Acute respiratory distress syndrome (ARDS) is a serious threat to human life and health disease, with acute onset and high mortality. The current diagnosis of the disease depends on blood gas analysis results, while calculating the oxygenation index. However, blood gas analysis is an invasive operation, and can’t continuously monitor the development of the disease. In response to the above problems, in this study, we proposed a new algorithm for identifying the severity of ARDS disease. Based on a variety of non-invasive physiological parameters of patients, combined with feature selection techniques, this paper sorts the importance of various physiological parameters. The cross-validation technique was used to evaluate the identification performance. The classification results of four supervised learning algorithms using neural network, logistic regression, AdaBoost and Bagging were compared under different feature subsets. The optimal feature subset and classification algorithm are comprehensively selected by the sensitivity, specificity, accuracy and area under curve (AUC) of different algorithms under different feature subsets. We use four supervised learning algorithms to distinguish the severity of ARDS (P/F ≤ 300). The performance of the algorithm is evaluated according to AUC. When AdaBoost uses 20 features, AUC = 0.832 1, the accuracy is 74.82%, and the optimal AUC is obtained. The performance of the algorithm is evaluated according to the number of features. When using 2 features, Bagging has AUC = 0.819 4 and the accuracy is 73.01%. Compared with traditional methods, this method has the advantage of continuously monitoring the development of patients with ARDS and providing medical staff with auxiliary diagnosis suggestions.
ObjectiveTo investigate the independent risk factors associated with postoperative acute respiratory distress syndrome in patients undergoing type A aortic dissection surgery.MethodsThe clinical data of 147 patients who underwent acute type A aortic dissection surgery in the First Affiliated Hospital of Anhui Medical University from 2015 to 2019 were retrospectively analyzed. There were 110 males at age of 51.9±10.1 years and 37 females at age of 54.3±11.1 years. According to whether the patients developed ARDS after surgery, all of the patients were divided into a ARDS group or a non-ARDS group. Logistic regress analysis was utilized to establish the predictive mode to identify the independent risk factors related to ARDS.ResultsOf the patients, 25 developed postoperative ARDS. Among them, 5 patients were mild ARDS, 13 patients were moderate, and 7 patients were severe ARDS. Multivariate logistic regression analysis showed that deep hypothermic circulatory arrest time [odds ratio (OR)=1.067, 95% confidence interval (CI) 1.014-1.124, P=0.013], cardiopulmonary bypass time (OR=1.012, 95%CI 1.001-1.022, P=0.027) and perioperative plasma input (OR=1.001, 95%CI 1.000-1.002, P=0.011) were independently associated with ARDS in patients undergoing acute A aortic dissection surgery. Receiver operating characteristic (ROC) curve analysis demonstrated a good discrimination ability of the logistic regression model, with an area under the curve of 0.835 (95%CI 0.740-0.929, P=0.000).ConclusionDuration of deep hypothermic circulatory arrest, cardiopulmonary bypass time and perioperative plasma are independent risk factors for postoperative ARDS in patients undergoing type A aortic dissection surgery.
Lung injury could be classified as acute and chronic injuries, such as acute respiratory distress syndrome and chronic obstructive pulmonary disease. Lung function recovery mainly depends on inflammation adjusting, lung and airway remodeling, endogenous stem cell proliferation and differentiation, and tissue repair. The principles of clinical therapy include inhibition of inflammation, balancing coagulation and fibrinolysis, and protective lung ventilation for acute lung injury; while reduction of hyper-secretion, bronchodilation, adjusting airway mucosal inflammation and immunity, as well as improving airway remodeling for chronic obstructive pulmonary disease. The functional recovery of lung and airway depends on endogenous stem cell proliferation and repair. The purpose of clinical treatment is to provide assistance for lung and airway repair besides pathophysiological improvement.
Objective To evaluate the efficacy of pulmonary surfactant (PS) on severe acute respiratory distress syndrome (ARDS) in different age baby with congenital heart disease. Methods We divided 43 baby patients into two separate groups including a little baby group (12 patients with age less than 3 months) and an infants group (31 patients with age of 3 months to one year). Both groups of patients were treated with intratracheal PS at the same time. The clinical data were collected and analyzed. Results The little baby group had lower body weight. There was no statistical difference in the cardiopulmonary bypass (CPB) time, operation blocking time, mechanical ventilation time, ICU stay time between the two groups (P>0.05). Before treatment, arterial partial presurre of oxygen (PaO2), fractional oxygen concentration in inspire gas (FiO2), the ratio of arterial PO2 to the inspired oxygen fraction (P/F) and arterial-alveolar N2 difference or gradient (a/A) had no difference between the two groups (P>0.05). After treatment, PaO2 and P/F of both groups were significantly lower than before (P<0.05), and FiO2 and P/F were significantly higher than before (P<0.05). After 24 h of treatment, PaO2 and P/F of the little baby group was significantly higher than that of the infants group (P<0.05), and FiO2 and P/F were significantly lower than those of the infants group (P<0.05). Conclusion PS treating severe ARDS in little baby with congenital heart disease has better effect than infants.
