Reduced Mortality With Ondansetron Use in SARS-CoV-2-Infected Inpatients.

BACKGROUND: The coronavirus disease 2019 (COVID-19) pandemic has led to a surge in clinical trials evaluating investigational and approved drugs. Retrospective analysis of drugs taken by COVID-19 inpatients provides key information on drugs associated with better or worse outcomes. METHODS: We conducted a retrospective cohort study of 10 741 patients testing positive for severe acute respiratory syndrome coronavirus 2 (SARS-CoV-2) infection within 3 days of admission to compare risk of 30-day all-cause mortality in patients receiving ondansetron using multivariate Cox proportional hazard models. All-cause mortality, length of hospital stay, adverse events such as ischemic cerebral infarction, and subsequent positive COVID-19 tests were measured. RESULTS: Administration of ≥8 mg of ondansetron within 48 hours of admission was correlated with an adjusted hazard ratio for 30-day all-cause mortality of 0.55 (95% CI, 0.42-0.70; P < .001) and 0.52 (95% CI, 0.31-0.87; P = .012) for all and intensive care unit-admitted patients, respectively. Decreased lengths of stay (9.2 vs 11.6; P < .001), frequencies of subsequent positive SARS-CoV-2 tests (53.6% vs 75.0%; P = .01), and long-term risks of ischemic cerebral ischemia (3.2% vs 6.1%; P < .001) were also noted. CONCLUSIONS: If confirmed by prospective clinical trials, our results suggest that ondansetron, a safe, widely available drug, could be used to decrease morbidity and mortality in at-risk populations.

Stochastic approximation EM for large-scale exploratory IRT factor analysis.

A stochastic approximation EM algorithm (SAEM) is described for exploratory factor analysis of dichotomous or ordinal variables. The factor structure is obtained from sufficient statistics that are updated during iterations with the Robbins-Monro procedure. Two large-scale simulations are reported that compare accuracy and CPU time of the proposed SAEM algorithm to the Metropolis-Hasting Robbins-Monro procedure and to a generalized least squares analysis of the polychoric correlation matrix. A smaller-scale application to real data is also reported, including a method for obtaining standard errors of rotated factor loadings. A simulation study based on the real data analysis is conducted to study bias and error estimates. The SAEM factor algorithm requires minimal lines of code, no derivatives, and no large-matrix inversion. It is programmed entirely in R.