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.