Alert to Action: Implementing Artificial Intelligence-Driven Clinical Decision Support Tools for Sepsis.

Background: Sepsis is the leading cause of mortality among hospitalized patients in our health care system and has been the target of major international initiatives such as the Surviving Sepsis Campaign championed by the Society of Critical Care Medicine and Get Ahead of Sepsis led by the Centers for Disease Control and Prevention. Methods: Our institution has strived to improve outcomes for patients by implementing a novel suite of integrated clinical decision support tools driven by a predictive learning algorithm in the electronic health record. The tools focus on sepsis multidisciplinary care using industry-standard heuristics of interface design to enhance usability and interaction. Results: Our novel clinical decision support tools demonstrated a higher level of interaction with a higher alert-to-action ratio compared to the average of all best practice alerts used at Ochsner Health (16.46% vs 8.4% to 12.1%). Conclusion: By using intuitive design strategies that encouraged users to complete best practice alerts and team-wide visualization of clinical decisions via a checklist, our clinical decision support tools for the detection and management of sepsis represent an improvement over legacy tools, and the results of this pilot may have implications beyond sepsis alerting.

Ochsner Emergency Department Overcrowding Scale (OEDOCS): predicting Emergency Department crowding among diverse academic hospital settings.

We developed the Ochsner Emergency Department Overcrowding Scale (OEDOCS) to help us measure and respond to crowding among diverse-sized Emergency Departments (ED) within our network. Not satisfied with our current Emergency Department (ED) crowding score, we first surveyed our ED staff to report perceived crowding and then developed models to predict perceived crowding from our Electronic Health Record (EHR) data. Staff at two ED locations, one large and one small, were asked to report a perceived crowding level between 0-200 every four hours for over 3 months. In addition, we collected Electronic Health Record (EHR) data during the same period. Next, we investigated models for predicting perceived crowding. Linear regression performed the best with an RMSE of 41.77 and 41.98% RMSE improvement over our previous crowding score. We have made OEDOCS publicly available.

Survey of Vaccine Hesitancy in Patients Visiting Three Tertiary-care Emergency Departments in Southeast Louisiana.

Objectives: Vaccine hesitancy has been a barrier to achieving herd immunity during the coronavirus 2019 (COVID-19) pandemic. Having low socioeconomic status and education levels, and being a person of color, are associated with higher COVID-19 infection risk and worse outcomes. These same groups are associated with higher vaccine hesitancy. The state of Louisiana has one of the lowest vaccination rates in the country. In this study we aimed to identify demographic, perspective, and health behavior factors associated with vaccine hesitancy in emergency departments (ED) in Southeast Louisiana. Methods: A cross-sectional survey was distributed at three tertiary-care hospital EDs. Patients >18 years old and not in acute distress were recruited between April-July 2021. The 37-item questionnaire addressed socioeconomic demographics, social determinants of health, COVID-19 safety practices, thoughts and perceptions on COVID-19 and vaccines, sources of COVID-19 and vaccine information, and trust in the healthcare system. Results: Overall, 247 patients completed our survey. Of those, 29.6% reported they were vaccine hesitant. These respondents were significantly more likely, when compared to vaccine-acceptant respondents, to never have married, to have some college education, make less than <$25,000 in household earnings yearly, be unsure whether vaccines prevent disease, not have discussed the COVID-19 vaccine with their primary care doctor, and to prefer to do their own research for COVID-19 vaccine information. We observed no statistically significant differences based on gender, race/ethnicity, parental status, area of living, or their perceived risk of needing hospitalization for treatment or dying from the virus. Conclusion: Vaccine hesitancy was associated with multiple socioeconomic factors, perspectives, and beliefs. Vaccine-hesitant individuals were more uncertain about the safety of the COVID-19 vaccine, the feasibility of obtaining the vaccine, and its efficacy. Public health interventions aimed at these findings and improving public trust in healthcare systems are needed to increase vaccine acceptance.