Aggregating Patient Safety and Status Information in the Electronic Health Record to Support Time-Sensitive Mobility Interventions in the Intensive Care Unit: Protocol for the Design and Testing of a Clinical Decision Support Tool
Bibliographic record
Abstract
BACKGROUND: Patients who require intensive care unit (ICU) care frequently develop hospital-acquired functional decline, defined as a new or worsening loss of ability to perform self-care activities that is associated with prolonged immobility. This morbidity may persist for months to years after hospitalization but is potentially preventable through initiating mobility in the ICU using a multidisciplinary, evidence-based intervention to maintain functional status. While guidelines for ICU physical activity exist, timely identification of patients suitable for activity interventions is an ongoing challenge due to the dynamic nature of critical illness and the number of locations in the electronic health record (EHR) that clinicians need to click in and out of to synthesize patient data. Therefore, there is a critical need to develop an effective knowledge-based clinical decision support system (CDSS) interface in the EHR for efficient identification of patients appropriate for physical activity interventions and coordination of patient-specific activity plans within the ICU team. OBJECTIVE: The objective of this 2-phase project is to develop a CDSS interface for consistent translation of patient-specific data to inform evidence-based physical activity interventions delivered by registered nurses and physical therapists in ICU settings and evaluate its usability, usefulness, cognitive workload, acceptability, feasibility, and effectiveness on decision-making outcomes. METHODS: In phase 1, we will develop a usable, useful, and acceptable CDSS prototype by conducting 4 rounds of user-centered design interviews with registered nurses and physical therapists by using think-aloud and cognitive interview methods. In preparation for implementing CDSS in phase 2, we will conduct semistructured stakeholder interviews using the Consolidated Framework for Implementation Research to identify clinical workflow considerations, potential barriers, and implementation strategies. In phase 2, we will evaluate CDSS's usability, cognitive workload, acceptability, and effectiveness for activity guideline adoption in two settings: (1) a simulated EHR environment and (2) two adult ICU units in a tertiary care hospital. RESULTS: This study received funding in April 2024. The CDSS development phase is expected to conclude by December 2025. Data collection and analysis of CDSS evaluation are expected to begin in April 2026 and conclude by December 2028. CONCLUSIONS: We expect the results of this multimethod process for designing, testing efficacy, and identifying barriers to real-world use to have an important positive impact on others who seek to develop safe and effective CDSSs that align with clinical workflow. Importantly, this work will complete the necessary pilot study for a subsequent multisite pragmatic clinical trial to scale the concurrent use of patient data with guideline recommendations at the point of care to deliver evidence-based interventions to reduce hospital-acquired functional decline and its negative, costly outcomes. INTERNATIONAL REGISTERED REPORT IDENTIFIER (IRRID): DERR1-10.2196/75752.
Fetched live from OpenAlex and de-inverted. Abstracts are not stored in this database: the inverted indexes are 8.6 GB of the frame’s 9.3 GB of text, and the host has 13 GB free.
How this classification was reachedexpand
Full frame machine prediction
Teacher imitationNot calibrated prevalence, not ground truth. Human validation pending. The Gemma side is a direct model label for every work in the frame, read from the title-only record. The Codex side is a classifier learned from the 10,348 direct Codex labels and calibrated to design-weighted sample rates; fields without enough sample support carry no Codex call. Candidate is the union of the two sides; consensus is their intersection. These outputs are machine_predicted_unvalidated and are not human labels.
Distilled classifier scores by category (both heads)
| Category | Codex | Gemma |
|---|---|---|
| Metaresearch | 0.065 | 0.056 |
| Meta-epidemiology (narrow) | 0.002 | 0.002 |
| Meta-epidemiology (broad) | 0.002 | 0.003 |
| Bibliometrics | 0.003 | 0.002 |
| Science and technology studies | 0.004 | 0.003 |
| Scholarly communication | 0.003 | 0.002 |
| Open science | 0.003 | 0.002 |
| Research integrity | 0.003 | 0.004 |
| Insufficient payload (model declined to judge) | 0.022 | 0.006 |
Machine scores (provisional)
The two teacher heads of the student model, read on this work. A score orders the frame for review; it never asserts a category, and the validation status ships verbatim with every row.
Baseline scores from an immature model (maturity gate not passed, 7 training rounds). Scores rank; they never assert a category.
score_only:v0-immature-baseline · verbatim from the scoring run: score_only means the number may rank works, and no category label ships from itClassification
machine, unvalidatedMachine predicted; a candidate call from one source (direct Gemma or distilled Codex), not a consensus.
How this classification was reached, model by model and score by score, is at the end of the page under "How this classification was reached".