How many lung function interpretations can an expert make in one hour based on the 2021 ERS/ATS standards?
Rationale:
New 2021 ERS/ATS standards for PFT interpretation introduce new decision trees and the use of Z-scores instead of predicted percentages to better reflect the population variation. This adds more granularity and precision, but also more complexity. This study investigates the speed at which an expert can perform PFT interpretations.
Methods:
Five experts and automatic software (ArtiQ.PFT) classified as many patients as possible in one uninterrupted hour following the 2021 ERS/ATS standards. They commented on spirometry, lung volume and diffusion, lung function, diffusion severities and bronchodilator response (BDR). Participants were allowed to consult the publication.
Results:
Experts classified on average 18 cases in 1 hour (3.3 min/cases) with a mean accuracy of 80% (Table) whereas software correctly classified five patients per second. The assessment of spirometry, lung volumes and diffusion was better than evaluation of severities. The large standard deviations reveal variations between experts.
Concluson:
This exploratory study shows that 2021 ERS/ATS standards require significant time from experts and are prone to inter-rater variability, whereas automatic software is accurate, consistent and fast.
Table
| Mean ± std (%) | |
| Number of patients in 1h | 18 ± 6 |
| Spirometry interpretation (fig 8*) | 91 ± 10 |
| Bronchodilator response | 89 ± 12 |
| Lung volumes interpretation (fig 10*) | 75 ± 17 |
| Lung function severity | 66 ± 17 |
| Diffusion interpretation (fig 11*) | 91 ± 10 |
| Diffusion severity |
|
| *from (Stanojevic et al., 2021) | |
Authors:
P. Desbordes, J. Maes, Stachowicz, J. Kaspers, R. Arfoosh, M. Malik, M. Hegewald, M. De Vos, M. Topalovic
Affiliations:
[1] ArtiQ NV, Leuven, BE
[2] Vyaire Medical, USA
[3] Pulmonary and Sleep Specialists of NEGA, USA
[4] Division of Pulmonary and Critical Care Medicine, Intermountain Medical Center, University of Utah, USA