In 2016, the SOFA score was proposed as the main evaluation system for diagnosis in the definition of sepsis 3.0, and the SOFA score has become a new research focus in sepsis. Some people are skeptical about diagnosing sepsis using the SOFA score. Experts and scholars from different regions have proposed different, modified versions of SOFA score to make up for the related problems with the use of the SOFA score in the diagnosis of sepsis. While synthesizing the different improved versions of SOFA proposed by experts and scholars in various regions, this paper also summarizes the relevant definitions of sepsis put forward in recent years to build a clear, improved application framework of SOFA score. In addition, the comparison between machine learning and SOFA scores related to sepsis is described and discussed in the article. Taken together, by summarizing the application of the improved SOFA score proposed in recent years in the related definition of sepsis, we believe that the SOFA score is still an effective means of diagnosing sepsis, but in the process of the continuous refinement and development of sepsis in the future, the SOFA score needs to be further refined and improved to provide more accurate coping strategies for different patient populations or application directions regarding sepsis. Against the big data background, machine learning has immeasurable value and significance, but its future applications should add more humanistic references and assistance.

(1) Background: Both sepsis acute lung injury (SALI) and non-small-cell lung cancer (NSCLC) are life-threatening diseases caused by immune response disorders and inflammation, but the underlining linking mechanisms are still not clear. This study aimed to detect the shared gene signature and potential molecular process between SALI and NSCLC. (2) Methods: RNA sequences and patient information on sepsis and NSCLC were acquired from the Gene Expression Omnibus (GEO) database. Weighted gene co-expression network analysis (WGCNA) was used to build a co-expression network associated with sepsis and NSCLC. Protein–protein interaction (PPI) analysis of shared genes was intuitively performed by the Search Tool for the Retrieval of Interacting Genes/Proteins (STRING) database. The involvement of EZH2 in the tumor immune microenvironment (TIME) and sepsis immune microenvironment (IME) was assessed by R software. Western blot, flow cytometry, and other in vitro assays were performed to further confirm the function and mechanism of EZH2 in NSCLC and SALI. (3) Results: WGCNA recognized three major modules for sepsis and two major modules for NSCLC, and there were seven shared genes identified for the two diseases. Additionally, the hub gene EZH2 was screened out. It was shown that EZH2 was closely related to the IME in the two diseases. In the validation assay, our data showed that EZH2 was expressed at a higher level in peripheral blood mononuclear cells (PBMCs) of septic patients than those of healthy donors (HDs), and EZH2 was also expressed at a higher level in lipopolysaccharide (LPS)-induced PBMCs and non-small cell lung cancer (A549) cells. EZH2 inhibitor (GSK343) downregulated the proliferation ability of A549 cells in a concentration-dependent manner, parallel with the decreased expression level of PD-L1. Similarly, GSK343 inhibited PD-L1 protein expression and downregulated the level of proinflammatory factors in LPS-induced PBMCs. In the co-culture system of PBMCs and human type II alveolar epithelial cells (ATIIs), the addition of GSK343 to PBMCs significantly downregulated the apoptosis of LPS-induced ATIIs. (4) Conclusions: This study illustrated that EZH2 inhibition could ameliorate A549 cell proliferation and LPS-induced ATII apoptosis in parallel with downregulation of PD-L1 protein expression, which provided new insights into molecular signaling networks involved in the pathogenetics of SALI and NSCLC.

Sepsis, a disease caused by severe infection, has a high mortality rate. At present, there is a lack of reliable algorithmic models for biomarker mining and diagnostic model construction for sepsis. Programmed cell death (PCD) has been shown to play a vital role in disease occurrence and progression, and different PCD-related genes have the potential to be targeted for the treatment of sepsis. In this paper, we analyzed PCD-related genes in sepsis. Implicated PCD processes include apoptosis, necroptosis, ferroptosis, pyroptosis, netotic cell death, entotic cell death, lysosome-dependent cell death, parthanatos, autophagy-dependent cell death, oxeiptosis, and alkaliptosis. We screened for diagnostic-related genes and constructed models for diagnosing sepsis using multiple machine-learning models. In addition, the immune landscape of sepsis was analyzed based on the diagnosis-related genes that were obtained. In this paper, 10 diagnosis-related genes were screened for using machine learning algorithms, and diagnostic models were constructed. The diagnostic model was validated in the internal and external test sets, and the Area Under Curve (AUC) reached 0.7951 in the internal test set and 0.9627 in the external test set. Furthermore, we verified the diagnostic gene via a qPCR experiment. The diagnostic-related genes and diagnostic genes obtained in this paper can be utilized as a reference for clinical sepsis diagnosis. The results of this study can act as a reference for the clinical diagnosis of sepsis and for target discovery for potential therapeutic drugs.