Background
Predicting early respiratory failure due to COVID-19 can help triage patients to higher levels of care, allocate scarce resources, and reduce morbidity and mortality by appropriately monitoring and treating the patients at greatest risk for deterioration. Given the complexity of COVID-19, machine learning approaches may support clinical decision making for patients with this disease.
Objective
Our objective is to derive a machine learning model that predicts respiratory failure within 48 hours of admission based on data from the emergency department.
Methods
Data were collected from patients with COVID-19 who were admitted to Northwell Health acute care hospitals and were discharged, died, or spent a minimum of 48 hours in the hospital between March 1 and May 11, 2020. Of 11,525 patients, 933 (8.1%) were placed on invasive mechanical ventilation within 48 hours of admission. Variables used by the models included clinical and laboratory data commonly collected in the emergency department. We trained and validated three predictive models (two based on XGBoost and one that used logistic regression) using cross-hospital validation. We compared model performance among all three models as well as an established early warning score (Modified Early Warning Score) using receiver operating characteristic curves, precision-recall curves, and other metrics.
Results
The XGBoost model had the highest mean accuracy (0.919; area under the curve=0.77), outperforming the other two models as well as the Modified Early Warning Score. Important predictor variables included the type of oxygen delivery used in the emergency department, patient age, Emergency Severity Index level, respiratory rate, serum lactate, and demographic characteristics.
Conclusions
The XGBoost model had high predictive accuracy, outperforming other early warning scores. The clinical plausibility and predictive ability of XGBoost suggest that the model could be used to predict 48-hour respiratory failure in admitted patients with COVID-19.
Objective
PICC line use for central venous access in thermally injured patients has increased in recent years despite a lack of evidence regarding safety in this patient population. A recent survey of invasive catheter practices among 44 burn centers in the United States found that 37% of burn units use PICC lines as part of their treatment protocol. The goal of this study was to compare PICC associated complication rates to existing literature in both the critical care and burn settings.
Methods
A single institution retrospective cohort review of patients who received a PICC line during admission to a regional burn unit between 2008–2013. Fifty-three patients were identified with a total of seventy-three PICC lines. The primary outcome measurement for this study was indication for PICC line discontinuation.
Results
The most common reason for PICC line discontinuation was that the line was no longer indicated (45.2%). Four cases of symptomatic upper extremity deep vein thrombosis (5.5%) and 3 cases of central line associated bloodstream infection (4.3%, 2.72 infections per 1000 line days) were identified. PICC lines were in situ an average of 15 days [range 1–49 days].
Conclusions
We suggest that PICC line associated complication rates are similar to those published in the critical care literature. Though these rates are higher than those published in the burn literature, they are similar to CVC associated complication rates. While PICC lines can be a useful resource in the treatment of the thermally injured patient, they are associated with significant, and potentially fatal risks.
Pulmonary fibrosis is a chronic debilitating condition characterized by progressive deposition of connective tissue, leading to a steady restriction of lung elasticity, a decline in lung function, and a median survival of 4.5 years. The leading causes of pulmonary fibrosis are inhalation of foreign particles (such as silicosis and pneumoconiosis), infections (such as post COVID-19), autoimmune diseases (such as systemic autoimmune diseases of the connective tissue), and idiopathic pulmonary fibrosis. The therapeutics currently available for pulmonary fibrosis only modestly slow the progression of the disease. This review is centered on the interplay of damage-associated molecular pattern (DAMP) molecules, Toll-like receptor 4 (TLR4), and inflammatory cytokines (such as TNF-α, IL-1β, and IL-17) as they contribute to the pathogenesis of pulmonary fibrosis, and the possible avenues to develop effective therapeutics that disrupt this interplay.
Extracellular cold-inducible RNA-binding protein (eCIRP), a new damage-associated molecular pattern (DAMP), has been recently shown to play a critical role in promoting the development of bleomycin-induced pulmonary fibrosis. Although fibroblast activation is a critical component of the fibrotic process, the direct effects of eCIRP on fibroblasts have never been examined. We studied eCIRP’s role in the induction of inflammatory phenotype in pulmonary fibroblasts and its connection to bleomycin-induced pulmonary fibrosis in mice. We found that eCIRP causes the induction of proinflammatory cytokines and differentially expression-related pathways in a TLR4-dependent manner in pulmonary fibroblasts. Our analysis further showed that the accessory pathways MD2 and Myd88 are involved in the induction of inflammatory phenotype. In order to study the connection of the enrichment of these pathways in priming the microenvironment for pulmonary fibrosis, we investigated the gene expression profile of lung tissues from mice subjected to bleomycin-induced pulmonary fibrosis collected at various time points. We found that at day 14, which corresponds to the inflammatory-to-fibrotic transition phase after bleomycin injection, TLR4, MD2, and Myd88 were induced, and the transcriptome was differentially enriched for genes in those pathways. Furthermore, we also found that inflammatory cytokines gene expressions were induced, and the cellular responses to these inflammatory cytokines were differentially enriched on day 14. Overall, our results show that eCIRP induces inflammatory phenotype in pulmonary fibroblasts in a TLR4 dependent manner. This study sheds light on the mechanism by which eCIRP induced inflammatory fibroblasts, contributing to pulmonary fibrosis.
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.