Endoscopic ultrasonography-based intratumoral and peritumoral machine learning radiomics analyses for distinguishing insulinomas from non-functional pancreatic neuroendocrine tumors.

Objectives: To develop and validate radiomics models utilizing endoscopic ultrasonography (EUS) images to distinguish insulinomas from non-functional pancreatic neuroendocrine tumors (NF-PNETs). Methods: A total of 106 patients, comprising 61 with insulinomas and 45 with NF-PNETs, were included in this study. The patients were randomly assigned to either the training or test cohort. Radiomics features were extracted from both the intratumoral and peritumoral regions, respectively. Six machine learning algorithms were utilized to train intratumoral prediction models, using only the nonzero coefficient features. The researchers identified the most effective intratumoral radiomics model and subsequently employed it to develop peritumoral and combined radiomics models. Finally, a predictive nomogram for insulinomas was constructed and assessed. Results: A total of 107 radiomics features were extracted based on EUS, and only features with nonzero coefficients were retained. Among the six intratumoral radiomics models, the light gradient boosting machine (LightGBM) model demonstrated superior performance. Furthermore, a peritumoral radiomics model was established and evaluated. The combined model, integrating both the intratumoral and peritumoral radiomics features, exhibited a comparable performance in the training cohort (AUC=0.876) and achieved the highest accuracy in predicting outcomes in the test cohorts (AUC=0.835). The Delong test, calibration curves, and decision curve analysis (DCA) were employed to validate these findings. Insulinomas exhibited a significantly smaller diameter compared to NF-PNETs. Finally, the nomogram, incorporating diameter and radiomics signature, was constructed and assessed, which owned superior performance in both the training (AUC=0.929) and test (AUC=0.913) cohorts. Conclusion: A novel and impactful radiomics model and nomogram were developed and validated for the accurate differentiation of NF-PNETs and insulinomas utilizing EUS images.

Construction and validation of an endoscopic ultrasonography-based ultrasomics nomogram for differentiating pancreatic neuroendocrine tumors from pancreatic cancer.

Objectives: To develop and validate various ultrasomics models based on endoscopic ultrasonography (EUS) for retrospective differentiating pancreatic neuroendocrine tumors (PNET) from pancreatic cancer. Methods: A total of 231 patients, comprising 127 with pancreatic cancer and 104 with PNET, were retrospectively enrolled. These patients were randomly divided into either a training or test cohort at a ratio of 7:3. Ultrasomics features were extracted from conventional EUS images, focusing on delineating the region of interest (ROI) for pancreatic lesions. Subsequently, dimensionality reduction of the ultrasomics features was performed by applying the Mann-Whitney test and least absolute shrinkage and selection operator (LASSO) algorithm. Eight machine learning algorithms, namely logistic regression (LR), light gradient boosting machine (LightGBM), multilayer perceptron (MLP), random forest (RF), extra trees, k nearest neighbors (KNN), support vector machine (SVM), and extreme gradient boosting (XGBoost), were employed to train prediction models using nonzero coefficient features. The optimal ultrasomics model was determined using a ROC curve and utilized for subsequent analysis. Clinical-ultrasonic features were assessed using both univariate and multivariate logistic regression. An ultrasomics nomogram model, integrating both ultrasomics and clinical-ultrasonic features, was developed. Results: A total of 107 EUS-based ultrasomics features were extracted, and 6 features with nonzero coefficients were ultimately retained. Among the eight ultrasomics models based on machine learning algorithms, the RF model exhibited superior performance with an AUC= 0.999 (95% CI 0.9977 - 1.0000) in the training cohort and an AUC= 0.649 (95% CI 0.5215 - 0.7760) in the test cohort. A clinical-ultrasonic model was established and evaluated, yielding an AUC of 0.999 (95% CI 0.9961 - 1.0000) in the training cohort and 0.847 (95% CI 0.7543 - 0.9391) in the test cohort. Subsequently, the ultrasomics nomogram demonstrated a significant improvement in prediction accuracy in the test cohort, as evidenced by an AUC of 0.884 (95% CI 0.8047 - 0.9635) and confirmed by the Delong test. The calibration curve and decision curve analysis (DCA) depicted this ultrasomics nomogram demonstrated superior accuracy. They also yielded the highest net benefit for clinical decision-making compared to alternative models. Conclusions: A novel ultrasomics nomogram was proposed and validated, that integrated clinical-ultrasonic and ultrasomics features obtained through EUS, aiming to accurately and efficiently identify pancreatic cancer and PNET.

