To facilitate patient consultation and assist in clinical decision-making, we developed a predictive model to analyze the overall survival (OS) rate of cervical cancer patients with concurrent lung metastasis for 6 months, 1 year, or 2 years.
We extracted data on patients diagnosed with cervical cancer and concurrent lung metastasis between 2010 and 2020 from the Surveillance, Epidemiology, and End Results (SEER) database. Through a random assignment process, these patients were allocated to either a training cohort or a validation cohort, maintaining a 7:3 ratio. Utilizing both univariate and multivariate Cox regression analyses, we determined the independent prognostic factors influencing OS. To enhance predictive accuracy, we developed a nomogram model incorporating these identified independent prognostic variables. Model effectiveness was subsequently assessed using various metrics, including receiver operating characteristic (ROC) curves, calibration plots, and decision curve analysis (DCA).
We gathered data on 1330 patients diagnosed with cervical cancer with lung metastases. An OS nomogram was developed, accounting for factors such as histological type, presence of metastases in other organs (brain, liver), surgical interventions, radiation therapy, and chemotherapy. The ROC curves, calibration plots, and DCA curves demonstrated the commendable predictive performance of the nomogram in assessing the prognosis of cervical cancer patients with lung metastases in both the training and validation cohorts.
By utilizing clinical data from the SEER database, we have effectively devised a nomogram capable of predicting the 6-month, 1-year, and 2-year survival rates of cervical cancer patients with lung metastases. The nomogram boasts high accuracy, offering precise prognostic predictions. Its implementation can guide the formulation of individualized follow-up and treatment plans for enhanced patient care.