ObjectiveTo construct a nomogram prediction model for pain crisis occurrence based on clinical data of patients with advanced non-small cell lung cancer (NSCLC), with the aim of providing a scientific basis for clinical decision-making.MethodsA total of patients with advanced non-small cell lung cancer (NSCLC) admitted to our hospital from January 2022 to January 2024 were selected as the study subjects. Demographic data, disease information, pain severity (assessed using the Numerical Rating Scale, NRS), psychological status (anxiety and depression assessed using the Self-Rating Anxiety Scale, SAS, and the Self-Rating Depression Scale, SDS), and social support (assessed using the Perceived Social Support Scale, PSSS) were collected. Univariate and multivariate Logistic regression analyses were performed to identify independent factors influencing pain crisis. The R software was used to visualize the nomogram, and the Receiver Operating Characteristic (ROC) curve, calibration curve, and Hosmer-Lemeshow test were employed to evaluate the discrimination and calibration of the model.ResultsA total of 500 questionnaires were distributed, and 448 qualified questionnaires were collected, with a qualification rate of 89.6%. The patients were divided into a modeling group (n=314) and a validation group (n=134). Univariate analysis showed significant differences between the pain crisis group and the pain-free group in terms of gender, age, education level, PSSS score, bone metastases, pleural metastases, depression and anxiety levels, and antitumor efficacy (P<0.05). Multivariate Logistic regression analysis showed that bone metastasis, PSSS score, age, depression, and anxiety levels were independent factors influencing pain crisis in patients with advanced NSCLC. Based on the results of the multivariate Logistic regression analysis, a nomogram prediction model for pain crisis occurrence in patients with advanced NSCLC was constructed. The Area Under the Curve (AUC) of the ROC curve in the modeling and validation groups was 0.948 and 0.921, respectively, indicating high discrimination of the model. The calibration curve and Hosmer-Lemeshow test results showed good consistency of the model.ConclusionThis study successfully constructed and validated a nomogram prediction model based on independent factors such as bone metastasis, social support (PSSS score), age, depression, and anxiety levels. This model can objectively and quantitatively predict the risk of pain crisis occurrence in patients with advanced NSCLC, providing a scientific basis for clinical decision-making. It helps identify high-risk patients with pain crisis in advance and optimize pain management strategies, thereby improving patient prognosis and quality of life.
Keloids are benign skin tumors resulting from the excessive proliferation of connective tissue in wound skin. Precise prediction of keloid risk in trauma patients and timely early diagnosis are of paramount importance for in-depth keloid management and control of its progression. This study analyzed four keloid datasets in the high-throughput gene expression omnibus (GEO) database, identified diagnostic markers for keloids, and established a nomogram prediction model. Initially, 37 core protein-encoding genes were selected through weighted gene co-expression network analysis (WGCNA), differential expression analysis, and the centrality algorithm of the protein-protein interaction network. Subsequently, two machine learning algorithms including the least absolute shrinkage and selection operator (LASSO) and the support vector machine-recursive feature elimination (SVM-RFE) were used to further screen out four diagnostic markers with the highest predictive power for keloids, which included hepatocyte growth factor (HGF), syndecan-4 (SDC4), ectonucleotide pyrophosphatase/phosphodiesterase 2 (ENPP2), and Rho family guanosine triphophatase 3 (RND3). Potential biological pathways involved were explored through gene set enrichment analysis (GSEA) of single-gene. Finally, univariate and multivariate logistic regression analyses of diagnostic markers were performed, and a nomogram prediction model was constructed. Internal and external validations revealed that the calibration curve of this model closely approximates the ideal curve, the decision curve is superior to other strategies, and the area under the receiver operating characteristic curve is higher than the control model (with optimal cutoff value of 0.588). This indicates that the model possesses high calibration, clinical benefit rate, and predictive power, and is promising to provide effective early means for clinical diagnosis.