Machine learning-based derivation and validation of three immune phenotypes for risk stratification and prognosis in community-acquired pneumonia: a retrospective cohort study.

Background: The clinical presentation of Community-acquired pneumonia (CAP) in hospitalized patients exhibits heterogeneity. Inflammation and immune responses play significant roles in CAP development. However, research on immunophenotypes in CAP patients is limited, with few machine learning (ML) models analyzing immune indicators. Methods: A retrospective cohort study was conducted at Xinhua Hospital, affiliated with Shanghai Jiaotong University. Patients meeting predefined criteria were included and unsupervised clustering was used to identify phenotypes. Patients with distinct phenotypes were also compared in different outcomes. By machine learning methods, we comprehensively assess the disease severity of CAP patients. Results: A total of 1156 CAP patients were included in this research. In the training cohort (n=809), we identified three immune phenotypes among patients: Phenotype A (42.0%), Phenotype B (40.2%), and Phenotype C (17.8%), with Phenotype C corresponding to more severe disease. Similar results can be observed in the validation cohort. The optimal prognostic model, SuperPC, achieved the highest average C-index of 0.859. For predicting CAP severity, the random forest model was highly accurate, with C-index of 0.998 and 0.794 in training and validation cohorts, respectively. Conclusion: CAP patients can be categorized into three distinct immune phenotypes, each with prognostic relevance. Machine learning exhibits potential in predicting mortality and disease severity in CAP patients by leveraging clinical immunological data. Further external validation studies are crucial to confirm applicability.

Mesenchymal Stromal Cell Therapy Alleviates Ovalbumin-Induced Chronic Airway Remodeling by Suppressing M2 Macrophage Polarization.

Chronic asthma is characterized by airway hyperresponsiveness, inflammation, and remodeling. Previous studies have shown that mesenchymal stromal/stem cells (MSCs) exert anti-inflammatory effects on asthma via regulation of the immune cells. However, the therapeutic mechanism of MSCs, especially the mechanism of airway remodeling in chronic asthma, remains to be elucidated. Here, we aimed to investigate the therapeutic effect of MSCs on airway remodeling in chronic asthma and explored the mechanisms by analyzing the polarization phenotype of macrophages in the lungs. We established a mouse model of chronic asthma induced by ovalbumin (OVA) and evaluated the effect of MSCs on airway remodeling. The data showed that MSCs treatment before the challenge exerted protective effects on OVA-induced chronic asthma, i.e., decreased the inflammatory cell infiltration, Th2 cytokine levels, subepithelial extracellular matrix deposition, and transforming growth factor ß (TGF-ß)/Smad signaling. Additionally, we found that MSCs treatment markedly suppressed macrophage M2 polarization in lung tissue. At the same time, MSCs treatment inhibited NF-κB p65 nuclear translocation, ER stress, and oxidative stress in the OVA-induced chronic allergic airway remodeling mice model. In conclusion, these results demonstrated that MSCs treatment prevents OVA-induced chronic airway remodeling by suppressing macrophage M2 polarization, which may be associated with the dual inhibition of ER stress and oxidative stress. This discovery may provide a new theoretical basis for the future clinical application of MSCs.

A Diagnostic Model for Alzheimer's Disease Based on Blood Levels of Autophagy-Related Genes.

Alzheimer's disease (AD) is a common neurodegenerative disease. The major problems that exist in the diagnosis of AD include the costly examinations and the high-invasive sampling tissue. Therefore, it would be advantageous to develop blood biomarkers. Because AD's pathological process is considered tightly related to autophagy; thus, a diagnostic model for AD based on ATGs may have more predictive accuracy than other models. We obtained GSE63060 dataset from the GEO database, ATGs from the HADb and screened 64 differentially expressed autophagy-related genes (DE-ATGs). We then applied them to Gene Ontology (GO) and Kyoto Encyclopedia of Genes and Genomes (KEGG) analyses as well as DisGeNET and PaGenBase enrichment analyses. By using the univariate analysis, least absolute shrinkage and selection operator (LASSO) regression method and the multivariable logistic regression, nine DE-ATGs were identified as biomarkers, which are ATG16L2, BAK1, CAPN10, CASP1, RAB24, RGS19, RPS6KB1, ULK2, and WDFY3. We combined them with sex and age to establish a nomogram model. To evaluate the model's distinguishability, consistency, and clinical applicability, we applied the receiver operating characteristic (ROC) curve, C-index, calibration curve, and on the validation datasets GSE63061, GSE54536, GSE22255, and GSE151371 from GEO database. The results show that our model demonstrates good prediction performance. This AD diagnosis model may benefit both clinical work and mechanistic research.