Predict Cancer-specific Survival After Nephrectomy for Nonmetastatic Renal Cancer: A Deep Learning-Based Prognostic Model

Predict Cancer-specific Survival After Nephrectomy for Nonmetastatic Renal Cancer: A Deep Learning-Based Prognostic Model | Research Square window.SnipcartSettings = { analytics: { enabled: false } }; (function() { var accessVector = localStorage.getItem('access_vector') || ''; window.dataLayer = window.dataLayer || []; if (accessVector) { window.dataLayer.push({ user: { profile: { profileInfo: { snid: accessVector } } } }); } })(); (function(w,d,s,l,i){w[l]=w[l]||[];w[l].push({'gtm.start':new Date().getTime(),event:'gtm.js'});var f=d.getElementsByTagName(s)[0],j=d.createElement(s),dl=l!='dataLayer'?'&l='+l:'';j.async=true;j.src='https://www.googletagmanager.com/gtm.js?id='+i+dl;f.parentNode.insertBefore(j,f);})(window,document,'script','dataLayer','GTM-K279D39R'); Browse Preprints In Review Journals COVID-19 Preprints AJE Video Bytes Research Tools Research Promotion AJE Professional Editing AJE Rubriq About Preprint Platform In Review Editorial Policies Our Team Advisory Board Help Center Sign In Submit a Preprint Cite Share Download PDF Article Predict Cancer-specific Survival After Nephrectomy for Nonmetastatic Renal Cancer: A Deep Learning-Based Prognostic Model Shuhong Yu, Xuanyu Wang, Siyu Wang, Ximing Xu This is a preprint; it has not been peer reviewed by a journal. https://doi.org/ 10.21203/rs.3.rs-4480345/v1 This work is licensed under a CC BY 4.0 License Status: Published Journal Publication published 11 Nov, 2024 Read the published version in Scientific Reports → Version 1 posted 10 You are reading this latest preprint version Abstract Background There are few analyses comparing radical nephrectomy with resection of the renal parenchyma only (RNRP) or radical nephrectomy that includes simultaneous resection of the parenchyma, affected perirenal fascia, perirenal fat, and ureter (RNPU) relative to partial nephrectomy (PN) for patients with nonmetastatic (M0) renal cell carcinoma (RCC) in terms of cancer-specific survival (CSS). This study aimed to evaluate the effect of different nephrectomy on the CSS of nonmetastatic RCC (nmRCC) and to identify the main beneficiaries of different nephrectomy. Methods 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 nmRCC patients after nephrectomy was established using the deep learning framework. Results Kaplan-Meier analysis after PSM showed that lymph node dissection (LND) was effective in patients after RNRP (HR = 0.41, 95%CI: 0.27–0.64, p < 0.0001). RNRP demonstrated less strongly association with CSS than was PN (HR = 0.49, 95%CI༚0.34–0.71, p < 0.0001). The established prognostic model showed that grade II stage I T1N0M0 patients were the primary beneficiary population of RN. Conclusions RN is more recommended than PN for grade II stage I T1N0M0 RCC patients. LND is necessary when performing RNRP. Biological sciences/Cancer/Urological cancer/Renal cancer Health sciences/Risk factors Health sciences/Nephrology/Kidney diseases/Renal cancer renal cell carcinoma nephrectomy SEER deep learning prognostic model Figures Figure 1 Figure 2 Figure 3 Figure 4 Figure 5 Figure 6 1. Introduction Renal cell carcinoma (RCC) is a complex malignancy with a multifactorial etiology, including genetic susceptibility, exposure to environmental carcinogens, and certain medical conditions [ 1 ]. RCC constitutes roughly 2.3% of all newly diagnosed malignant tumors in males and 1.3% in females [ 2 ], with a higher incidence rate observed in Western countries [ 3 ]. The incidence of RCC has been increasing at a rate of approximately 1% annually in recent times [ 2 ], and staging migration has contributed to a rise in the detection of early-stage RCC [ 4 ]. Consequently, surgical treatments for patients with low-stage RCC are