Investigation of Risk Factors and Development and Validation of a Nomogram for Predicting Overall Survival in Breast-Invasive Lobular Carcinoma

Objective: Invasive lobular carcinoma (ILC) of the breast is a common pathological subtype of breast cancer, ranks second in terms of incidence rate following invasive ductal carcinoma. The aims of this study were to construct a nomogram for predicting overall survival (OS) in patients with ILC and to identify risk factors that affect their survival prognosis. Methods: The patients diagnosed with ILC between 2010 and 2015 were extracted from Surveillance, Epidemiology, and End Results (SEER) database. They were randomly split into a training set with 18,365 samples for model training and parameter tuning and a validation set with 7,872 samples for independent accuracy verification. The independent risk factors were screened by lasso regression and multivariable Cox regression. A nomogram was constructed for the 3-year, 5-year, and 10-year OS rates based on these independent risk factors. Model efficiency was assessed through Harrell’s concordance index (C-index), calibration curves, receiver operating characteristic curves, and decision curve analysis (DCA). Results: A total of 26,237 patients diagnosed with ILC were included. The following factors were identified as independent risk factors associated with OS: age, marital status, grade, estrogen receptor, progesterone receptor, surgery, radiation therapy, tumor size (T), lymph node (N), and metastasis (M) stages. The C-index was 0.795 in the training set, while in the validation set it was 0.791. The corresponding areas under the curve for 3-year, 5-year, and 10-year OS were 0.837, 0.828, and 0.791 in the training set and 0.832, 0.826, and 0.781 in the validation set, respectively. The calibration curve of the nomogram showed good consistency, and the DCA curves also suggested that it can provide valuable guidance for clinical decision-making. Conclusions: The established nomogram predicting 3-year, 5-year, and 10-year OS for patients with ILC showed a good performance and it can help clinicians make more favorable clinical decisions.