Machine learning-based prognostic model for in-hospital mortality of aortic dissection: Insights from an intensive care medicine perspective.

Objective: Aortic dissection (AD) is a severe emergency with high morbidity and mortality, necessitating strict monitoring and management. This retrospective study aimed to identify prognostic factors and establish predictive models for in-hospital mortality among AD patients in the intensive care unit (ICU). Methods: We retrieved ICU admission records of AD patients from the Medical Information Mart for Intensive Care (MIMIC)-IV critical care data set and the eICU Collaborative Research Database. Functional data analysis was further applied to estimate continuous vital sign processes, and variables associated with in-hospital mortality were identified through univariate analyses. Subsequently, we employed multivariable logistic regression and machine learning techniques, including simple decision tree, random forest (RF), and eXtreme Gradient Boosting (XGBoost) to develop prognostic models for in-hospital mortality. Results: Given 643 ICU admissions from MIMIC-IV and 501 admissions from eICU, 29 and 28 prognostic factors were identified from each database through univariate analyses, respectively. For prognostic model construction, 507 MIMIC-IV admissions were divided into 406 (80%) for training and 101 (20%) for internal validation, and 87 eICU admissions were included as an external validation group. Of the four models tested, the RF consistently exhibited the best performance among different variable subsets, boasting area under the receiver operating characteristic curves of 0.870 and 0.850. The models highlighted the mean 24-h fluid intake as the most potent prognostic factor. Conclusions: The current prognostic models effectively forecasted in-hospital mortality among AD patients, and they pinpointed noteworthy prognostic factors, including initial blood pressure upon ICU admission and mean 24-h fluid intake.

Integrative multi-omics analyses reveal vesicle transport as a potential target for thoracic aortic aneurysm.

BACKGROUND: Thoracic aortic aneurysm (TAA) refers to dilation and enlargement of the thoracic aorta caused by various reasons. Most patients have no apparent symptoms in the early stage and are subject to a poor prognosis once the aneurysm ruptures. It is crucial to identify individuals who are predisposed to TAA and to discover effective therapeutic targets for early intervention. METHODS: We conducted a label-free quantitative proteomic analysis among aorta tissue samples from TAA patients to screen differentially expressed proteins (DEPs) and key co-expression modules. Two datasets from Gene Expression Omnibus (GEO) database were included for integrative analysis, and the identified genes were subjected to immunohistochemistry (IHC) validation. Detailed vesicle transport related enrichment analysis was conducted and two FDA-approved drugs, chlorpromazine (CPZ) and chloroquine (CQ), were selected for in vivo inhibition of vesicle transport in mice TAA model. The diameter of thoracic aorta, mortality and histological differences after interventions were evaluated. RESULTS: We found significant enrichments in functions involved with vesicle transport, extracellular matrix organizing, and infection diseases in TAA. Endocytosis was the most essential vesicle transport process in TAA formation. Interventions with CPZ and CQ significantly reduced the aneurysm diameter and elastin degradation in vivo and enhanced the survival rates of TAA mice. CONCLUSIONS: We systematically screened the aberrantly regulated bioprocesses in TAA based on integrative multi-omics analyses, identified and demonstrated the importance of vesicle transport in the TAA formation. Our study provided pilot evidence that vesicular transport was a potential and promising target for the treatment of TAA.

NINJ1 Facilitates Abdominal Aortic Aneurysm Formation via Blocking TLR4-ANXA2 Interaction and Enhancing Macrophage Infiltration.

Abdominal aortic aneurysm (AAA) is a common and potentially life-threatening condition. Chronic aortic inflammation is closely associated with the pathogenesis of AAA. Nerve injury-induced protein 1 (NINJ1) is increasingly acknowledged as a significant regulator of the inflammatory process. However, the precise involvement of NINJ1 in AAA formation remains largely unexplored. The present study finds that the expression level of NINJ1 is elevated, along with the specific expression level in macrophages within human and angiotensin II (Ang II)-induced murine AAA lesions. Furthermore, Ninj1flox/flox and Ninj1flox/floxLyz2-Cre mice on an ApoE-/- background are generated, and macrophage NINJ1 deficiency inhibits AAA formation and reduces macrophage infiltration in mice infused with Ang II. Consistently, in vitro suppressing the expression level of NINJ1 in macrophages significantly restricts macrophage adhesion and migration, while attenuating macrophage pro-inflammatory responses. Bulk RNA-sequencing and pathway analysis uncover that NINJ1 can modulate macrophage infiltration through the TLR4/NF-κB/CCR2 signaling pathway. Protein-protein interaction analysis indicates that NINJ1 can activate TLR4 by competitively binding with ANXA2, an inhibitory interacting protein of TLR4. These findings reveal that NINJ1 can modulate AAA formation by promoting macrophage infiltration and pro-inflammatory responses, highlighting the potential of NINJ1 as a therapeutic target for AAA.