Precision of CT-derived alveolar recruitment assessed by human observers and a machine learning algorithm in moderate and severe ARDS

• Published in: Intensive care medicine experimental 2023-02, Vol.11 (1), p.8-8, Article 8
• Main Authors: Penarrubia, Ludmilla, Verstraete, Aude, Orkisz, Maciej, Davila, Eduardo, Boussel, Loic, Yonis, Hodane, Mezidi, Mehdi, Dhelft, Francois, Danjou, William, Bazzani, Alwin, Sigaud, Florian, Bayat, Sam, Terzi, Nicolas, Girard, Mehdi, Bitker, Laurent, Roux, Emmanuel, Richard, Jean-Christophe
• Format: Article
• Language: English
• Subjects: Acute respiratory distress syndrome; Alveolar recruitment; Bias; Computed tomography; Critical Care Medicine; Intensive; Intensive care; Life Sciences; Machine learning; Medical diagnosis; Medicine; Medicine & Public Health; Repeatability; Reproducibility; Respiratory distress syndrome; Tomography
• ISSN: 2197-425X; 2197-425X
• DOI: 10.1186/s40635-023-00495-6

Background Assessing measurement error in alveolar recruitment on computed tomography (CT) is of paramount importance to select a reliable threshold identifying patients with high potential for alveolar recruitment and to rationalize positive end-expiratory pressure (PEEP) setting in acute respiratory distress syndrome (ARDS). The aim of this study was to assess both intra- and inter-observer smallest real difference (SRD) exceeding measurement error of recruitment using both human and machine learning-made lung segmentation (i.e., delineation) on CT. This single-center observational study was performed on adult ARDS patients. CT were acquired at end-expiration and end-inspiration at the PEEP level selected by clinicians, and at end-expiration at PEEP 5 and 15 cmH 2 O. Two human observers and a machine learning algorithm performed lung segmentation. Recruitment was computed as the weight change of the non-aerated compartment on CT between PEEP 5 and 15 cmH 2 O. Results Thirteen patients were included, of whom 11 (85%) presented a severe ARDS. Intra- and inter-observer measurements of recruitment were virtually unbiased, with 95% confidence intervals (CI 95% ) encompassing zero. The intra-observer SRD of recruitment amounted to 3.5 [CI 95% 2.4–5.2]% of lung weight. The human–human inter-observer SRD of recruitment was slightly higher amounting to 5.7 [CI 95% 4.0–8.0]% of lung weight, as was the human–machine SRD (5.9 [CI 95% 4.3–7.8]% of lung weight). Regarding other CT measurements, both intra-observer and inter-observer SRD were close to zero for the CT-measurements focusing on aerated lung (end-expiratory lung volume, hyperinflation), and higher for the CT-measurements relying on accurate segmentation of the non-aerated lung (lung weight, tidal recruitment…). The average symmetric surface distance between lung segmentation masks was significatively lower in intra-observer comparisons (0.8 mm [interquartile range (IQR) 0.6–0.9]) as compared to human–human (1.0 mm [IQR 0.8–1.3] and human–machine inter-observer comparisons (1.1 mm [IQR 0.9–1.3]). Conclusions The SRD exceeding intra-observer experimental error in the measurement of alveolar recruitment may be conservatively set to 5% (i.e., the upper value of the CI 95% ). Human–machine and human–human inter-observer measurement errors with CT are of similar magnitude, suggesting that machine learning segmentation algorithms are credible alternative to humans for quantifying alveolar recruitment on CT.