and the medical AI life cycle guidelines to investigate studies and tools which address AI/ML-based approaches towards clinical decision support (CDS) for monitoring cardiovascular patients in intensive care units (ICUs). We further discuss recent advances, pitfalls, and future perspectives towards effective integration of AI into routine practices as were identified and elaborated over an extensive selection process for state-of-the-art manuscripts.MethodsStudies with available English full text from PubMed and Google Scholar in the period from January 2018 to August 2022 were considered. The manuscripts were fetched through a combination of the search keywords including AI, ML, reinforcement learning (RL), deep learning, clinical decision support, and cardiovascular critical care and patients monitoring. The manuscripts were analyzed and filtered based on qualitative and quantitative criteria such as target population, proper study design, cross-validation, and risk of bias.ResultsMore than 100 queries over two medical search engines and subjective literature research were developed which identified 89 studies. After extensive assessments of the studies both technically and medically, 21 studies were selected for the final qualitative assessment.DiscussionClinical time series and electronic health records (EHR) data were the most common input modalities, while methods such as gradient boosting, recurrent neural networks (RNNs) and RL were mostly used for the analysis. Seventy-five percent of the selected papers lacked validation against external datasets highlighting the generalizability issue. Also, interpretability of the AI decisions was identified as a central issue towards effective integration of AI in healthcare.

show abstract

Section: Introductionmentioning

confidence: 99%

“…There are a number of efforts to provide structured eligibility criteria in a computable expression language (E4), such as Clinical Quality Language (CQL), and either convert eligibility criteria to this expression language (E1-E3-E4) using natural language processing (NLP) 5,6 or developing authoring tools to facilitate subject matter experts directly expressing their eligibility criteria in the expression language (such as the CDS Authoring Tool). [7][8][9] However, there are relatively few execution engines (EP5) that are able to evaluate CQL queries. 10 Efforts to extract patient data in FHIR to convert to other formats for execution engines not using CQL (eg, the P1-P3-P4 pathway for creating research datasets) require an uncommon level of technical expertise and are difficult to apply for real-time decision support.…”

mentioning

confidence: 99%

Striking a match between FHIR‐based patient data and FHIR‐based eligibility criteria

Alper¹,

Dehnbostel²,

Shahin³

et al. 2023

Learning Health Systems

View full text Add to dashboard Cite

Inputs and OutputsThe Strike‐a‐Match Function, written in JavaScript version ES6+, accepts the input of two datasets (one dataset defining eligibility criteria for research studies or clinical decision support, and one dataset defining characteristics for an individual patient). It returns an output signaling whether the patient characteristics are a match for the eligibility criteria.PurposeUltimately, such a system will play a “matchmaker” role in facilitating point‐of‐care recognition of patient‐specific clinical decision support.SpecificationsThe eligibility criteria are defined in HL7 FHIR (version R5) EvidenceVariable Resource JSON structure. The patient characteristics are provided in an FHIR Bundle Resource JSON including one Patient Resource and one or more Observation and Condition Resources which could be obtained from the patient's electronic health record.ApplicationThe Strike‐a‐Match Function determines whether or not the patient is a match to the eligibility criteria and an Eligibility Criteria Matching Software Demonstration interface provides a human‐readable display of matching results by criteria for the clinician or patient to consider. This is the first software application, serving as proof of principle, that compares patient characteristics and eligibility criteria with all data exchanged using HL7 FHIR JSON. An Eligibility Criteria Matching Software Library at https://fevir.net/110192 provides a method for sharing functions using the same information model.

show abstract

Translating an evidence-based clinical pathway into shareable CDS: developing a systematic process using publicly available tools

Cited by 4 publications

References 26 publications

Lessons Learned from a National Initiative Promoting Publicly Available Standards-Based Clinical Decision Support

Lessons Learned from a National Initiative Promoting Publicly Available Standards-Based Clinical Decision Support

Artificial intelligence for clinical decision support for monitoring patients in cardiovascular ICUs: A systematic review

Striking a match between FHIR‐based patient data and FHIR‐based eligibility criteria

Contact Info

Product

Resources

About