1. Impact of different nephrectomy types on M0 renal cell carcinoma outcomes in a propensity score matching and deep learning study
- Author
-
Shuhong Yu, Xuanyu Wang, Siyu Wang, and Ximing Xu
- Subjects
Renal cell carcinoma ,Nephrectomy ,SEER ,Deep learning ,Propensity score matching ,Medicine ,Science - Abstract
Abstract There are few analyses comparing complete nephrectomy with resection of the renal parenchyma only (CN) or radical nephrectomy that includes simultaneous resection of the parenchyma, affected perirenal fascia, perirenal fat, and ureter (RN) relative to partial nephrectomy (PN) for patients with nonmetastatic (M0) renal cell carcinoma (RCC) in terms of overall survival (OS). This study aimed to evaluate the effect of different nephrectomy on the OS of M0 RCC and to identify the main beneficiaries of different nephrectomy. The data was collected from the Surveillance, Epidemiology and End Results (SEER) database. Kaplan–Meier plots, and multivariable Cox regression models were used. Propensity score matching (PSM) was performed to reduce the effect of selection bias. A prognostic model for M0 RCC patients after nephrectomy was established using the deep learning framework. Stage I M0 RCC patients who received PN did not have a better prognosis than none surgery in terms of CSS and OS after PSM. Stage I M0 RCC patients who received PN did not have a better prognosis than CN in terms of CSS but had in terms of OS after PSM. Stage I M0 RCC patients who received PN had a better prognosis in terms of CSS and OS after PSM. The test set AUC values for 1/3/5/7/9 year survival prediction of the surgical decision model were 0.844, 0.812, 0.794, 0.79, 0.813. For OS and CSS in M0 RCC patients, PN was superior to CN and RN regardless of grade. But for grade I, PN and none surgery did not show significant differences. In order to further categorize surgical patients and make more precise decisions regarding their treatment, a surgical decision-making model has been established.
- Published
- 2024
- Full Text
- View/download PDF