Dataset Information

Inflammatory signature-based theranostics for acute lung injury in acute type A aortic dissection.

ABSTRACT: Acute lung injury (ALI) is a serious adverse event in the management of acute type A aortic dissection (ATAAD). Using a large-scale cohort, we applied artificial intelligence-driven approach to stratify patients with different outcomes and treatment responses. A total of 2,499 patients from China 5A study database (2016-2022) from 10 cardiovascular centers were divided into 70% for derivation cohort and 30% for validation cohort, in which extreme gradient boosting algorithm was used to develop ALI risk model. Logistic regression was used to assess the risk under anti-inflammatory strategies in different risk probability. Eight top features of importance (leukocyte, platelet, hemoglobin, base excess, age, creatinine, glucose, and left ventricular end-diastolic dimension) were used to develop and validate an ALI risk model, with adequate discrimination ability regarding area under the receiver operating characteristic curve of 0.844 and 0.799 in the derivation and validation cohort, respectively. By the individualized treatment effect prediction, ulinastatin use was significantly associated with significantly lower risk of developing ALI (odds ratio [OR] 0.623 [95% CI 0.456, 0.851]; P = 0.003) in patients with a predicted ALI risk of 32.5-73.0%, rather than in pooled patients with a risk of <32.5 and >73.0% (OR 0.929 [0.682, 1.267], P = 0.642) (Pinteraction = 0.075). An artificial intelligence-driven risk stratification of ALI following ATAAD surgery were developed and validated, and subgroup analysis showed the heterogeneity of anti-inflammatory pharmacotherapy, which suggested individualized anti-inflammatory strategies in different risk probability of ALI.

SUBMITTER: Liu H

PROVIDER: S-EPMC11373310 | biostudies-literature | 2024 Sep

REPOSITORIES: biostudies-literature

ACCESS DATA

Publications

Inflammatory signature-based theranostics for acute lung injury in acute type A aortic dissection.

Liu Hong H Diao Yi-Fei YF Qian Si-Chong SC Shao Yong-Feng YF Zhao Sheng S Li Hai-Yang HY Zhang Hong-Jia HJ

PNAS nexus 20240827 9

Acute lung injury (ALI) is a serious adverse event in the management of acute type A aortic dissection (ATAAD). Using a large-scale cohort, we applied artificial intelligence-driven approach to stratify patients with different outcomes and treatment responses. A total of 2,499 patients from China 5A study database (2016-2022) from 10 cardiovascular centers were divided into 70% for derivation cohort and 30% for validation cohort, in which extreme gradient boosting algorithm was used to develop A ...[more]

PMID: 39234501

Similar Datasets

Project description:Introduction: Acute aortic dissection (AAD) often leads to the development of acute lung injury (ALI). However, the early detection and diagnosis of AAD in patients with ALI pose significant challenges. The objective of this study is to investigate distinct metabolic alterations in the plasma samples of AAD patients with ALI, AAD patients without ALI, and healthy individuals. Method: Between September 2019 and September 2022, we retrospectively collected data from 228 AAD patients who were diagnosed with ALI through post-surgery chest X-ray and PaO2/FiO2 assessments. Univariate analysis was employed to identify pre-surgery risk factors for ALI. Additionally, we conducted high-throughput target metabolic analysis on 90 plasma samples, comprising 30 samples from AAD patients with ALI, 30 from patients with AAD only, and 30 from healthy controls. After LC-MS spectral processing and metabolite quantification, the recursive feature elimination with cross-validation (RFECV) analysis based on the random forest was used to select the optimal metabolites as a diagnostic panel for the detection of AAD patients with ALI. The support vector machines (SVM) machine learning model was further applied to validate the diagnostic accuracy of the established biomarker panel. Results: In the univariate analysis, preoperative β-HB and TNF-α exhibited a significant association with lung injury (OR = 0.906, 95% CI 0.852-0.965, p = 0.002; OR = 1.007, 95% CI 1.003-1.011, p < 0.0001). The multiple-reaction monitoring analysis of 417 common metabolites identified significant changes in 145 metabolites (fold change >1.2 or <0.833, p < 0.05) across the three groups. Multivariate statistical analysis revealed notable differences between AAD patients and healthy controls. When compared with the non-ALI group, AAD patients with ALI displayed remarkable upregulation in 19 metabolites and downregulation in 4 metabolites. Particularly, combining citric acid and glucuronic acid as a biomarker panel improved the classification performance for distinguishing between the ALI and non-ALI groups. Discussion: Differentially expressed metabolites in the ALI group were primarily involved in amino acids biosynthesis, carbohydrate metabolism (TCA cycle), arginine and proline metabolism, and glucagon signaling pathway. These findings demonstrate a great potential of the targeted metabolomic approach for screening, routine surveillance, and diagnosis of pulmonary injury in patients with AAD.

