The probability of correctly predicting subglottic penetration from clinical observations

Abstract

It is difficult to predict from clinical signs and symptoms which patients suffer from subglottic penetration of foods. Most investigators attempting to predict aspiration have used small numbers of patients and relatively unsophisticated statistical techniques. In this study, we utilized 249 patients to examine the predictive value of several clinical factors thought to be suggestive of subglottic penetration with discriminant analysis. Using this approach we were able to correctly predict about 2/3 of both those who aspirate and those who do not aspirate. This is better than others have reported but still inadequate for clinical purposes.