A prognostic nomogram based on least absolute shrinkage and selection operator Cox regression in patients with pulmonary large-cell neuroendocrine carcinoma.

Background: Pulmonary large-cell neuroendocrine carcinoma (LCNEC) is a rare subtype of breast cancer with a poor prognosis. Despite its rarity, it is important to gain a better understanding of the epidemiological, clinical, and prognostic features of pulmonary LCNEC. The purpose of this study was to design, construct, and validate a new nomogram for predicting overall survival (OS) in patients with pulmonary LCNEC. Methods: In total, the data of 1,864 LCNEC patients were extracted from the Surveillance, Epidemiology, and End Results (SEER) database, which is maintained by the National Cancer Institute in the United States and serves as a comprehensive source of cancer-related information. Of these patients, 556 served as the validation group and 1,308 served as the training cohort. We constructed a new nomogram with the training cohort that included the independent factors for OS as identified by least absolute shrinkage and selection operator Cox regression. Five independent factors were ultimately selected by the stepwise regression. Every factor of the Cox regression was included in the nomogram. Analyses of the calibration curve, decision curve, area under the curve, and concordance index (C-index) values were performed to assess the effectiveness and discriminative ability of the nomogram. Results: Five optimal predictive factors for OS were selected and merged to construct a 3- and 5-year OS nomogram. The nomogram had C-index values of 0.716 and 0.708 in the training cohort and validation cohort, respectively. The actual OS rates and the calibration curves showing the predictions of the nomogram were in good agreement. Conclusions: The prognostic nomogram may be very helpful in estimating the OS of patients with pulmonary LCNEC.