Background
Tocilizumab blocks pro-inflammatory activity of interleukin-6 (IL-6), involved in pathogenesis of pneumonia the most frequent cause of death in COVID-19 patients.
Methods
A multicenter, single-arm, hypothesis-driven trial was planned, according to a phase 2 design, to study the effect of tocilizumab on lethality rates at 14 and 30 days (co-primary endpoints, a priori expected rates being 20 and 35%, respectively). A further prospective cohort of patients, consecutively enrolled after the first cohort was accomplished, was used as a secondary validation dataset. The two cohorts were evaluated jointly in an exploratory multivariable logistic regression model to assess prognostic variables on survival.
Results
In the primary intention-to-treat (ITT) phase 2 population, 180/301 (59.8%) subjects received tocilizumab, and 67 deaths were observed overall. Lethality rates were equal to 18.4% (97.5% CI: 13.6–24.0, P = 0.52) and 22.4% (97.5% CI: 17.2–28.3, P < 0.001) at 14 and 30 days, respectively. Lethality rates were lower in the validation dataset, that included 920 patients. No signal of specific drug toxicity was reported. In the exploratory multivariable logistic regression analysis, older age and lower PaO2/FiO2 ratio negatively affected survival, while the concurrent use of steroids was associated with greater survival. A statistically significant interaction was found between tocilizumab and respiratory support, suggesting that tocilizumab might be more effective in patients not requiring mechanical respiratory support at baseline.
Conclusions
Tocilizumab reduced lethality rate at 30 days compared with null hypothesis, without significant toxicity. Possibly, this effect could be limited to patients not requiring mechanical respiratory support at baseline.
Registration EudraCT (2020-001110-38); clinicaltrials.gov (NCT04317092).
Background: Enrollment of large cohorts of syncope patients from administrative data is crucial for proper risk stratification but is limited by the enormous amount of time required for manual revision of medical records. Aim: To develop a Natural Language Processing (NLP) algorithm to automatically identify syncope from Emergency Department (ED) electronic medical records (EMRs). Methods: De-identified EMRs of all consecutive patients evaluated at Humanitas Research Hospital ED from 1 December 2013 to 31 March 2014 and from 1 December 2015 to 31 March 2016 were manually annotated to identify syncope. Records were combined in a single dataset and classified. The performance of combined multiple NLP feature selectors and classifiers was tested. Primary Outcomes: NLP algorithms’ accuracy, sensitivity, specificity, positive predictive value, negative predictive value, and F3 score. Results: 15,098 and 15,222 records from 2013 and 2015 datasets were analyzed. Syncope was present in 571 records. Normalized Gini Index feature selector combined with Support Vector Machines classifier obtained the best F3 value (84.0%), with 92.2% sensitivity and 47.4% positive predictive value. A 96% analysis time reduction was computed, compared with EMRs manual review. Conclusions: This artificial intelligence algorithm enabled the automatic identification of a large population of syncope patients using EMRs.
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.