Prediction of medication nonadherence in patients with lung cancer based on nomogram model construction.

Lung cancer is the leading cause of death among patients with cancer. Medication nonadherence affects survival time and remission of disease symptoms in patients with lung cancer. Therefore, this study analyzed the risk factors for medication nonadherence in patients with lung cancer and established a nomogram prediction model. The basic information and clinical characteristics of patients with lung cancer were collected from the Affiliated Hospital of Chengde Medical University from April 2020 to March 2023. The Chinese version of the Morisky Medication Adherence Questionnaire-8 was used to evaluate patients' medication adherence. A least absolute shrinkage and selection operator regression model and multivariate logistic regression analysis were used to identify the risk factors for medication nonadherence and establish a nomogram prediction model. The predictive ability of the nomogram was evaluated using the concordance index (C-index) and the area under the operating characteristic curve. Decision curve analysis (DCA) and the clinical impact curve were used to assess the potential clinical value of the nomogram. A total of 161 patients with lung cancer were included in this study, with a medication nonadherence rate of 47.20%. Risk factors included age, surgery, education level, bone metastases, comorbidities, well-being, and constipation. The C-index and area under the operating characteristic curve were 0.946. The threshold probability for DCA ranged from 0.07 to 0.95. The nomogram can predict the risk of medication nonadherence in patients with lung cancer and help identify those at risk early in clinical settings, allowing for the development of intervention programs and improved clinical management.