ABSTRACT
In an effort to expedite the publication of articles, AJHP is posting manuscripts online as soon as possible after acceptance. Accepted manuscripts have been peer-reviewed and copyedited, but are posted online before technical formatting and author proofing. These manuscripts are not the final version of record and will be replaced with the final article (formatted per AJHP style and proofed by the authors) at a later time.
ABSTRACT
Objective: Common data models provide a standard means of describing data for artificial intelligence (AI) applications, but this process has never been undertaken for medications used in the intensive care unit (ICU). We sought to develop a common data model (CDM) for ICU medications to standardize the medication features needed to support future ICU AI efforts. Materials and Methods: A 9-member, multi-professional team of ICU clinicians and AI experts conducted a 5-round modified Delphi process employing conference calls, web-based communication, and electronic surveys to define the most important medication features for AI efforts. Candidate ICU medication features were generated through group discussion and then independently scored by each team member based on relevance to ICU clinical decision-making and feasibility for collection and coding. A key consideration was to ensure the final ontology both distinguished unique medications and met Findable, Accessible, Interoperable, and Reusable (FAIR) guiding principles. Results: Using a list of 889 ICU medications, the team initially generated 106 different medication features, and 71 were ranked as being core features for the CDM. Through this process, 106 medication features were assigned to 2 key feature domains: drug product-related (n = 43) and clinical practice-related (n = 63). Each feature included a standardized definition and suggested response values housed in the electronic data library. This CDM for ICU medications is available online. Conclusion: The CDM for ICU medications represents an important first step for the research community focused on exploring how AI can improve patient outcomes and will require ongoing engagement and refinement.
ABSTRACT
OBJECTIVES: To summarize the effectiveness of implementation strategies for ICU execution of recommendations from the 2013 Pain, Agitation/Sedation, Delirium (PAD) or 2018 PAD, Immobility, Sleep Disruption (PADIS) guidelines. DATA SOURCES: PubMed, CINAHL, Scopus, and Web of Science were searched from January 2012 to August 2023. The protocol was registered with PROSPERO (CRD42020175268). STUDY SELECTION: Articles were included if: 1) design was randomized or cohort, 2) adult population evaluated, 3) employed recommendations from greater than or equal to two PAD/PADIS domains, and 4) evaluated greater than or equal to 1 of the following outcome(s): short-term mortality, delirium occurrence, mechanical ventilation (MV) duration, or ICU length of stay (LOS). DATA EXTRACTION: Two authors independently reviewed articles for eligibility, number of PAD/PADIS domains, quality according to National Heart, Lung, and Blood Institute assessment tools, implementation strategy use (including Assess, prevent, and manage pain; Both SAT and SBT; Choice of analgesia and sedation; Delirium: assess, prevent, and manage; Early mobility and exercise; Family engagement and empowerment [ABCDEF] bundle) by Cochrane Effective Practice and Organization of Care (EPOC) category, and clinical outcomes. Certainty of evidence was assessed using Grading of Recommendations Assessment, Development, and Evaluation. DATA SYNTHESIS: Among the 25 of 243 (10.3%) full-text articles included ( n = 23,215 patients), risk of bias was high in 13 (52%). Most studies were cohort ( n = 22, 88%). A median of 5 (interquartile range [IQR] 4-7) EPOC strategies were used to implement recommendations from two (IQR 2-3) PAD/PADIS domains. Cohort and randomized studies were pooled separately. In the cohort studies, use of EPOC strategies was not associated with a change in mortality (risk ratio [RR] 1.01; 95% CI, 0.9-1.12), or delirium (RR 0.92; 95% CI, 0.82-1.03), but was associated with a reduction in MV duration (weighted mean difference [WMD] -0.84 d; 95% CI, -1.25 to -0.43) and ICU LOS (WMD -0.77 d; 95% CI, -1.51 to 0.04). For randomized studies, EPOC strategy use was associated with reduced mortality and MV duration but not delirium or ICU LOS. CONCLUSIONS: Using multiple implementation strategies to adopt PAD/PADIS guideline recommendations may reduce mortality, duration of MV, and ICU LOS. Further prospective, controlled studies are needed to identify the most effective strategies to implement PAD/PADIS recommendations.