No abstract

Background Real-time automated continuous sampling of electronic medical record data may expeditiously identify patients at risk for death and enable prompt life-saving interventions. We hypothesized that a real-time electronic medical record-based alert could identify hospitalized patients at risk for mortality. Methods An automated alert was developed and implemented to continuously sample electronic medical record data and trigger when at least two of four systemic inflammatory response syndrome criteria plus at least one of 14 acute organ dysfunction parameters was detected. The SIRS/OD alert was applied real-time to 312,214 patients in 24 hospitals and analyzed in two phases: training and validation datasets. Results In the training phase, 29,317 (18.8%) triggered the alert and 5.2% of such patients died whereas only 0.2% without the alert died (unadjusted odds ratio 30.1; 95% confidence interval [95%CI] 26.1, 34.5; P<0.0001). In the validation phase, the sensitivity, specificity, area under curve (AUC), positive and negative likelihood ratios for predicting mortality were 0.86, 0.82, 0.84, 4.9, and 0.16, respectively. Multivariate Cox-proportional hazard regression model revealed greater hospital mortality when the alert was triggered (adjusted Hazards Ratio 4.0; 95%CI 3.3, 4.9; P<0.0001). Triggering the alert was associated with additional hospitalization days (+3.0 days) and ventilator days (+1.6 days; P<0.0001). Conclusion An automated alert system that continuously samples electronic medical record-data can be implemented, has excellent test characteristics, and can assist in the real-time identification of hospitalized patients at risk for death.

Objectives: Implement a connected network between two Tele-ICU programs to support staffing and rounding during the first wave of the coronavirus disease 2019 pandemic in the United States. Design: Proof of Concept model. Setting: Northwell Health; a 23 Hospital, 40 ICU (500 ICU beds) healthcare organization serving the downstate NY area. During the initial coronavirus disease 2019 pandemic, Northwell Health rapidly expanded to greater than 1,000 ICU beds. The surge in patients required redeployment of noncritical care providers to the ICU bedside. The Tele-ICU program expanded from covering 176 beds pre pandemic to assisting with care for patients in approximately 450 beds via deployment of Wi-Fi-enabled mobile telehealth carts to the newly formed ICUs. Patients: Critically ill coronavirus disease 2019 patients hospitalized at Northwell Health, NY, at any point from March 2020 to June 2020. Interventions: To offset the shortage of critical care physicians, Northwell Health established a collaboration with the Tele-ICU program of Providence, St. Joseph Health in the state of Washington, which enabled the critical care physicians of Providence, St. Joseph Health to participate in virtual rounding on critically ill coronavirus disease 2019 patients at Northwell Health. Main Results: We developed an innovative hybrid model that allowed for virtual rounding on an additional 40–60 patients per day by a remote critical care physician at Providence, St. Joseph Health. This was accomplished in approximately 3 weeks and provided remote care to complex patients. Conclusions: Our findings demonstrate the proof of concept of establishing a network of connected Tele-ICU programs as a rapidly scalable and sustainable paradigm for the provision of support from critical care physicians for noncritical care teams at the bedside.

Background Telemedicine is a vital component of the healthcare system’s response to COVID-19. In March of 2020, Providence health system rapidly implemented a telemedicine home monitoring program (HMP) for COVID-19 patients that included use of at-home pulse oximeters and thermometers and text-based surveys to monitor symptoms. By June 2020, Providence updated the HMP to be offered in Spanish. This program was implemented before COVID-19 testing was readily available and therefore was offered to all patients suspected of having COVID-19. This study examines engagement, experience, and utilization patterns for English and Spanish-speaking patients engaged in the COVID-19 HMP. Methods A retrospective review of program data was used to understand HMP patient engagement (responsiveness to three daily text to monitor symptoms), satisfaction with the program (likelihood to recommend the program) as well as comfort using home monitoring devices and comfort recovering from home. To understand impact on care for COVID-19 confirmed cases, we used electronic health records to measure patterns in healthcare use for COVID-19 positive HMP participants and non-HMP propensity weighted controls. All patients enrolled in the COVID-19 HMP from March–October 2020 were included in the study. Patients tested for COVID-19 during the time window and not enrolled in HMP were included in the propensity-weighted comparison group. Descriptive and regression analyses were performed overall and stratified by English and Spanish speakers. Results Of the 4,358 HMP participants, 75.5% identified as English speakers and 18.2% identified as Spanish speakers. There was high level of responsiveness to three daily text-based surveys monitoring symptoms engagement (>80%) and a high level of comfort using the home monitoring devices (thermometers and pulse oximeters) for English- and Spanish-speaking participants (97.3% and 99.6%, respectively). The majority of English (95.7%) and Spanish-speaking (100%) patients felt safe monitoring their condition from home and had high satisfaction with the HMP (76.5% and 83.6%, respectively). English and Spanish-speaking COVID-19 positive HMP participants had more outpatient and emergency departments (ED) encounters than non-participants 7 and 30 days after their positive test. Conclusion This widely implemented HMP provided participants with a sense of safety and satisfaction and its use was associated with more outpatient care and ED encounters. These outcomes were comparable across English and Spanish-speakers, highlighting the importance and potential impact of language-concordant telemedicine.