A fully-automatic semi-supervised deep learning model for difficult airway assessment.

Background: Difficult airway conditions represent a substantial challenge for clinicians. Predicting such conditions is essential for subsequent treatment planning, but the reported diagnostic accuracies are still quite low. To overcome these challenges, we developed a rapid, non-invasive, cost-effective, and highly-accurate deep-learning approach to identify difficult airway conditions through photographic image analysis. Methods: For each of 1000 patients scheduled for elective surgery under general anesthesia, images were captured from 9 specific and different viewpoints. The collected image set was divided into training and testing subsets in the ratio of 8:2. We used a semi-supervised deep-learning method to train and test an AI model for difficult airway prediction. Results: We trained our semi-supervised deep-learning model using only 30% of the labeled training samples (with the remaining 70% used without labels). We evaluated the model performance using metrics of accuracy, sensitivity, specificity, F1-score, and the area under the ROC curve (AUC). The numerical values of these four metrics were found to be 90.00%, 89.58%, 90.13%, 81.13%, and 0.9435, respectively. For a fully-supervised learning scheme (with 100% of the labeled training samples used for model training), the corresponding values were 90.50%, 91.67%, 90.13%, 82.25%, and 0.9457, respectively. When three professional anesthesiologists conducted comprehensive evaluation, the corresponding results were 91.00%, 91.67%, 90.79%, 83.26%, and 0.9497, respectively. It can be seen that the semi-supervised deep learning model trained by us with only 30% labeled samples can achieve a comparable effect with the fully supervised learning model, but the sample labeling cost is smaller. Our method can achieve a good balance between performance and cost. At the same time, the results of the semi-supervised model trained with only 30% labeled samples were very close to the performance of human experts. Conclusions: To the best of our knowledge, our study is the first one to apply a semi-supervised deep-learning method in order to identify the difficulties of both mask ventilation and intubation. Our AI-based image analysis system can be used as an effective tool to identify patients with difficult airway conditions. Clinical trial registration: ChiCTR2100049879 (URL: http://www.chictr.org.cn).

The protective effects of Omarigliptin against Lipopolysaccharide (LPS)- induced inflammatory response and expression of mucin 5AC (MUC5AC) in human bronchial epithelial cells.

The epidemic of chronic inflammatory lung diseases such as asthma, bronchitis, and chronic obstructive pulmonary disease (COPD) has become a global public health problem. Oxidative stress, inflammation, and overproduction of airway mucus play critical roles in the progression of these diseases. Omarigliptin, an oral dipeptidyl peptidase 4 (DPP-4) inhibitor, has been demonstrated to have anti-inflammatory effects in patients with type II diabetes. However, its role in chronic inflammatory lung diseases remains enigmatic. This study is to investigate whether Omarigliptin possesses a beneficial effect against Lipopolysaccharide (LPS)-induced injuries in human BEAS-2B bronchial epithelial cells. Our results show that Omarigliptin suppressed LPS-induced oxidative stress by attenuating the generation of mitochondrial reactive oxygen species (ROS) and decrease in reduced glutathione (GSH) in BEAS-2B cells. Additionally, Omarigliptin mitigated inflammatory response by inhibiting the expression of pro-inflammatory mediators, including interleukin-1ß (IL-1ß), interleukin-12 (IL-12), and macrophage chemoattractant protein-1 (MCP-1) in LPS-challenged BEAS-2B cells. Moreover, Omarigliptin mitigated the LPS-induced overproduction of MUC5AC by rescuing the expression of the suppressor of cytokine signaling 1(SOCS1). Importantly, we found that this process is mediated by the Adenosine 5'-monophosphate (AMP)-activated protein kinase (AMPK) signaling pathway. Based on these findings, we conclude that Omarigliptin might be a promising agent for the treatment of chronic inflammatory lung diseases.

[Comparison of the efficacy of different venous intubation in venous-arterial extracorporeal membrane oxygenation assisted lung transplantation].

OBJECTIVE: To compare the curative effects of different venous cannulas and drainage to improve patient's whole body oxygenation during the auxiliary process of venous-arterial extracorporeal membrane oxygenation (VA-ECMO) in lung transplantation. METHODS: From December 2016 to December 2019, 12 patients who were assisted by VA-ECMO in one lung transplantation in People's Hospital of Henan Province were selected as the research objects. According to the number of side holes of venous cannulas, they were divided into two groups: one group with few side holes and other group with multiple side holes. The differences in blood gas indexes among the right radial artery, left radial artery, and right internal jugular vein before and after assistance were compared, and the assistance effect was evaluated. RESULTS: The arterial partial pressure of oxygen (PaO2) of blood gas indexes of the right and left radial arteries in both groups were significantly higher than that before assistance [mmHg (1 mmHg = 0.133 kPa): right and left radial artery in few side holes group: 79.5±4.2 vs. 48.3±3.8 and 88.1±3.5 vs. 48.3±3.8; right and left radial artery in multiple side holes group: 67.7±5.9 vs. 48.7±3.2 and 84.0±3.8 vs. 48.7±3.2, all P < 0.05]. The arterial partial pressure of carbon dioxide (PaCO2) of blood gas index was significantly lower than that before assistance (mmHg: 44.2±2.6 vs. 71.7±4.4 for the right radial artery and 44.7±1.4 vs. 71.7±4.4 for the left radial artery in the group with few side holes; 46.2±2.1 vs. 71.2±3.5 for the right radial artery and 44.1±1.9 vs. 71.2±3.5 for the left radial artery in the group with multiple side holes, all P < 0.05). The partial pressure of oxygen in venous blood (PvO2) of blood gas index of ECMO system in the group with few side holes was significantly lower than that of the multiport side holes group (mmHg: 56.4±3.2 vs. 88.7±1.5, P < 0.01), and the partial pressure of carbon dioxide in venous blood (PvCO2) was significantly higher than that of multiport side holes group (mmHg: 63.6±3.7 vs. 44.2±1.7, P < 0.01). CONCLUSIONS: When VA-ECMO is used in lung transplantation, the superior vena cava blood flow can be fully drained by using intravenous cannula with few side holes. It can effectively improve the oxygenation of the upper body of lung transplant patients, avoid the dilemma of hypoxemia in the upper body and hyperxemia in the lower body, provide more effective assistance to patients undergoing single lung transplantation, and is more meaningful for improving the oxygenation status of the whole body in patients undergoing single lung transplantation.