As an extracorporeal life support technology, veno-venous extracorporeal membrane oxygenation (VV-ECMO) has been demonstrated its role in the treatment of patients with severe respiratory failure. Its main advantages include the ability to maintain adequate oxygenation and remove excess CO2, increase oxygen delivery, improve tissue perfusion and metabolism, and implement lung protection strategies. Clinicians should accurately assess and identify the patient's condition, timely and accurately carry out VV-ECMO operation and management. This article will review the patient selection, cannulation strategy, anticoagulation, clinical management and weaning involved in the application of VV-ECMO.
A novel coronavirus (SARS-CoV-2) that broke out at the end of 2019 is a newly discovered highly pathogenic human coronavirus and has some similarities with severe acute respiratory syndrome coronavirus (SARS-CoV). Angiotensin-converting enzyme 2 (ACE2) is the receptor for infected cells by SARS-CoV. SARS-CoV can invade cells by binding to ACE2 through the spike protein and SARS-CoV-2 may also infect cells through ACE2. Meanwhile, ACE2 also plays an important role in the course of pneumonia. Therefore the possible role of ACE2 in SARS and coronavirus disease 2019 (COVID-19) is worth discussing. This paper briefly summarized the role of ACE2 in SARS, and discussed the possible function of ACE2 in COVID-19 and potential risk of infection with other organs. At last, the function of ACE2 was explored for possible treatment strategies for SARS. It is hoped to provide ideas and theoretical support for clinical treatment of COVID-19.
Objective To investigated the early risk factors of AIDS severe pneumonia complicated with acute respiratory distress syndrome in order to carry out early recognition and intervention of ARDS and improve the prognosis of patients. Methods The clinical data of 232 patients with severe AIDS pneumonia admitted to Chengdu Public Health Clinical Medical Center from January 2017 to December 2020 were retrospectively analyzed, including general data, vital signs, laboratory examination indexes, basic diseases, etc. Firstly influential indexes for complicated with ARDS were screened by single factor logistic regression analysis, then the multicollinearity assessment indicators were filtered out in multi-factor logistic stepwise regression analysis, finally the receiver operating characteristic (ROC) curves were drawn and the predictive value of the indicators were assessed. Results Thirty-three of 232 AIDS patients with severe pneumonia were complicated with ARDS. The mortality rate in ARDS group was 81.8%. The intra-group mortality of non-ARDS group was 33.7%. Single factor logistic regression analysis showed that pH, acute physiology and chronic health evaluation Ⅱ grade, sequential organ failure assessment grade, white blood cell count, lactate dehydrogenase, α-hydroxybutyric acid dehydrogenase (α-HBDH), alanine aminotransferase (ALT), aspartic acid aminotransferase (AST), calcium, fibrinogen degradation produc (FDP) and D-dimer, total 11 indicators were associated with the incidence of ARDS. The multicollinearity analysis of the 11 indicators showed that there was no multicollinearity problem among the other 9 indicators except the variance inflation factor of ALT and AST which was greater than 10. Multivariate logistic stepwise regression analysis showed α-HBDH (OR=1.001, 95% confidence interval 1.000 - 1.002, P=0.045) and D-dimer (OR=1.044, 95% confidence interval 1.006 - 1.083, P=0.024) were independent factors. ROC curve indicated the following: alpha hydroxy butyric acid dehydrogenase (the area under ROC curve=0.667, P=0.002, the optimal threshold was 391 U/L, the corresponding sensitivity and specificity was 78.8% and 61.8%, respectively), D-dimer (the area under ROC curve=0.602, P=0.062, the optimal threshold was 4.855 μg/mL, the corresponding sensitivity and specificity was 42.4% and 82.9%, respectively). Conclusion AIDS severe pneumonia complicated with ARDS is associated with many factors, among whichα-HBDH (≥391 U/L) and D-dimer (≥ 4.855 μg/mL) on admission are independent risk factors, which have great early predictive value and can provide reference for early clinical identification of ARDS high-risk patients.
