The resulting pain IM is a consensus model based on actual EHR documentation in the participating health systems. The IM captures the most important concepts related to pain.

Background: Documentation burden associated with electronic health records (EHR) is well documented in the literature. Usability and functionality of the EHR are considered fragmented and disorganized making it difficult to synthesize clinical information. Few best practices are reported in the literature to support streamlining the configuration of documentation fields to align clinical workflow with EHR data entry elements. Objective: The primary objective was to improve performance, reduce duplication, and remove non-value-added tasks by redesigning the patient assessment template in the EHR using best practice approaches. Methods: A quality improvement approach and pre/post design was used to implement and evaluate best approaches to redesign standardized flowsheet documentation workflow. We implemented standards for usability modifications targeting efficiency, reducing redundancy and improving workflow navigation. The assessment type row was removed; a reassessment section was added to the first three flowsheet rows; and documentation practices were revised to document changes from the initial assessment by selecting the corresponding body system from the dropdown menu. Vendor-supplied timestamp data was used to evaluate documentation times. Video motion-time recording was used to capture click and scroll burden, defined as steps in documentation, and was analyzed using the Keystroke Level Model. Results: Results included an 18.5% decreased time in the EHR; decrease of 7-12% % total time in flowsheets; time savings of 1.5 to 6.5 minutes per reassessment per patient; and a decrease of 88-97% in number of steps to perform reassessment documentation. Conclusion: Workflow redesign to improve the usability and functionality decreased documentation time, redundancy, and click burden resulting in improved productivity. The time savings correlate to several hours per 12 hour shift which could be reallocated to value-added patient care activities. Revising documentation practices in alignment with redesign benefits staff by decreasing workload, improving quality, and satisfaction. Keywords: reassessment, documentation burden, electronic health records, workflow redesign

Clinical decision support tools in electronic health records have demonstrated improvement with process measures and clinician performance, predominantly for providers. Clinical decision support tools could improve patient fall risk identification and prevention plans, a common concern for nursing. This quality-improvement project used clinical decision support to improve the rate of nurse compliance with documented fall risk assessments and, for patients at high risk, fall prevention plans of care in 16 adult inpatient units. Preintervention and postintervention data were compared using quarterly audits, retrospective chart review, safety reports, and falls and falls-with-injury rates. Documentation of fall risk assessments on the 16 units improved significantly according to quarterly audit data (P = .05), whereas documentation of the plans of care did not. Retrospective chart review on two units indicated improvement for admission fall risk assessment (P = .05) and a decrease in the documentation of the shift plan of care (P = .01); one unit had a statistically significant decrease in documentation of plans of care on admission (P = .00). Examination of safety reports for patients who fell showed all patients before and after clinical decision support had fall risk assessments documented. Falls and falls with injury did not change significantly before and after clinical decision support intervention.

Artificial intelligence/machine learning models are being rapidly developed and used in clinical practice. However, many models are deployed without a clear understanding of clinical or operational impact and frequently lack monitoring plans that can detect potential safety signals. There is a lack of consensus in establishing governance to deploy, pilot, and monitor algorithms within operational healthcare delivery workflows. Here, we describe a governance framework that combines current regulatory best practices and lifecycle management of predictive models being used for clinical care. Since January 2021, we have successfully added models to our governance portfolio and are currently managing 52 models.