attracting increasing interest [ 5 ]. For localized RCC, surgical intervention remains the primary and most effective radical treatment modality [ 6 ]. The utilization of radiotherapy and chemotherapy is restricted in the management of nonmetastatic RCC (nmRCC) [ 7 , 8 ]. It is well-established that for patients with localized T1 RCC, partial nephrectomy (PN) is preferentially employed over radical nephrectomy (RN) [ 6 ]. However, the lack of an accepted standard for choosing between RN and PN for nmRCC patients necessitates further investigation, particularly in studies targeting specific patient populations to optimize benefits. Additionally, the therapeutic efficacy of lymph node dissection (LND) in the treatment of nmRCC remains controversial at best [ 9 ]. Determining the optimal treatment for nmRCC patients is challenging due to the diversity in tumor biology and patient characteristics [ 10 ]. The relative benefits of PN versus RN and the utility of LND are not fully resolved, highlighting the need for evidence-based guidelines and personalized treatment approaches. Post-nephrectomy survival outcomes are influenced by a multitude of factors, including tumor stage, grade, and TNM states [ 11 ]. Developing a prognostic model that accurately predicts cancer-specific survival (CSS) could inform treatment decisions and improve patient outcomes [ 12 ]. In this study, we sought to characterize the population appropriate for nephrectomy based on SEER database, in which RN can be further classified based on the extent of resection: RN with removal of renal parenchyma alone (RNRP) and RN that includes simultaneous resection of the parenchyma, affected perirenal fascia, perirenal fat, and ureter (RNPU). We also evaluated risk factors and established prognostic model predicting cancer-specific survival (CSS) for nmRCC patients after nephrectomy. Our findings aim to contribute to the existing body of knowledge by providing insights into the optimal management strategies for nmRCC patients and guiding clinical decision-making. 2. Materials and Methods Cohort Selection Patients in our study were obtained from the SEER database using the following selection criteria for patients undergoing RCC surgery:(1) malignant tumor primary site limited to the "kidney"; (2) no evidence of distant metastasis; (3) pathologic subtypes of adenomas and adenocarcinomas, including 8140–8389. Exclusion criteria were (1) age at diagnosis < 20 years; (2) unknown characteristics; (3) survival time < 30 days; (4) non-cancer death. Because publicly available data were used, no ethical approval or declaration was required in our study. Data Collection We used SEER*Stat software version 8.4.1 to retrieve data (SEER Study data, 17 registry, November 2022 - sub − 2000–2022) for our study. All patient data collected included: marital status, gender, age, tumor laterality, primary site surgery, radiation therapy, chemotherapy, year of diagnosis, primary tumor site, histologic type, T stage, N stage, tumor size, duration of treatment, number of tumors, stage, grading, and survival outcomes. Data were converted to binary or categorical variables when necessary to comply with specifications. Model Construction Autogluon models deep learning framework ( https://github.com/autogluon/autogluon ) was utilized to construct a prognostic model of RCC patients for surgical decision making. The models were evaluated using Harrell’s Consistency Index (C-index), receiver operating characteristic (ROC) curve, calibration curve and decision curve analysis (DCA) [ 13 ] respectively. A user-friendly online website interactor was constructed using Dash ( https://github.com/plotly/dash ). Statistical Analysis The Kaplan-Meier method was used to estimate survival. Cox regression analysis was used to determine the association between clinical variables and survival. Patients in the PN, RN, and other groups, were matched using 1:1 propensity score matching (PSM). 