Analysis of pulmonary function tests (PFTs) is an area where machine learning (ML) may benefit clinicians, researchers, and the patients. PFT measures spirometry, lung volumes, and carbon monoxide diffusion capacity of the lung (DLCO). The results are usually interpreted by the clinicians using discrete numeric data according to published guidelines. PFT interpretations by clinicians, however, are known to have inter-rater variability and the inaccuracy can impact patient care. This variability may be caused by unfamiliarity of the guidelines, lack of training, inadequate understanding of lung physiology, or simply mental lapses. A rules-based automated interpretation system can recapitulate expert’s pattern recognition capability and decrease errors. ML can also be used to analyze continuous data or the graphics, including the flow-volume loop, the DLCO and the nitrogen washout curves. These analyses can discover novel physiological biomarkers. In the era of wearables and telehealth, particularly with the COVID-19 pandemic restricting PFTs to be done in the clinical laboratories, ML can also be used to combine mobile spirometry results with an individual’s clinical profile to deliver precision medicine. There are, however, hurdles in the development and commercialization of the ML-assisted PFT interpretation programs, including the need for high quality representative data, the existence of different formats for data acquisition and sharing in PFT software by different vendors, and the need for collaboration amongst clinicians, biomedical engineers, and information technologists. Hurdles notwithstanding, the new developments would represent significant advances that could be the future of PFT, the oldest test still in use in clinical medicine.
Excessive decrease in the flow of the late expiratory portion of a flow volume loop (FVL) or “flattening”, reflects small airway dysfunction. The assessment of the flattening is currently determined by visual inspection by the pulmonary function test (PFT) interpreters and is highly variable. In this study, we developed an objective measure to quantify the flattening. We downloaded 172 PFT reports in PDF format from the electronic medical records and digitized and extracted the expiratory portion of the FVL. We located point A (the point of the peak expiratory flow), point B (the point corresponding to 75% of the expiratory vital capacity), and point C (the end of the expiratory portion of the FVL intersecting with the x-axis). We did a linear fitting to the A-B segment and the B-C segment. We calculated: 1) the AB-BC angle (∠ABC), 2) BC-x-axis angle (∠BCX), and 3) the log ratio of the BC slope over the vertical distance between point A and x-axis [log (BC/A-x)]. We asked an expert pulmonologist to assess the FVLs and separated the 172 PFTs into the flattening and the non-flattening groups. We defined the cutoff value as the mean minus one standard deviation using data from the non-flattening group. ∠ABC had the best concordance rate of 80.2% with a cutoff value of 149.7°. We then asked eight pulmonologists to evaluate the flattening with and without ∠ABC in another 168 PFTs. The Fleiss’ kappa was 0.320 (lower and upper confidence intervals [CIs]: 0.293 and 0.348 respectively) without ∠ABC and increased to 0.522 (lower and upper CIs: 0.494 and 0.550) with ∠ABC. There were 147 CT scans performed within 6 months of the 172 PFTs. Twenty-six of 55 PFTs (47.3%) with ∠ABC <149.7° had CT scans showing small airway disease patterns while 44 of 92 PFTs (47.8%) with ∠ABC ≥149.7° had no CT evidence of small airway disease. We concluded that ∠ABC improved the inter-rater agreement on the presence of the late expiratory flattening in FVL. It could be a useful addition to the assessment of small airway disease in the PFT interpretation algorithm and reporting.
scite is a Brooklyn-based organization that helps researchers better discover and understand research articles through Smart Citations–citations that display the context of the citation and describe whether the article provides supporting or contrasting evidence. scite is used by students and researchers from around the world and is funded in part by the National Science Foundation and the National Institute on Drug Abuse of the National Institutes of Health.
hi@scite.ai
10624 S. Eastern Ave., Ste. A-614
Henderson, NV 89052, USA
Copyright © 2024 scite LLC. All rights reserved.
Made with 💙 for researchers
Part of the Research Solutions Family.