Cannulation selection in relation to deep learning-based algorithm for the detection of thoracic aortic calcifications

Dear Editor,

Critical factors such as the choice of cannula, its anatomical positioning and the type of pump used (centrifugal versus roller pump) are essential considerations that can significantly influence surgical outcomes and should be explored further. Understanding the role of calcifications in the aortic clamping zone is crucial, but it is equally important to consider how these calcifications might impact the insertion and function of the cannula. Calcified regions can pose challenges for secure cannula placement and may increase the risk of dislodging plaques, potentially leading to embolic events. The recent article titled ‘Accuracy of a Deep Learning-Based Algorithm for the Detection of Thoracic Aortic Calcifications in Chest Computed Tomography and Cardiovascular Surgery Planning’ by R. Saffar et al. presents significant advancements in the application of deep learning for the automated detection of thoracic aortic calcifications, particularly in the aortic clamping zone. The study’s findings, highlighting a sensitivity of 93% and a specificity of 82% with an area under the receiver operating characteristic curve of 0.874, underscore the potential of this technology to enhance preoperative planning and improve patient outcomes [1]. Despite the promising results, the article does not sufficiently address the implications of these findings in the context of cannulation and fluid dynamics during cardiovascular surgery. Additionally, the study does not discuss how variations in calcification might affect the decision-making process regarding the use of centrifugal versus roller pumps, each having different flow characteristics and implications for patients with calcified aortas. In summary, while the study’s findings on the accuracy of the deep learning algorithm are encouraging, a more comprehensive discussion on the clinical application, including the nuances of cannulation techniques and the choice of pump systems, would provide a more holistic understanding and utility of the algorithm in cardiovascular surgery planning. Various surgical techniques have been described to reduce the risk of athero-embolism that may lead to cerebrovascular events in patients with severely atherosclerotic ascending aorta. In cases where severe atherosclerotic disease or other factors preclude safe use of the ascending aorta, modifications in the surgical techniques, such as switching to different cannulation sites including the axillary/subclavian, femoral and innominate arteries, or using hypothermic ventricular fibrillation [2]. Future research should consider these aspects to further enhance the clinical relevance and application of this innovative technology.

Conflict of interest: none declared.

REFERENCES