3. Results 3.1. Univariate and multivariate COX regression analysis A total of 66,665 RCC patients from 2004 to 2020 were obtained from the SEER database. Univariate Cox regression analysis was used to screen for influential factors associated with survival of nmRCC patients. The results showed that marital status, gender, age, surgery, radiotherapy, chemotherapy, number of malignant tumors, tumor size, pathological grade, pathological stage, and TN stage were independent prognostic factors for nmRCC patients (Table 1 ). Table 1 Univariate and multivariate cox regression analysis in nmRCC patients. Variables Univariable Multivariable HR P value HR P value Marital Status Single Reference Reference Reference Reference Coupled 0.876 < 0.0001 1.151 < 0.0001 Unknown 0.771 < 0.0001 0.891 0.043 Gender Male Reference Reference Reference Reference Female 1.251 < 0.0001 1.114 < 0.0001 Age < 50 Reference Reference Reference Reference 50–60 1.432 < 0.0001 1.400 < 0.0001 60–70 2.891 < 0.0001 2.706 < 0.0001 ≥ 70 0.592 < 0.0001 0.654 < 0.0001 Laterality Left Reference Reference Reference Reference Right 0.957 0.028 1.012 0.565 Unknown 1.639 0.269 0.799 0.616 Surgery Complete/total nephrectomy Reference Reference Reference Reference Partial/subtotal nephrectomy 4.056 < 0.0001 3.593 < 0.0001 No surgery 0.567 < 0.0001 1.059 0.612 Radiotherapy None/Unknown Reference Reference Reference Reference Yes 9.368 < 0.0001 2.474 < 0.0001 Chemotherapy None/Unknown Reference Reference Reference Reference Yes 7.177 < 0.0001 1.791 < 0.0001 Months to Treatment 1.007 0.248 Number of Malignant Tumors 0.978 0.030 0.952 0.023 Number of Borderline Tumors 0.964 0.701 Tumor size 1.004 < 0.0001 1.002 < 0.0001 Grade Ⅰ Reference Reference Reference Reference Ⅱ 1.320 < 0.0001 1.126 0.005 Ⅲ 3.208 < 0.0001 1.890 < 0.0001 Ⅳ 9.433 < 0.0001 3.432 < 0.0001 Stage Ⅰ Reference Reference Reference Reference Ⅱ 3.000 < 0.0001 1.742 < 0.0001 Ⅲ 5.949 < 0.0001 2.450 < 0.0001 Ⅳ 22.795 < 0.0001 2.977 < 0.0001 Tstage T1 Reference Reference Reference Reference T2 3.120 < 0.0001 1.299 0.048 T3 5.959 < 0.0001 1.365 0.004 T4 20.874 < 0.0001 1.972 0.002 Nstage N0 Reference Reference Reference Reference N1 10.573 < 0.0001 2.485 < 0.0001 N2 13.346 < 0.0001 2.333 < 0.0001 3.2. Benefits of radiotherapy and chemotherapy in surgically treated nmRCC patients Patients who received additional radiotherapy (Before PSM: HR = 10.10, 95%CI: 6.62–45.41, p < 0.0001; After PSM: HR = 3.73, 95%CI༚2.72–5.13, p < 0.0001) or chemotherapy (Before PSM: HR = 6.83, 95%CI༚5.65–8.25, p < 0.0001; After PSM: HR = 1.74, 95%CI༚1.46–2.06, p < 0.0001) following surgery had a poorer prognosis (Fig. 1 A-B). The post-PSM baseline data are presented in Supplementary Tables 1–2. 3.3. Benefit of lymph node dissection in nmRCC patients with RN LND was associated with improved outcomes (Before PSM: HR = 0.99, 95%CI: 0.93–1.07, p = 0.88; After PSM: HR = 0.81, 95%CI༚0.73–0.91, p = 0.00047) (Fig. 2 A). Specifically, LND was effective in enhancing the prognosis for RNRP patients (Before PSM: HR = 0.53, 95%CI༚0.38–0.77, p < 0.0001; After PSM: HR = 0.41, 95%CI༚0.27–0.64, p < 0.0001) (Fig. 2 B), while it did not confer a similar benefit for RNPU patients (Before PSM: HR = 1.35, 95%CI༚1.27–1.45, p < 0.0001; After PSM: HR = 1.08, 95%CI༚0.95–1.20, p = 0.23) (Fig. 2 C). The post-PSM baseline data are presented in Supplementary Tables 3–5. 