Respiratory virus detections in children presenting to an Australian paediatric referral hospital pre-COVID-19 pandemic, January 2014 to December 2019

Abstract

Acute respiratory infections cause significant paediatric morbidity, but for pathogens other than influenza, respiratory syncytial virus (RSV), and SARS-CoV-2, systematic monitoring is not commonly performed. This retrospective analysis of six years of routinely collected respiratory pathogen multiplex PCR testing at a major paediatric hospital in New South Wales Australia, describes the epidemiology, year-round seasonality, and co-detection patterns of 15 viral respiratory pathogens. 32,599 respiratory samples from children aged under 16 years were analysed. Most samples were associated with a hospital admission (24,149, 74.1%) and the median age of sampling was 16 months (IQR 5-53). Viruses were detected in 62.9% (20,510) of samples, with single virus detections occurring in 73.5% (15,082) of positive samples. In instances of single virus detection, rhinovirus was most frequent (5125, 40.6%), followed by RSV-B (1394, 9.2%) and RSV-A (1290, 8.6%). Moderate to strong seasonal strength was observed for most viruses with some notable exceptions. Rhinovirus and enterovirus were detected year-round and low seasonal strength was observed for adenovirus and bocavirus. Biennial seasonal patterns were observed for influenza B and parainfluenza virus 2. Co-detections occurred in 5,428 samples, predominantly with two (4284, 79.0%) or three viruses (904, 16.7%). The most common co-detections were rhinovirus-adenovirus (566, 10.4%), rhinovirus-enterovirus (357, 8.3%), and rhinovirus-RSV-B (337, 7.9%). Ongoing pan-pathogen surveillance, integrating both laboratory and clinical data, is necessary to assist in identification of key pathogens and combination of pathogens to support effective preventative public health strategies and reduce the burden of paediatric respiratory infections.

Fig 1. Average annual seasonal curve by virus: Test percent positive, five weekly moving average.

Five weekly moving average test percent positive seasonal curves by virus across the study period (2014–2019). Mean percentage of positive samples (solid blue line) banded by 95% confidence interval (light blue) by epidemiological week. Measures of average test percent positive for each virus were calculated over the full study period, including mean (orange horizontal dashed and dotted lines) and median (red horizontal dashed lines). Percent positive axis scaled to each virus as to not diminish visibility of fluctuations for less frequently detected viruses. Viruses ordered from most (rhinovirus A/B/C) to least (parainfluenza 4) frequently detected. *Includes samples positive for either coronavirus 229E and/or coronavirus NL63 over the full study period. Results for each assay is available in S3 Fig.

Fig 2. Multi-positive samples by virus, with dual positive heatmap.

Bar chart representing the number of viruses detected within samples by virus.