Characterizing the relationship between coronavirus disease 2019 (COVID-19) and central-line-associated bloodstream infection (CLABSI) and assessing the impact of a nursing-focused CLABSI reduction intervention during the COVID-19 pandemic.

OBJECTIVE: To examine the impact of SARS-CoV-2 infection on CLABSI rate and characterize the patients who developed a CLABSI. We also examined the impact of a CLABSI-reduction quality-improvement project in patients with and without COVID-19. DESIGN: Retrospective cohort analysis. SETTING: Academic 889-bed tertiary-care teaching hospital in urban Los Angeles. PATIENTS OR PARTICIPANTS: Inpatients 18 years and older with CLABSI as defined by the National Healthcare Safety Network (NHSN). INTERVENTION(S): CLABSI rate and patient characteristics were analyzed for 2 cohorts during the pandemic era (March 2020-August 2021): COVID-19 CLABSI patients and non-COVID-19 CLABSI patients, based on diagnosis of COVID-19 during admission. Secondary analyses were non-COVID-19 CLABSI rate versus a historical control period (2019), ICU CLABSI rate in COVID-19 versus non-COVID-19 patients, and CLABSI rates before and after a quality- improvement initiative. RESULTS: The rate of COVID-19 CLABSI was significantly higher than non-COVID-19 CLABSI. We did not detect a difference between the non-COVID-19 CLABSI rate and the historical control. COVID-19 CLABSIs occurred predominantly in the ICU, and the ICU COVID-19 CLABSI rate was significantly higher than the ICU non-COVID-19 CLABSI rate. A hospital-wide quality-improvement initiative reduced the rate of non-COVID-19 CLABSI but not COVID-19 CLABSI. CONCLUSIONS: Patients hospitalized for COVID-19 have a significantly higher CLABSI rate, particularly in the ICU setting. Reasons for this increase are likely multifactorial, including both patient-specific and process-related issues. Focused quality-improvement efforts were effective in reducing CLABSI rates in non-COVID-19 patients but were less effective in COVID-19 patients.

Artificial Intelligence Forecasting Census and Supporting Early Decisions.

Matching resources to demand is a daily challenge for hospital leadership. In interdisciplinary collaboration, nurse leaders and data scientists collaborated to develop advanced machine learning to support early proactive decisions to improve ability to accommodate demand. When hundreds or even thousands of forecasts are made, it becomes important to let machines do the hard work of mathematical pattern recognition, while efficiently using human feedback to address performance and accuracy problems. Nurse leaders and data scientists collaborated to create a usable, low-error predictive model to let machines do the hard work of pattern recognition and model evaluation, while efficiently using nurse leader domain expert feedback to address performance and accuracy problems. During the evaluation period, the overall census mean absolute percentage error was 3.7%. ALEx's predictions have become part of the team's operational norm, helping them anticipate and prepare for census fluctuations. This experience suggests that operational leaders empowered with effective predictive analytics can take decisive proactive staffing and capacity management choices. Predictive analytic information can also result in team learning and ensure safety and operational excellence is supported in all aspects of the organization.

Net In-Neutrality's Impact on Health Care.

The Internet is a utility, just as water and electricity are, and is directly linked to care outcomes, budgeting considerations, and workforce acquisition. If water or electricity services were to be throttled up and down or commoditized, it would be important for health care leaders to understand and prepare for the resulting disruptions. In 2017, the Federal Communications Commission voted to eliminate consumer protection regulations that stopped Internet service providers from interfering with Internet service put in place under President Bush and maintained during the Obama administration. The elimination of these protections threatens to disrupt the Internet as the platform on which our health care industry builds capacity for health information exchange. The ability of Internet service providers to throttle up and down speed based on their own interests threatens our ability to meet community needs and increases the likelihood of health care disparities, just as would happen if city water providers could ration water based on their own economic interests. Proponents for net in-neutrality argue that not all Internet traffic should be equal. For instance, there could be an advantage for health care if data traffic related to health care operations was prioritized over video streaming a movie or uploading a video, but if health care companies would be required to pay for that speed, there would be financial considerations. Nurse leaders need to understand the real and possible consequences of the Internet's lack of consumer protection regulations.

Extracorporeal Membrane Oxygenation Appropriateness: An Interdisciplinary Consensus-Based Approach.

We describe a quality improvement initiative aimed at achieving interdisciplinary consensus about the appropriate delivery of extracorporeal membrane oxygenation (ECMO). Interdisciplinary rounds were implemented for all patients on ECMO and addressed whether care was consistent with a patient's minimally acceptable outcome, maximally acceptable burden, and relative likelihood of achieving either. The rounding process was associated with decreased days on venoarterial ECMO, from a median of 6 days in 2014 (first quartile [Q1]-third quartile [Q3], 3-10) to 5 days in 2015 (Q1-Q3, 2.5-8) and in 2016 (Q1-Q3, 1-8). Our statistical methods do not allow us to conclude that this change was due to our intervention, and it is possible that the observed decreases would have occurred whether or not the rounding process was implemented.