Sir.—We are concerned about both the safety and utility of direct inspection of the epiglottis in patients with suspected laryngotracheobronchitis, as reported by Mauro and colleagues.
They report no complications on direct inspection of the epiglottis in six children with acute epiglottitis. The exact upper 95% confidence limit for this proportion (0/6) is 35%.1 This means that the study results are compatible with a complication rate as high as 35% for direct inspection of the epiglottis in patients with acute epiglottitis. Safety of the procedure certainly remains in doubt.
There is a rapid method to calculate the approximate upper 95% confidence limit when the number of occurrences in a study is 0.2,3 If N is the number of study subjects, 3/N approximates the upper 95% confidence limit. When N is greater than 30, this approximation is accurate to one decimal place. For Mauro and colleagues' study, the