3.4. Comparison of the prognosis between PN and RN in nmRCC patients Before PSM, PN-treated patients had a better prognosis, but this was reversed after performing PSM (Before PSM: HR = 1.80, 95%CI: 1.52–2.13, p < 0.0001; After PSM: HR = 0.65, 95%CI༚0.47–0.91, p = 0.007) (Fig. 3 A). The post-PSM baseline data are presented in Supplementary Tables 6–9. RN can be divided into RNRP and RNRU, with RNRP showing a better prognosis (Before PSM: HR = 0.22, 95%CI༚0.21–0.23, p < 0.0001; After PSM: HR = 0.63, 95%CI༚0.57–0.69, p < 0.0001) (Fig. 3 B). Analysis revealed that patients after RNRP exhibited superior CSS than PN (Before PSM: HR = 0.52, 95%CI༚0.38–0.71, p < 0.0001; After PSM: HR = 0.49, 95%CI༚0.34–0.71, p < 0.0001) (Fig. 3 C). No significant prognostic disparity was detected between RNPU-treated patients and PN-treated patients (Before PSM: HR = 2.61, 95%CI༚2.26–3.01, p < 0.0001; After PSM: HR = 0.92, 95%CI༚0.67–1.28, p = 0.62) (Fig. 3 D). 3.5. Establishing a prognostic prediction model for nmRCC patients using deep learning Survival analyses have indicated that RN may confer potentially superior outcomes compared to PN, necessitating the identification of populations that optimally benefit from RN. Consequently, the 2,724 nmRCC patients, matched according to criteria, were subdivided into a training cohort (2,180 patients) and a testing cohort (544 patients) at an 8:2 ratio, excluding those with less than 365 days of survival data. Prognostic models for nmRCC patients after nephrectomy were developed utilizing various deep learning methodologies, with the model exhibiting the highest efficacy chosen for further analysis (Fig. 4 A). The importance of each feature is illustrated in the graphic, with 'year' denoting different temporal milestones (1/3/5/7/9 years) for assessing survival status (Fig. 4 B). The C-index and area under the curve (AUC) values were computed for 1/3/5/7/9 years survival prediction intervals, both in the training and testing cohorts (Figs. 4 C-D). The calibration and DCA performed satisfactorily (Figs. 4 E-F). 3.6. Stage I nmRCC patients undergoing surgery are candidates for RN In tandem with modeling prognosis, we anticipated delineating the principal cohort that would derive the greatest benefit from RN. Notably, our analysis of the matched cohort revealed that 99.6% of patients were classified as stage I, suggesting that stage I nmRCC patients was the primary population to benefit most significantly (Supplementary Table 8). Consequently, we conducted a subgroup analysis to the stage of nmRCC patients. The findings indicated that RN was associated with a superior prognosis compared to PN, only in the stage I cohort (HR = 0.80, 95%CI: 0.62–1.03, p = 0.055) (Fig. 5 A). Subsequent PSM of stage I patients revealed a significant prognostic improvement with RN relative to PN (HR = 0.49, 95%CI༚0.34–0.72, p < 0.0001) (Fig. 5 B). The post-PSM baseline data are presented in Supplementary Table 11. RN was associated with higher CSS rates (Before PSM: HR = 0.65, 95%CI༚0.45–0.95, p = 0.0057; After PSM: HR = 0.39, 95%CI༚0.24–0.65, p = 0.0001) (Fig. 5 C). 3.7. Grade II stage I T1N0M0 nmRCC patients are the primary beneficiary population of RN Analogously, our model traversal identified a patient cohort with the following demographic traits: grade = Ⅱ in 62.7%, stage = Ⅰ, and TMN = T1N0M0 (Supplementary Table 10). Consequently, a subpopulation analysis by grade became imperative. We examined the survival rates of renal cell carcinoma patients with TNM staging of T1N0M0 and stage Ⅰ, stratified by grade. The findings revealed no discernible survival disparities among patients with grade I (HR = 0.90, 95%CI: 0.53–1.52, p = 0.68) (Fig. 6 A). Conversely, grade II patients demonstrated greater suitability for RN (HR = 0.51, 95%CI༚0.35–0.75, p < 0.0001) (Fig. 6 B). No significant differences were noted in patients with grade III (HR = 1.15, 95%CI༚0.51–2.61, p = 0.75) and IV (HR = 1.18, 95%CI༚0.56–2.47, p = 0.69) (Figs. 6 C-D). Therefore, RCC patients with grade II, stage I, T1N0M0 classification represent the predominant cohort that benefits most significantly from RN. 4. Discussion In recent years, the advancement