Exhaled volatile organic compounds detect pulmonary exacerbations early in children with cystic fibrosis: results of a 1 year observational pilot study

Abstract

In patients with cystic fibrosis (CF), pulmonary exacerbations (PEx) have an important influence on well-being, quality of life, and lung function decline. Early detection combined with early treatment may prevent severe PEx. To determine whether early detection of PEx is possible by non-invasive markers (volatile organic compounds) in exhaled breath. In a 1 year prospective observational pilot study, 49 children with CF were studied. At clinical visits with an interval of 2 months, lung function, volatile organic compounds (VOCs) in exhaled breath by means of gas chromatography-time-of-flight-mass spectrometry, and medication use were assessed. PEx were recorded. Random forest (RF) classification modelling was used to select discriminatory VOCs, followed by building of receiver operating characteristic curves. An inverse relation between the predictive power of a set of VOCs and time between exhaled breath sampling and the onset of PEx was found. When this time period was within 7 d, the RF model with the nine most discriminatory VOCs was able to correctly predict 79% of the children with an upcoming PEx or remaining stable (sensitivity 79% and specificity 78%). This result was validated by means of bootstrapping within the RF classification model. PEx in children with CF can be detected at an early stage by means of exhaled VOCs. The highest predictive value was reached if time between sampling and the onset of an exacerbation was no longer than 7 d.

Implementation of prognostic machine learning algorithms in paediatric chronic respiratory conditions: a scoping review

“…There were more studies with data from North America (68%)21–37 than Europe (24%),38–43 Australia (4%),44 or the Middle East (4%) 45. Data collected during studies (ie, cross-sectional, longitudinal cohort) were the most common sources of data (56%),23 25 27 31 35 37–45 followed by registry data from either routine EHR (24%),26 28 30 32 34 36 regional or national databases (12%),21 22 33 or clinical records (4%) 24. One study did not report the source of data for model development (4%) 29…”

“…Participant ages within a study ranged from infants less than a year old, to 2–22 years. Dates of study data ranged from 1993 to 2019, 6 studies (24%)29 38 41 43–45 did not report any study dates. There was no evidence of any model being updated over time.…”

“…It was often not clear whether large-scale studies included data of repeated measures, or if they were independent records. In handling missing values, 32% of studies used complete case analysis,21 22 26 27 31 32 34 39 28% imputed missing values,23–25 33 35 42 45 and one used a combination of both30; however, 36% of studies did not define any explicit methods 28 29 36–38 40 41 43 44. In defining outcomes, proxy measures were often used, for example exacerbation was often recorded as requirement of a medication, which can be biased towards clinician or centre treatment preferences.…”

“…These models are uninterpretable as it is unknown which of the hundreds of variables influenced clinically relevant poor outcomes for a particular person. Studies using smaller numbers often used clinical knowledge to select variables,22 23 25 29 31–33 36 excluded those with high missingness,24 35 42 or used various statistical techniques to ensure included variables were clinically relevant,38 39 41 45 which may allow for more interpretability.…”

2022 Year in review: Neonatal pulmonology

“…The use of VOC in adult asthma has not provided enough guidance to design studies in children: timing, sample handling, choice of analyte all vary a great deal in previously published studies 49,50. On the other hand, clinical exacerbations and decrements in spirometry in cystic fibrosis have recently been shown to correlate with increased exhaled VOCs 51. The use of VOC biomarkers of inflammation may help to improve the accuracy of interpretation of PFT results since interpretation of flow impairments could easily be confounded by concurrent airway inflammation.The reports in Pediatric Pulmonology in 2022 continued the theme of surveillance of lung function changes following neonatal perturbations such as preterm birth, mechanical ventilation, and growth restriction.…”