Discriminant analyses of peanut allergy severity scores

Abstract

Peanut allergy is one of the most prevalent food allergies. The possibility of a lethal accidental exposure and the persistence of the disease make it a public health problem. Evaluating the intensity of symptoms is accomplished with a double blind placebo controlled food challenge (DBPCFC), which scores the severity of reactions and measures the dose of peanut that elicits the first reaction. Since DBPCFC can result in life-threatening responses, we propose an alternate procedure with the long term goal of replacing invasive allergy tests. Discriminant analyses of DBPCFC score, the eliciting dose and the first accidental exposure score were performed in 76 allergic patients using 6 immunoassays and 28 skin prick tests. A Multiple Factorial Analysis was performed to assign equal weights to both groups of variables and predictive models were built by cross-validation with LDA, k-NN, CART, penalized SVM, stepwise logistic regression and AdaBoost methods. We developed an algorithm for simultaneously clustering eliciting dose values and selecting discriminant variables. Our main conclusion is that antibody measurements offer information on the allergy severity, especially those directed against rAra-h1 and rAra-h3. Further independent validation of these results and the use of new predictors will help extend this study to clinical practices.

Clustering of the Values of a Response Variable and Simultaneous Covariate Selection Using a Stepwise Algorithm

“…In this article, we extended our previous version of the algorithm [9] to a more general framework where any model selection criterion for which a test of significance is available can be used in addition to Wilks' Lambda and where forward covariate inclusion was replaced by stepwise selection. Of note, a version of the algorithm allowing the use of logistic regression with AIC as optimality criterion has already been coded and evaluated on two small datasets.…”

“…We already had to overcome these issues in a dataset we analyzed previously [9]. In order to clarify our objectives, recall briefly its framework.…”