of precision medicine in RCC has necessitated a comprehensive understanding of the individual risks and benefits for each patient [ 14 , 15 ]. The increasing trend is to stratify patients based on disease attributes and predicted risk scores, thereby enhancing personalized care. Our study presents a surgical prognostic model that exhibits independent prognostic significance and has identified a particular advantage of RN for grade II, stage I, and T1N0M0 RCC patients. While numerous prospective studies investigate the application of PN in nmRCC across various stages, with no significant disparity in postoperative complications and survival between PN (216 cases) and RN (156 cases) in clinical T1 RCC [ 16 ]. In contrast, the utilization of PN should be more judiciously considered for clinical T2 and clinical T3a RCC, taking into account specific patient characteristics as well as tumor factors [ 17 , 18 ]. Our model introduces a more granular evaluation by integrating stage and grade as determinants of surgical advantage, potentially facilitating more personalized treatment decisions. Indeed, the use of PN for T1 nmRCC remains heterogeneous, and the population should be more narrowly delineated [ 19 ]. Furthermore, alongside the selection of the optimal surgical approach, the integration of surgery with additional treatment modalities constitutes a significant strategy for enhancing the prognosis of nmRCC patients. Our findings suggest that the combined use of radiotherapy and chemotherapy with surgery may not significantly improve outcomes for nmRCC patients. Hence, the refinement of surgical treatments and the establishment of surgical benefit profiles for distinct patient subsets may represent a more auspicious strategy than multimodal therapy. Emerging studies, such as Hannan et al.'s work on the efficacy and safety of stereotactic ablative radiation for primary RCC [ 20 ], suggest potential avenues for future research. Moreover, targeted therapies have shown promise for localized and locally advanced RCC [ 5 ], although data limitations precluded further examination in our study. The role of LND in enhancing survival for RCC patients with and without nodal involvement remains undetermined [ 9 ]. Our study contributes to this discussion by elucidating the differential benefits of LND in RNRP versus RNPU [ 21 ]. The impact of surgical waiting times on patient mortality is also an area of interest, with some studies indicating an increased risk of death [ 22 ]. Our study did not find treatment delay to be an independent risk factor, a finding that requires further validation. To our knowledge, this is the inaugural surgical prognostic model for RCC patients that can precisely identify the cohort that will derive the most benefit from surgery. The use of the PSM method has helped to mitigate bias and derive robust results. Nonetheless, the model retains certain limitations: it is a retrospective study, which makes avoiding selection bias difficult, and the sample size utilized for training is relatively small and derived from a single cohort. Consequently, prospective clinical trials and additional external validations are imperative. 5. Conclusions For nmRCC, combined nephrectomy with radiotherapy or chemotherapy are not recommended. In the choice of nephrectomy, RN is more suggested for grade II, stage I, and T1N0M0 patients. Moreover, LND is necessary when RNRP is performed. Declarations Ethics approval and consent to participate Patient consent was waived due to this article using data from the SEER database, which are publicly available deidentified patient data from the National Cancer Institute (NCI), USA. Availability of data and materials The datasets analysed in the current study are available from the corresponding author on reasonable request. Competing interests No