Faculty Bibliography

This paper aims to highlight how to reduce medication errors through the implementation of human factors science to the design features of medication containers. Despite efforts to employ automation for increased safety and decreased workload, medication administration in hospital wards is still heavily dependent on human operators (pharmacists, nurses, physicians, etc.). Improving this multi-step process requires its being studied and designed as an interface in a complex socio-technical system. Human factors engineering, also known as ergonomics, involves designing socio-technical systems to improve overall system performance, and reduces the risk of system, and in particular, operator, failures. The incorporation of human factors principles into the design of the work environment and tools that are in use during medication administration could improve this process. During periods of high workload, the cognitive effort necessary to work through a very demanding process may overwhelm even expert operators. In such conditions, the entire system should facilitate the human operator's high level of performance. Regarding medications, clinicians should be provided with as many perceptual cues as possible to facilitate medication identification. Neglecting the shape of the container as one of the features that differentiates between classes of medications is a lost opportunity to use a helpful characteristic, and medication administration failures that happen in the absence of such intentional design arise from "designer error" rather than "user error". Guidelines that define a container's shape for each class of medication would compel pharmaceutical manufacturers to be compatible and would eliminate the confusion that arises when a hospital changes the supplier of a given medication.

OBJECTIVES/OBJECTIVE:To evaluate how key aspects of New York State Ventilator Allocation Guidelines (NYSVAG)-Sequential Organ Failure Assessment score criteria and ventilator time trials -might perform with respect to the frequency of ventilator reallocation and survival to hospital discharge in a simulated cohort of COVID-19 patients. METHODS:Single center retrospective observational and simulation cohort study of 884 critically-ill COVID-19 patients undergoing ventilator allocation per NYSVAG. RESULTS:742 patients (83.9%) would have had their ventilator reallocated during the 11-day observation period, 280 (37.7%) of whom would have otherwise survived to hospital discharge if provided a ventilator. Only 65 (18.1%) of the observed surviving patients would have survived by NYSVAG. Extending ventilator time trials from 2 to 5 days resulted in a 49.2% increase in simulated survival to discharge. CONCLUSIONS:In the setting of a protracted respiratory pandemic, implementation of NYSVAG or similar protocols could lead to a high degree of ventilator reallocation, including withdrawal from patients who might otherwise survive. Longer ventilator time trials might lead to improved survival for COVID-19 patients given their protracted respiratory failure. Further studies are needed to understand the survival of patients receiving reallocated ventilators to determine whether implementation of NYSVAG would improve overall survival.

Testing multiple treatments for heterogeneous (varying) effectiveness with respect to many underlying risk factors requires many pairwise tests; we would like to instead automatically discover and visualize patient archetypes and predictors of treatment effectiveness using multitask machine learning. In this paper, we present a method to estimate these heterogeneous treatment effects with an interpretable hierarchical framework that uses additive models to visualize expected treatment benefits as a function of patient factors (identifying personalized treatment benefits) and concurrent treatments (identifying combinatorial treatment benefits). This method achieves state-of-the-art predictive power for COVID-19 in-hospital mortality and interpretable identification of heterogeneous treatment benefits. We first validate this method on the large public MIMIC-IV dataset of ICU patients to test recovery of heterogeneous treatment effects. Next we apply this method to a proprietary dataset of over 3000 patients hospitalized for COVID-19, and find evidence of heterogeneous treatment effectiveness predicted largely by indicators of inflammation and thrombosis risk: patients with few indicators of thrombosis risk benefit most from treatments against inflammation, while patients with few indicators of inflammation risk benefit most from treatments against thrombosis. This approach provides an automated methodology to discover heterogeneous and individualized effectiveness of treatments.

OBJECTIVE:An interprofessional team, also known as the tracheostomy steering committee (TSC) was established to prevent tracheotomy-related pressure injuries (TRPI) and standardize practice for tracheostomy insertion and care of patients with tracheostomies. In addition to reducing the number TRPIs, the TSC sought establish an escalation process for all clinicians to raise concerns about the care and management of patients with tracheostomies. METHODS:This quality improvement initiative used the DMAIC (Define, Measure, Analyze, Improve and Control) framework with a pre- and post-intervention design. The patient population included all adult patients requiring a tracheostomy. The TSC created a TRPI-prevention bundle, which included recommendations for protective foam dressing and skin barrier film, suture tension, timing of suture removal, stoma care, offloading and positioning, escalation, documentation, and dual skin assessment. An electronic tracheostomy report was developed to track patients with a tracheostomy across the enterprise. RESULTS:A total of 289 patients had a tracheostomy during their inpatient hospital stay from January 2018 through December 2019. There was an observed a reduction in the daily rate of TRPIs by 50% with the use of the standardized TRPI-prevention bundle. CONCLUSIONS:Use of the TRPI-prevention bundle at our institution resulted in a significant reduction in the incidence of TRPI. Timely escalation of possible tracheostomy injuries or tracheostomies at risk enabled rapid intervention, likely preventing many injuries, and real-time feedback to clinicians reinforced best practices. The use of an interprofessional team is necessary in providing optimal tracheostomy care to ensure the best outcomes.