[Catheterization of the subclavian vein and the risk of pneumothorax : Mechanical ventilation increases the risk of pneumothorax during infraclavicular landmark-guided subclavian vein puncture: a prospective randomized study]

Quantitative Measurement of Pneumothorax Using Artificial Intelligence Management Model and Clinical Application

Artificial intelligence (AI) techniques can be a solution for delayed or misdiagnosed pneumothorax. This study developed, a deep-learning-based AI model to estimate the pneumothorax amount on a chest radiograph and applied it to a treatment algorithm developed by experienced thoracic surgeons. U-net performed semantic segmentation and classification of pneumothorax and non-pneumothorax areas. The pneumothorax amount was measured using chest computed tomography (volume ratio, gold standard) and chest radiographs (area ratio, true label) and calculated using the AI model (area ratio, predicted label). Each value was compared and analyzed based on clinical outcomes. The study included 96 patients, of which 67 comprised the training set and the others the test set. The AI model showed an accuracy of 97.8%, sensitivity of 69.2%, a negative predictive value of 99.1%, and a dice similarity coefficient of 61.8%. In the test set, the average amount of pneumothorax was 15%, 16%, and 13% in the gold standard, predicted, and true labels, respectively. The predicted label was not significantly different from the gold standard (p = 0.11) but inferior to the true label (difference in MAE: 3.03%). The amount of pneumothorax in thoracostomy patients was 21.6% in predicted cases and 18.5% in true cases.

[Complications and success rates of subclavian vein catheterization depending on experience]

BACKGROUND

The infraclavicular puncture of the subclavian vein is a standard procedure for anesthetists. Meanwhile the literature and recommendations are clear and the use of real-time ultrasound guidance is the standard procedure; however, anesthetists will always get into special circumstances were they have to use the landmark technique, so this competence must be preserved. Feared complications of infraclavicular subclavian vein puncture are pneumothorax and arterial puncture. Up to now there is no clear learning curve for the infraclavicular subclavian vein puncture in the landmark technique performed by anesthetists.

OBJECTIVE

The aim of this study was to examine the influence of the puncture experience on the success rate and mechanical complications, such as pneumothorax and arterial puncture in patients who received an infraclavicular subclavian vein puncture with the landmark technique. Three levels of experience were defined for comparison: inexperienced 0-20 punctures, moderately experienced 21-50 and experienced over 50 punctures.

MATERIAL AND METHODS

Post hoc analysis of a previously published noninferiority study to examine the influence of ventilation on the pneumothorax rate in the subclavian vein puncture using the landmark technique. This analysis included 1021 anesthetized patients who were included in the original study between August 2014 and October 2017. Demographic data as well as the number of puncture attempts, puncture success, the overall rate of mechanical complications, pneumothorax rate and arterial puncture rates were calculated.

RESULTS

The overall rate of mechanical complications (pneumothorax + arterial puncture) was significantly higher in the inexperienced group (0-21) compared to the experienced group (>50, 15% vs. 8.5%, respectively, p = 0.023). This resulted in an odds ratio of 0.52 (confidence interval, CI: 0.32-0.85, p = 0.027). Likewise, the rate of puncture attempts in the group of inexperienced (0-20) with 1.85 ± 1.12 was significantly higher than in the group of experienced (>50, 1.58 ± 0.99, p = 0.004) and resulted in an odds ratio of 0.59 (CI: 0.31-0.96, p = 0.028). Although the puncture attempts of the moderately experienced (21-50) compared to the inexperienced (0-20) was not significant lower, we found an odds ratio of 0.69 (CI: 0.48-0.99, p = 0.042). The rate of successful puncture was 95.1% in the experienced group versus 89.3% in the inexperienced group (p = 0.001), which resulted in an odds ratio of 2.35 (CI: 1.28-4.31, p = 0.018). When viewed individually, no significant differences were found for pneumothorax and arterial puncture.

CONCLUSION

In this post hoc analysis of the puncture of the subclavian vein using the landmark technique, we found a significant reduction of puncture attempts and overall mechanical complications. At least 50 punctures seem to be necessary to achieve the end of the learning curve; however, the landmark technique should only be used under special circumstances, when real-time ultrasound is not available. Anesthetists who want to complete their repertoire and learn the landmark technique should always perform a static ultrasound examination before starting the puncture in order to reduce complications due to anatomical variations or thrombosis.