conflict of interest existed in the present research. Funding No funding in the present research. Authors' contributions S.Y. and X.W. designed this research. S.Y. organized the processing flow. S.Y. and X.W. completed the whole analytic process of this study. S.W. organized and presented the results. S.Y., X.W., and S. W. contributed to the writing of the manuscript. X.X. provided administrative and technical support. All authors reviewed the manuscript, agreeing with the publishing. Acknowledgements We want to be grateful for the SEER database. References Linehan WM, Ricketts CJ: The Cancer Genome Atlas of renal cell carcinoma: findings and clinical implications. Nature Reviews Urology 2019, 16: 539-552. Siegel RL, Miller KD, Wagle NS, Jemal A: Cancer statistics, 2023. Ca-a Cancer Journal for Clinicians 2023, 73: 17-48. Ferlay J, Colombet M, Soerjomataram I, Dyba T, Randi G, Bettio M, Gavin A, Visser O, Bray F: Cancer incidence and mortality patterns in Europe: Estimates for 40 countries and 25 major cancers in 2018. European Journal of Cancer 2018, 103: 356-387. Patel HD, Gupta M, Joice GA, Srivastava A, Alam R, Allaf ME, Pierorazio PM: Clinical Stage Migration and Survival for Renal Cell Carcinoma in the United States. European Urology Oncology 2019, 2: 343-348. Ingels A, Campi R, Capitanio U, Amparore D, Bertolo R, Carbonara U, Erdem S, Kara Ö, Klatte T, Kriegmair MC, et al: Complementary roles of surgery and systemic treatment in clear cell renal cell carcinoma. Nature Reviews Urology 2022, 19: 391-418. Ljungberg B, Albiges L, Abu-Ghanem Y, Bedke J, Capitanio U, Dabestani S, Fernández-Pello S, Giles RH, Hofmann F, Hora M, et al: European Association of Urology Guidelines on Renal Cell Carcinoma: The 2022 Update. European Urology 2022, 82: 399-410. Grabbert M, Grosu AL, Zamboglou C, Gratzke C: Nivolumab in Combination with Stereotactic Body Radiotherapy in Pretreated Patients with Metastatic Renal Cell Carcinoma. Results of the Phase II NIVES Study. European Urology 2022, 81: 622-622. Ryan CW, Tangen CM, Heath E, Stein MN, Meng M, Alva AS, Pal SK, Puzanov I, Clark J, Choueiri TK, et al: Adjuvant everolimus after surgery for renal cell carcinoma (EVEREST): a double-blind, placebo-controlled, randomised, phase 3 trial. Lancet 2023, 402: 1043-1051. Ngai M, Chandrasekar T, Bratslavsky G, Goldberg H: The Current Role of Lymph Node Dissection in Nonmetastatic Localized Renal Cell Carcinoma. Journal of Clinical Medicine 2023, 12 . Singla N: Progress Toward Precision Medicine in Frontline Treatment of Metastatic Renal Cell Carcinoma. Jama Oncology 2020, 6: 25-26. Ciccarese C, Strusi A, Arduini D, Russo P, Palermo G, Foschi N, Racioppi M, Tortora G, Iacovelli R: Post nephrectomy management of localized renal cell carcinoma. From risk stratification to therapeutic evidence in an evolving clinical scenario. Cancer Treatment Reviews 2023, 115 . Zhanghuang C, Wang JK, Yao ZG, Li L, Xie YC, Tang HY, Zhang K, Wu CC, Yang Z, Yan B: Development and Validation of a Nomogram to Predict Cancer-Specific Survival in Elderly Patients With Papillary Renal Cell Carcinoma. Frontiers in Public Health 2022, 10 . Vickers AJ, Elkin EB: Decision curve analysis: A novel method for evaluating prediction models. Medical Decision Making 2006, 26: 565-574. Elias R, Tcheuyap VT, Kaushik AK, Singla N, Gao M, Torras OR, Christie A, Mulgaonkar A, Woolford L, Stevens C, et al: A renal cell carcinoma tumorgraft platform to advance precision medicine. Cell Reports 2021, 37 . Wu QY, Huang G, Wei WJ, Liu JJ: Molecular Imaging of Renal Cell Carcinoma in Precision Medicine. Molecular Pharmaceutics 2022. Luis-Cardo A, Herranz-Amo F, Rodríguez-Cabero M, Quintana-Alvarez R, Esteban-Labrador L, Rodríguez-Fernández E, Mayor-de Castro J, Barbas-Bernardos G, Ramírez-Martín D, Hernández-Fernández C: Laparoscopic nephron sparing