Project description:ObjectiveThe study objective was to assess the radiological properties of acute type A aortic dissection-related neurological injuries and identify predictors of neurological injury.MethodsOur single-center, retrospective, observational study included all patients who underwent acute type A aortic dissection repair between January 1998 and December 2021. Multivariable analyses and Cox regression were performed to identify predictors of embolic lesions, watershed lesions, neurological injury, 30-day mortality, and late mortality.ResultsA total of 538 patients were included. Of these, 120 patients (22.3%) experienced postoperative neurological injury; 74 patients (13.8%) had postoperative stroke, and 36 patients (6.8%) had postoperative coma. The 30-day mortality was 22.7% in the neurological injury group versus 5.8% in the no neurological injury group (P < .001). We identified several independent predictors of neurological injury. Cerebral malperfusion (odds ratio, 2.77; 95% confidence interval, 1.53-5.00), systemic hypotensive shock (odds ratio, 1.97; 95% confidence interval, 1.13-3.43), and aortic arch replacement (odds ratio, 3.08; 95% confidence interval, 1.17-8.08) predicted embolic lesions. Diabetes mellitus (odds ratio, 5.35; 95% confidence interval, 1.85-15.42), previous cardiac surgery (odds ratio, 8.62; 95% confidence interval, 1.47-50.43), duration of hypothermic circulatory arrest (odds ratio, 1.05; 95% confidence interval, 1.01-1.08), cardiopulmonary bypass time (odds ratio, 1.01; 95% confidence interval, 1.00-1.01), ascending aortic/arch cannulation (odds ratio, 5.68; 95% confidence interval, 1.88-17.12), and left ventricular cannulation (odds ratio, 17.81; 95% confidence interval, 1.69-188.01) predicted watershed lesions. Retrograde cerebral perfusion (odds ratio, 0.28; 95% confidence interval, 0.01-0.84) had a protective effect against watershed lesions.ConclusionsIn this study, we demonstrated that the radiological features of neurological injury may be as important as clinical characteristics in understanding the pathophysiology and causality behind neurological injury related to acute type A aortic dissection repair.

Project description:ObjectiveWe aimed to explore the application value of unsupervised machine learning in identifying acute gastrointestinal injury (AGI) after extracorporeal circulation for acute type A aortic dissection (ATAAD).MethodsPatients who underwent extracorporeal circulation for ATAAD at the First Hospital of Lanzhou University from January 2016 to January 2021 were included. Unsupervised machine learning algorithm was used to stratify patients into different phenogroups according to the similarity of their clinical features and laboratory test results. The differences in the incidence of perioperative AGI and other adverse events among different phenogroups were compared. Logistic regression was used to analyze the high-risk factors for AGI in each phenogroups and random forest (RF) algorithms were used to construct diagnostic models for AGI in different phenogroups.ResultsA total of 188 patients were included, with 166 males and 22 females. Unsupervised Machine Learning stratified patients into three phenogroups (phenogroup A, B, and C). Compared with other phenogroups, phenogroup B patients were older (P < 0.01), had higher preoperative lactate and D-dimer levels, and had the highest incidence of AGI (52.5%, P < 0.001) and in-hospital mortality (18.6%, P = 0.002). The random forest model showed that the top four risk factors for AGI in phenogroup B were cardiopulmonary bypass time, operation time, aortic clamping time, and ventilator time, which were significantly different from other phenogroups. The areas under the curve (AUCs) for diagnosing postoperative AGI of phenogroup A, B, and C were 0.943 (0.854-0.992), 0.990 (0.966-1.000), and 0.964 (0.899-0.997) using the RF model, respectively.ConclusionPhenogroup stratification based on unsupervised learning can accurately identify high-risk populations for postoperative AGI in ATAAD, providing a new approach for implementing individualized preventive and therapeutic measures in clinical practice.

Dataset Information

Inflammatory signature-based theranostics for acute lung injury in acute type A aortic dissection.

Publications

Inflammatory signature-based theranostics for acute lung injury in acute type A aortic dissection.

Similar Datasets

OmicsDI is part of the ELIXIR infrastructure

Tweets