Inappropriate Use of Lumbar Magnetic Resonance Imaging: Limitations and Potential Solutions

Abstract

stable injury fatality rate over the decade; however, this is an open question requiring further study. Westphal addresses the use of fatality rates in the Poisson regression models to determine the relationship between firearm legislation and firearm-related fatalities. The regression models we used in our study accurately evaluated this relationship1; however, we repeated the analysis using Poisson models with counts of deaths rather than rates, adjusted for population. Using this methodology in our previous multivariable model, we found a similar effect of legislation (incident rate ratio for suicide, 0.41 in the fourth compared with the first quartile; 95% CI, 0.21-0.82). This effect persisted after correction for gun prevalence (incident rate ratio, 0.48; 95% CI, 0.23-0.98).