ObjectiveTo develop a predictive model for acute respiratory distress syndrome (ARDS) following cardiac mechanical valve replacement under cardiopulmonary bypass (CPB) using artificial intelligence algorithms, providing a novel method for early identification of high-risk ARDS patients. MethodsPatients undergoing CPB-assisted cardiac mechanical valve replacement surgery in the Department of Cardiovascular Surgery at the First Hospital of Lanzhou University from January 2023 to March 2025 were retrospectively and consecutively enrolled. Data processing and model construction were performed using Python software. Variables with missing data proportions ≥30% were excluded, while multiple imputation combined with sensitivity analysis and standardization was applied to the remaining dataset. The dataset was randomly partitioned into training (70%) and testing (30%) sets. Feature selection was conducted using the Boruta algorithm and least absolute shrinkage and selection operator regression. The synthetic minority over-sampling technique edited nearest neighbors (SMOTEEN) algorithm was applied to balance samples in the training set. Six machine learning models, including random forest, light gradient boosting machine, extreme gradient boosting, categorical boosting (CatBoost), gradient boosting decision tree, and logistic regression, were developed through 5-fold nested cross-validation for parameter optimization. Model performance was evaluated via area under the receiver operating characteristic curve (AUC), sensitivity, specificity, accuracy, average precision, recall rate, and F1 score. The optimal model was determined based on AUC values and validated through Hosmer-Lemeshow (HL) goodness-of-fit test. Decision curve analysis was performed for all models, while SHAP algorithm was employed for feature interpretation and visualization. External validation was conducted using clinical data from patients who underwent CPB-assisted mechanical valve replacement between April 1 and October 1, 2025. ResultsA total of 352 patients were included [training set: n=246, 135 males, 111 females, aged (51.71±11.03) years; testing set: n=106, 62 males, 44 females, aged (53.27±9.67) years], with 34 (9.7%) patients developing early ARDS in ICU. Key predictors included cardioplegia duration, right atrial transverse diameter, right ventricular transverse diameter, indirect bilirubin, and rewarming time. The CatBoost model demonstrated superior performance (AUC=0.828) with HL test P=0.64. In the single-center temporal validation cohort [n=41, 25 males, 16 females, aged (52.18±10.56) years], the CatBoost model achieved AUC=0.771. ConclusionCardiac arrest duration, right atrial transverse diameter, right ventricular transverse diameter, indirect bilirubin, and rewarming time are identified as critical factors influencing postoperative ARDS development after CPB-assisted mechanical valve replacement. The CatBoost model exhibits excellent accuracy, consistency, and clinical applicability.
Since the beginning of the coronavirus disease 2019 (COVID-19) pandemic at the end of December 2019, more than 85% of the population in China has been infected. Severe acute respiratory syndrome coronavirus 2 (SARS-CoV-2) mainly affects the respiratory system, especially the lungs. The mortality rate of patients with severe infection is high. A percentage of 6% to 10% of patients will eventually develop into COVID-related acute respiratory distress syndrome (CARDS), which requires mechanical ventilation and extracorporeal membrane oxygenation (ECMO) support. Some patients who survive acute lung injury will subsequently develop post COVID-19 pulmonary fibrosis (PCPF). Both fully treated CARDS and severe PCPF are suitable candidates for lung transplantation. Due to the special course, evaluation strategies are different from those used in patients with common end-stage lung disease. After lung transplantation in COVID-19 patients, special treatment is required, including standardized nucleic acid testing for the novel coronavirus, adjustment strategy of immunosuppressive drugs, and rational use of antiviral drugs, which is a big challenge for the postoperative management of lung transplantation. This consensus was evidence-based written and was reached by experts after multiple rounds of discussions, providing reference for assessment and postoperative management of patients with interstitial pneumonia after COVID-19 infection.
急性肺損傷（ALI）和急性呼吸窘迫綜合征（ARDS）是指由心源性以外的各種肺內外致病因素所導致的急性進行性缺氧性呼吸衰竭，它們具有性質相同的病理生理改變，嚴重的ALI或ALI的最終嚴重階段被定義為ARDS，臨床表現以呼吸窘迫、頑固性低氧血癥和非心源性肺水腫為特征，采用常規的治療難以糾正其低氧血癥，死亡率高達60%。目前，有關ALI/ARDS的研究取得較多進展，其中，能有效評估ALI病情和預測死亡率的臨床參數和生化指標一直是研究熱點。