Improving racial disparities in unmet palliative care needs among intensive care unit family members with a needs-targeted app intervention: The ICUconnect randomized clinical trial.

INTRODUCTION: The technologies used to treat the millions who receive care in intensive care unit (ICUs) each year have steadily advanced. However, the quality of ICU-based communication has remained suboptimal, particularly concerning for Black patients and their family members. Therefore we developed a mobile app intervention for ICU clinicians and family members called ICUconnect that assists with delivering need-based care. OBJECTIVE: To describe the methods and early experiences of a clustered randomized clinical trial (RCT) being conducted to compare ICUconnect vs. usual care. METHODS AND ANALYSIS: The goal of this two-arm, parallel group clustered RCT is to determine the clinical impact of the ICUconnect intervention in improving outcomes overall and for each racial subgroup on reducing racial disparities in core palliative care outcomes over a 3-month follow up period. ICU attending physicians are randomized to either ICUconnect or usual care, with outcomes obtained from family members of ICU patients. The primary outcome is change in unmet palliative care needs measured by the NEST instrument between baseline and 3 days post-randomization. Secondary outcomes include goal concordance of care and interpersonal processes of care at 3 days post-randomization; length of stay; as well as symptoms of depression, anxiety, and post-traumatic stress disorder at 3 months post-randomization. We will use hierarchical linear models to compare outcomes between the ICUconnect and usual care arms within all participants and assess for differential intervention effects in Blacks and Whites by adding a patient-race interaction term. We hypothesize that both compared to usual care as well as among Blacks compared to Whites, ICUconnect will reduce unmet palliative care needs, psychological distress and healthcare resource utilization while improving goal concordance and interpersonal processes of care. In this manuscript, we also describe steps taken to adapt the ICUconnect intervention to the COVID-19 pandemic healthcare setting. ENROLLMENT STATUS: A total of 36 (90%) of 40 ICU physicians have been randomized and 83 (52%) of 160 patient-family dyads have been enrolled to date. Enrollment will continue until the end of 2021.

Machine learning methods accurately predict host specificity of coronaviruses based on spike sequences alone.

Coronaviruses infect many animals, including humans, due to interspecies transmission. Three of the known human coronaviruses: MERS, SARS-CoV-1, and SARS-CoV-2, the pathogen for the COVID-19 pandemic, cause severe disease. Improved methods to predict host specificity of coronaviruses will be valuable for identifying and controlling future outbreaks. The coronavirus S protein plays a key role in host specificity by attaching the virus to receptors on the cell membrane. We analyzed 1238 spike sequences for their host specificity. Spike sequences readily segregate in t-SNE embeddings into clusters of similar hosts and/or virus species. Machine learning with SVM, Logistic Regression, Decision Tree, Random Forest gave high average accuracies, F1 scores, sensitivities and specificities of 0.95-0.99. Importantly, sites identified by Decision Tree correspond to protein regions with known biological importance. These results demonstrate that spike sequences alone can be used to predict host specificity.