Girard, Timothy D.

Abstract Background Delirium is often underdiagnosed in clinical practice and is not routinely coded for billing. While manual chart review can identify delirium, it is labor-intensive and impractical for large-scale studies. Natural language processing (NLP) can analyze unstructured text in electronic health records (EHRs) to extract meaningful clinical information. Methods To support national integration of NLP for EHR-based delirium identification across different institutions, we launched the Delirium Interest Group within the national Evolve to Next-Gen Accrual to Clinical Trials (ENACT) NLP Working Group. This paper outlines our initial efforts to standardize, evaluate, and translate an NLP-based delirium detection model into the i2b2/ENACT platform. Results Multisite contextual inquiry identified several key challenges, including variations in local screening practices (eg, tools used, documentation frequency, and quality control), the need for harmonized definitions in the context of EHRs, and the complexity of modeling temporal logic. Multisite NLP evaluation revealed variable performance degradation driven by differences in delirium screening practices, clinical documentation patterns and semantics, and note syntactic structures. Conclusion Our work represents an important first step toward enabling scalable and standardized NLP-based delirium detection across institutions. By engaging diverse institutions through the ENACT NLP Working Group, we identified shared challenges and site-specific variations that impact model implementation and performance. Our collaborative approach enabled the development of a more robust framework for delirium identification across heterogeneous EHR systems. Future efforts will build on this foundation to enhance the validity, usability, and translational impact of delirium detection.

RATIONALE: Critically ill adults are at risk for a variety of distressing and consequential symptoms both during and after an ICU stay. Management of these symptoms can directly influence outcomes. OBJECTIVES: The objective was to update and expand the Society of Critical Care Medicine’s 2018 Clinical Practice Guidelines for the Prevention and Management of Pain, Agitation/Sedation, Delirium, Immobility, and Sleep Disruption in Adult Patients in the ICU. PANEL DESIGN: The interprofessional inclusive guidelines task force was composed of 24 individuals including nurses, physicians, pharmacists, physiotherapists, psychologists, and ICU survivors. The task force developed evidence-based recommendations using the Grading of Recommendations, Assessment, Development, and Evaluation (GRADE) approach. Conflict-of-interest policies were strictly followed in all phases of the guidelines, including task force selection and voting. METHODS: The task force focused on five main content areas as they pertain to adult ICU patients: anxiety (new topic), agitation/sedation, delirium, immobility, and sleep disruption. Using the GRADE approach, we conducted a rigorous systematic review for each population, intervention, control, and outcome question to identify the best available evidence, statistically summarized the evidence, assessed the quality of evidence, and then performed the evidence-to-decision framework to formulate recommendations. RESULTS: The task force issued five statements related to the management of anxiety, agitation/sedation, delirium, immobility, and sleep disruption in adults admitted to the ICU. In adult patients admitted to the ICU, the task force issued conditional recommendations to use dexmedetomidine over propofol for sedation, provide enhanced mobilization/rehabilitation over usual mobilization/rehabilitation, and administer melatonin. The task force was unable to issue recommendations on the administration of benzodiazepines to treat anxiety, and the use of antipsychotics to treat delirium. CONCLUSIONS: The guidelines task force provided recommendations for pharmacologic management of agitation/sedation and sleep, and nonpharmacologic management of immobility in critically ill adults. These recommendations are intended for consideration along with the patient’s clinical status.