Machine learning-based clinical decision support tools for sepsis create opportunities to identify at-risk patients and initiate treatments earlier, critical to improving sepsis outcomes. Increasing use of such systems necessitates quantifying and understanding provider adoption. Using realtime provider interactions with a sepsis early detection tool (Targeted Real-time Early Warning System) deployed at five hospitals over a two-year period (469,419 screened encounters, 9,805 (2.1%) retrospectively-identified sepsis cases), we found high sensitivity (82% of sepsis cases identified), high adoption rates (89% of alerts evaluated by a physician or advanced practice provider and 38% of evaluated alerts confirmed) and an association between use of the tool and earlier treatment of sepsis patients (1.85 (95% CI:1.66-2.00) hour reduction in median time to first antibiotics order). Further, we found that provider-related factors were strongly associated with adoption. Beyond improving system performance, efforts to improve adoption should focus on provider knowledge, experience, and perceptions of the system.
We assessed temporal changes in the household secondary attack rate of SARS-CoV-2 and identified risk factors for transmission in vulnerable Latino households of Baltimore, Maryland. The household SAR was 45.8%, and it appeared to increase as the alpha variant spread, highlighting the magnified risk of spread in unvaccinated populations.
Background: Despite the disproportionate impact of COVID-19 on Latinos, there were disparities in vaccination, especially during the early phase of COVID-19 immunization rollout. Methods: Leveraging a community-academic partnership established to expand access to SARS-CoV2 testing, we implemented community vaccination clinics with multifaceted outreach strategies and flexible appointments for limited English proficiency Latinos. Results: Between February 26 and May 7 2021, 2250 individuals received the first dose of COVID-19 vaccination during 18 free community events. Among them, 92.4% (95% confidence interval [CI], 91.2%-93.4%) self-identified as Hispanic, 88.7% (95% CI, 87.2%-89.9%) were limited English proficiency Spanish speakers, 23.1% (95% CI, 20.9%-25.2%) reported prior COVID-19 infection, 19.4% (95% CI, 16.9%-22.25%) had a body mass index of more than 35, 35.0% (95% CI, 32.2%-37.8%) had cardiovascular disease, and 21.6% (95% CI, 19.2%-24.0%) had diabetes. The timely second-dose completion rate was high (98.7%; 95% CI, 97.6%-99.2%) and did not vary by outreach method. Conclusion: A free community-based vaccination initiative expanded access for Latinos with limited English proficiency at high risk for COVID-19 during the early phase of the immunization program in the US.
Machine learning-based clinical decision support tools for sepsis create opportunities to identify at-risk patients and initiate treatments earlier, an important step in improving sepsis outcomes. Increasing use of such systems means quantifying and understanding provider adoption is critical. Using real-time provider interactions with a sepsis early detection tool (Targeted Real-time Early Warning System) deployed at five hospitals over a two-year period (469,419 screened patient encounters, 9,805 (2.1%) of which were retrospectively identified as having sepsis), we found high adoption rates (89% of alerts were evaluated by a physician or advanced practice provider) and an association between use of the tool and earlier treatment of sepsis patients (1.85 (95% CI: 1.66 - 2.00) hour reduction in median time to first antibiotics order). Further, we found that provider-related factors had the strongest association with alert adoption and that case complexity and atypical presentation were associated with dismissal of alerts on sepsis patients. Beyond improving the performance of the system, efforts to improve adoption should focus on provider knowledge, experience, and perceptions of the system.
The disproportionate impact of COVID-19 on low-income Latinos with limited access to health care services prompted the expansion of community-based COVID-19 services. From June 25, 2020, to May 20, 2021, we established a coalition of faith leaders, community organizations, and governmental organizations to implement a Spanish-language hotline and social media campaign that linked people to a COVID-19 testing site at a local church in a high-density Latino neighborhood in Baltimore, Maryland. This retrospective analysis compared the characteristics of Latinos accessing testing in community versus health care facility–based settings. (Am J Public Health. 2022;112(S9):S913–S917. https://doi.org/10.2105/AJPH.2022.307074 )
To assess factors associated with timely second-dose completion, we analyzed COVID-19 vaccine data from community-based and mobile vaccine clinics in Maryland. Overall, 85.3% of patients received a timely second dose. Factors associated with a timely second dose included Latino ethnicity (adjusted odds ratio [AOR] = 1.5; 95% confidence interval [CI] = 1.1, 2.0) and receipt of the first dose at community-based vaccine clinics (AOR = 2.1; 95% CI = 1.8, 2.5). Future health initiatives for underserved communities should focus on establishing vaccine clinics in trusted community spaces with culturally sensitive support. (Am J Public Health. 2023;113(9):947–951. https://doi.org/10.2105/AJPH.2023.307338 )
scite is a Brooklyn-based organization that helps researchers better discover and understand research articles through Smart Citations–citations that display the context of the citation and describe whether the article provides supporting or contrasting evidence. scite is used by students and researchers from around the world and is funded in part by the National Science Foundation and the National Institute on Drug Abuse of the National Institutes of Health.