Identification and analysis of chemokine-related and NETosis-related genes in acute pancreatitis to develop a predictive model.

Background: Chemokines and NETosis are significant contributors to the inflammatory response, yet there still needs to be a more comprehensive understanding regarding the specific molecular characteristics and interactions of NETosis and chemokines in the context of acute pancreatitis (AP) and severe AP (SAP). Methods: To address this gap, the mRNA expression profile dataset GSE194331 was utilized for analysis, comprising 87 AP samples (77 non-SAP and 10 SAP) and 32 healthy control samples. Enrichment analyses were conducted for differentially expressed chemokine-related genes (DECRGs) and NETosis-related genes (DENRGs). Three machine-learning algorithms were used for the identification of signature genes, which were subsequently utilized in the development and validation of nomogram diagnostic models for the prediction of AP and SAP. Furthermore, single-gene Gene Set Enrichment Analysis (GSEA) and Gene Set Variation Analysis (GSVA) were performed. Lastly, an interaction network for the identified signature genes was constructed. Results: We identified 12 DECRGs and 7 DENRGs, and enrichment analyses indicated they were primarily enriched in cytokine-cytokine receptor interaction, chemokine signaling pathway, TNF signaling pathway, and T cell receptor signaling pathway. Moreover, these machine learning algorithms finally recognized three signature genes (S100A8, AIF1, and IL18). Utilizing the identified signature genes, we developed nomogram models with high predictive accuracy for AP and differentiation of SAP from non-SAP, as demonstrated by area under the curve (AUC) values of 0.968 (95% CI 0.937-0.990) and 0.862 (95% CI 0.742-0.955), respectively, in receiver operating characteristic (ROC) curve analysis. Subsequent single-gene GESA and GSVA indicated a significant positive correlation between these signature genes and the proteasome complex. At the same time, a negative association was observed with the Th1 and Th2 cell differentiation signaling pathways. Conclusion: We have identified three genes (S100A8, AIF1, and IL18) related to chemokines and NETosis, and have developed accurate diagnostic models that might provide a novel method for diagnosing AP and differentiating between severe and non-severe cases.

Identification of common genes and pathways between type 2 diabetes and COVID-19.

Background: Numerous studies have reported a high incidence and risk of severe illness due to coronavirus disease 2019 (COVID-19) in patients with type 2 diabetes (T2DM). COVID-19 patients may experience elevated or decreased blood sugar levels and may even develop diabetes. However, the molecular mechanisms linking these two diseases remain unclear. This study aimed to identify the common genes and pathways between T2DM and COVID-19. Methods: Two public datasets from the Gene Expression Omnibus (GEO) database (GSE95849 and GSE164805) were analyzed to identify differentially expressed genes (DEGs) in blood between people with and without T2DM and COVID-19. Gene ontology (GO) and Kyoto Encyclopedia of Genes and Genomes (KEGG) enrichment analyses were performed on the common DEGs. A protein-protein interaction (PPI) network was constructed to identify common genes, and their diagnostic performance was evaluated by receiver operating characteristic (ROC) curve analysis. Validation was performed on the GSE213313 and GSE15932 datasets. A gene co-expression network was constructed using the GeneMANIA database to explore interactions among core DEGs and their co-expressed genes. Finally, a microRNA (miRNA)-transcription factor (TF)-messenger RNA (mRNA) regulatory network was constructed based on the common feature genes. Results: In the GSE95849 and GSE164805 datasets, 81 upregulated genes and 140 downregulated genes were identified. GO and KEGG enrichment analyses revealed that these DEGs were closely related to the negative regulation of phosphate metabolic processes, the positive regulation of mitotic nuclear division, T-cell co-stimulation, and lymphocyte co-stimulation. Four upregulated common genes (DHX15, USP14, COPS3, TYK2) and one downregulated common feature gene (RIOK2) were identified and showed good diagnostic accuracy for T2DM and COVID-19. The AUC values of DHX15, USP14, COPS3, TYK2, and RIOK2 in T2DM diagnosis were 0.931, 0.917, 0.986, 0.903, and 0.917, respectively. In COVID-19 diagnosis, the AUC values were 0.960, 0.860, 1.0, 0.9, and 0.90, respectively. Validation in the GSE213313 and GSE15932 datasets confirmed these results. The miRNA-TF-mRNA regulatory network showed that TYH2 was targeted by PITX1, PITX2, CRX, NFYA, SREBF1, RELB, NR1L2, and CEBP, whereas miR-124-3p regulates THK2, RIOK2, and USP14. Conclusion: We identified five common feature genes (DHX15, USP14, COPS3, TYK2, and RIOK2) and their co-regulatory pathways between T2DM and COVID-19, which may provide new insights for further molecular mechanism studies.

