Multivariate Analysis As a Support for Diagnostic Flowcharts in Allergic Bronchopulmonary Aspergillosis: A Proof-of-Concept Study

Abstract

Molecular-based allergy diagnosis yields multiple biomarker datasets. The classical diagnostic score for allergic bronchopulmonary aspergillosis (ABPA), a severe disease usually occurring in asthmatic patients and people with cystic fibrosis, comprises succinct immunological criteria formulated in 1977: total IgE, anti-Aspergillus fumigatus (Af) IgE, anti-Af "precipitins," and anti-Af IgG. Progress achieved over the last four decades led to multiple IgE and IgG(4) Af biomarkers available with quantitative, standardized, molecular-level reports. These newly available biomarkers have not been included in the current diagnostic criteria, either individually or in algorithms, despite persistent underdiagnosis of ABPA. Large numbers of individual biomarkers may hinder their use in clinical practice. Conversely, multivariate analysis using new tools may bring about a better chance of less diagnostic mistakes. We report here a proof-of-concept work consisting of a three-step multivariate analysis of Af IgE, IgG, and IgG4 biomarkers through a combination of principal component analysis, hierarchical ascendant classification, and classification and regression tree multivariate analysis. The resulting diagnostic algorithms might show the way for novel criteria and improved diagnostic efficiency in Af-sensitized patients at risk for ABPA.

Keywords: Aspergillus fumigatus; allergic bronchopulmonary aspergillosis; immunoglobulin; molecular allergens; multivariate analysis.

Figure 1

Hierarchical ascendant classification on principal component analysis (PCA) of the study sample. X- and Y-axes are the two first dimensions issued from the PCA. Patients are denoted 1–10 for the allergic bronchopulmonary aspergillosis (ABPA) group and 11–49 for the Aspergillus fumigatus (Af)-cystic fibrosis (CF) group. Af-sensitized patients without ABPA (Af-CF) are mostly found in the homogenous cluster 1 (34/39), while ABPA patients are mostly found in cluster 2 (6/10).

Figure 2

Classification tree using analysis of sIgE, sIgG, and sIgG4 responses to Asp f 1, Asp f 2, Asp f 3, Asp f 4, and Asp f 6 molecules. The diagnostic algorithm retains IgE to Asp f 4, Asp f 1, Asp f 6, and IgG4 to Asp f 2, yielding 1 Aspergillus fumigatus (Af)-cystic fibrosis (CF)-only groups counting 35/39 patients, 1 allergic bronchopulmonary aspergillosis (ABPA)-only group of 7 patients, and 3 mixed groups of undetermined clinical significance where other criteria are needed. Overall, 7/10 ABPA patients and 35/39 Af-CF patients are clearly identified.