Bacterial Signatures of Paediatric Respiratory Disease: An Individual Participant Data Meta-Analysis

Abstract

Introduction: The airway microbiota has been linked to specific paediatric respiratory diseases, but studies are often small. It remains unclear whether particular bacteria are associated with a given disease, or if a more general, non-specific microbiota association with disease exists, as suggested for the gut. We investigated overarching patterns of bacterial association with acute and chronic paediatric respiratory disease in an individual participant data (IPD) meta-analysis of 16S rRNA gene sequences from published respiratory microbiota studies. Methods: We obtained raw microbiota data from public repositories or via communication with corresponding authors. Cross-sectional analyses of the paediatric (<18 years) microbiota in acute and chronic respiratory conditions, with >10 case subjects were included. Sequence data were processed using a uniform bioinformatics pipeline, removing a potentially substantial source of variation. Microbiota differences across diagnoses were assessed using alpha- and beta-diversity approaches, machine learning, and biomarker analyses. Results: We ultimately included 20 studies containing individual data from 2624 children. Disease was associated with lower bacterial diversity in nasal and lower airway samples and higher relative abundances of specific nasal taxa including Streptococcus and Haemophilus. Machine learning success in assigning samples to diagnostic groupings varied with anatomical site, with positive predictive value and sensitivity ranging from 43 to 100 and 8 to 99%, respectively. Conclusion: IPD meta-analysis of the respiratory microbiota across multiple diseases allowed identification of a non-specific disease association which cannot be recognised by studying a single disease. Whilst imperfect, machine learning offers promise as a potential additional tool to aid clinical diagnosis.

Keywords: individual participant data (IPD) meta-analysis; meta-analysis; microbiota (16S); paediatrics; respiratory infection; respiratory tract.

FIGURE 1

Schematic showing protocol for selecting meta-analysis studies.

FIGURE 2

Bacterial alpha-diversity at broad disease (A) and specific diagnostic grouping levels (B). Significant differences in (A), as assessed by a Bonferroni corrected t-test, are denoted by asterisks (p < 0.05). For clarity, statistical significance for (B) is presented in Supplementary Tables E6–9. Diamonds on each box represent the mean value. Alpha-diversity across different anatomical sites (lower airways, sputum, oral, and nasal) was not explicitly compared. Below the plot the number of studies (bold) and number of contributing samples is reported. AI, acute infections; AS, asthma; CF, cystic fibrosis; DC, disease control; HE, healthy; SU, suppurative; WH, wheezing illness.

FIGURE 3

Rank-abundance plots showing the 15 most abundant bacterial phylotypes in control samples (blue) and their respective proportional relative abundance in disease samples (red), for lower airway, oral, and nasal samples. Taxa are ranked based on their relative sequence abundance in controls.

FIGURE 4

Representation of bacterial genus-level phylotypes in the core microbiota from nasal, oral, sputum, and lower airway samples. A core was defined as presence in at least 75% of samples, based on the rarefied data. An abundance filter was also applied, whereby a genus must represent ≥10% in at least one sample. Cross-hatching separates broad-level comparisons from those involving specific diagnostic groupings, within a given anatomical site. AI, acute infections; AS, asthma; C, control; CF, cystic fibrosis; DC, disease control; DS, disease (any respiratory diagnosis); HE, healthy; SU, suppurative; WH, wheezing illness.

FIGURE 5

Average positive predictive value (fraction of calls of a diagnostic grouping which are correct) and sensitivity (fraction of samples within a diagnostic grouping which are correctly identified) rates of sample assignments to both broad disease level (circles) and specific diagnostic groupings (diamonds), through use of random forest machine learning. Data are displayed according to anatomical category: lower airways (A), sputum (B), oral (C), and nasal (D). Predictions were made based on rarefied data in which the numbers of samples for each diagnostic grouping were made equal. The Control symbol (blue circles) in (D) is hidden behind the red (Disease) circle. AI, acute infections; AS, asthma; CF, cystic fibrosis; DC, disease control; HE, healthy; SU, suppurative; WH, wheezing illness.