Identifying target ion channel-related genes to construct a diagnosis model for insulinoma.

Background: Insulinoma is the most common functional pancreatic neuroendocrine tumor (PNET) with abnormal insulin hypersecretion. The etiopathogenesis of insulinoma remains indefinable. Based on multiple bioinformatics methods and machine learning algorithms, this study proposed exploring the molecular mechanism from ion channel-related genes to establish a genetic diagnosis model for insulinoma. Methods: The mRNA expression profile dataset of GSE73338 was applied to the analysis, which contains 17 insulinoma samples, 63 nonfunctional PNET (NFPNET) samples, and four normal islet samples. Differently expressed ion channel-related genes (DEICRGs) enrichment analyses were performed. We utilized the protein-protein interaction (PPI) analysis and machine learning of LASSO and support vector machine-recursive feature elimination (SVM-RFE) to identify the target genes. Based on these target genes, a nomogram diagnostic model was constructed and verified by a receiver operating characteristic (ROC) curve. Moreover, immune infiltration analysis, single-gene gene set enrichment analysis (GSEA), and gene set variation analysis (GSVA) were executed. Finally, a drug-gene interaction network was constructed. Results: We identified 29 DEICRGs, and enrichment analyses indicated they were primarily enriched in ion transport, cellular ion homeostasis, pancreatic secretion, and lysosome. Moreover, the PPI network and machine learning recognized three target genes (MCOLN1, ATP6V0E1, and ATP4A). Based on these target genes, we constructed an efficiently predictable diagnosis model for identifying insulinomas with a nomogram and validated it with the ROC curve (AUC = 0.801, 95% CI 0.674-0.898). Then, single-gene GSEA analysis revealed that these target genes had a significantly positive correlation with insulin secretion and lysosome. In contrast, the TGF-beta signaling pathway was negatively associated with them. Furthermore, statistically significant discrepancies in immune infiltration were revealed. Conclusion: We identified three ion channel-related genes and constructed an efficiently predictable diagnosis model to offer a novel approach for diagnosing insulinoma.

Identification of common signature genes and pathways underlying the pathogenesis association between nonalcoholic fatty liver disease and atherosclerosis.

Background: Atherosclerosis (AS) is one of the leading causes of the cardio-cerebral vascular incident. The constantly emerging evidence indicates a close association between nonalcoholic fatty liver disease (NAFLD) and AS. However, the exact molecular mechanisms underlying the correlation between these two diseases remain unclear. This study proposed exploring the common signature genes, pathways, and immune cells among AS and NAFLD. Methods: The common differentially expressed genes (co-DEGs) with a consistent trend were identified via bioinformatic analyses of the Gene Expression Omnibus (GEO) datasets GSE28829 and GSE49541, respectively. Further, the Gene Ontology (GO) and Kyoto Encyclopedia of Genes and Genomes (KEGG) enrichment analyses were performed. We utilized machine learning algorithms of lasso and random forest (RF) to identify the common signature genes. Then the diagnostic nomogram models and receiver operator characteristic curve (ROC) analyses were constructed and validated with external verification datasets. The gene interaction network was established via the GeneMANIA database. Additionally, gene set enrichment analysis (GSEA), gene set variation analysis (GSVA), and immune infiltration analysis were performed to explore the co-regulated pathways and immune cells. Results: A total of 11 co-DEGs were identified. GO and KEGG analyses revealed that co-DEGs were mainly enriched in lipid catabolic process, calcium ion transport, and regulation of cytokine. Moreover, three common signature genes (PLCXD3, CCL19, and PKD2) were defined. Based on these genes, we constructed the efficiently predictable diagnostic models for advanced AS and NAFLD with the nomograms, evaluated with the ROC curves (AUC = 0.995 for advanced AS, 95% CI 0.971-1.0; AUC = 0.973 for advanced NAFLD, 95% CI 0.938-0.998). In addition, the AUC of the verification datasets had a similar trend. The NOD-like receptors (NLRs) signaling pathway might be the most crucial co-regulated pathway, and activated CD4 T cells and central memory CD4 T cells were significantly excessive infiltration in advanced NAFLD and AS. Conclusion: We identified three common signature genes (PLCXD3, CCL19, and PKD2), co-regulated pathways, and shared immune features of NAFLD and AS, which might provide novel insights into the molecular mechanism of NAFLD complicated with AS.