surgery and radical nephrectomy in cT1 renal tumors. Comparative analysis of complications and survival. Actas Urologicas Espanolas 2022, 46: 340-347. Mir MC, Derweesh I, Porpiglia F, Zargar H, Mottrie A, Autorino R: Partial Nephrectomy Versus Radical Nephrectomy for Clinical T1b and T2 Renal Tumors: A Systematic Review and Meta-analysis of Comparative Studies. European Urology 2017, 71: 606-617. Stout TE, Gellhaus PT, Tracy CR, Steinberg RL: Robotic Partial Radical Nephrectomy for Clinical T3a Tumors: A Narrative Review. Journal of Endourology 2023, 37: 978-985. Liu N, Qu F, Shi QC, Zhuang WY, Ma WL, Yang ZH, Sun J, Xu W, Zhang LH, Jia RP, et al: Nephron-Sparing Surgery for Adult Xp11.2 Translocation Renal Cell Carcinoma at Clinical T1 Stage: A Multicenter Study in China. Annals of Surgical Oncology 2021, 28: 1238-1246. Hannan R, McLaughlin MF, Pop LM, Pedrosa I, Kapur P, Garant A, Ahn C, Christie A, Zhu J, Wangg T, et al: Phase 2 Trial of Stereotactic Ablative Radiotherapy for Patients with Renal Cancer. European Urology 2023, 84 . Bekku K, Kawada T, Yanagisawa T, Karakiewicz PI, Shariat SF: Role of lymphadenectomy during primary surgery for kidney cancer. Current Opinion in Urology 2023, 33: 294-301. Rosenblad AK, Sundqvist P, Harmenberg U, Hellström M, Hofmann F, Kjellman A, Dahlin BIK, Lindblad P, Lindskog M, Lundstam S, Ljungberg B: Surgical waiting times and all-cause mortality in patients with non-metastatic renal cell carcinoma. Scandinavian Journal of Urology 2022, 56: 383-390. Additional Declarations No competing interests reported. Supplementary Files SupplementaryMaterial.docx Cite Share Download PDF Status: Published Journal Publication published 11 Nov, 2024 Read the published version in Scientific Reports → Version 1 posted Editorial decision: Revision requested 12 Aug, 2024 Reviews received at journal 10 Aug, 2024 Reviewers agreed at journal 02 Aug, 2024 Reviews received at journal 26 Jul, 2024 Reviewers agreed at journal 23 Jul, 2024 Reviewers invited by journal 18 Jul, 2024 Editor assigned by journal 18 Jul, 2024 Editor invited by journal 06 Jun, 2024 Submission checks completed at journal 06 Jun, 2024 First submitted to journal 26 May, 2024 You are reading this latest preprint version Research Square lets you share your work early, gain feedback from the community, and start making changes to your manuscript prior to peer review in a journal. As a division of Research Square Company, we’re committed to making research communication faster, fairer, and more useful. We do this by developing innovative software and high quality services for the global research community. Our growing team is made up of researchers and industry professionals working together to solve the most critical problems facing scientific publishing. Also discoverable on Platform About Our Team In Review Editorial Policies Advisory Board Help Center Resources Author Services Accessibility API Access RSS feed Manage Cookie Preferences © Research Square 2026 | ISSN 2693-5015 (online) Privacy Policy Terms of Service Do Not Sell My Personal Information {"props":{"pageProps":{"initialData":{"identity":"rs-4480345","acceptedTermsAndConditions":true,"allowDirectSubmit":false,"archivedVersions":[],"articleType":"Article","associatedPublications":[],"authors":[{"id":315187236,"identity":"4189d9a5-db5a-4434-987f-2be8bd18c6ba","order_by":0,"name":"Shuhong Yu","email":"","orcid":"","institution":"Renmin Hospital of Wuhan University","correspondingAuthor":false,"prefix":"","firstName":"Shuhong","middleName":"","lastName":"Yu","suffix":""},{"id":315187237,"identity":"6ca99a78-9719-4ce2-aaba-23e06ccc5f13","order_by":1,"name":"Xuanyu Wang","email":"","orcid":"","institution":"Zhongnan Hospital of Wuhan University","correspondingAuthor":false,"prefix":"","firstName":"Xuanyu","middleName":"","lastName":"Wang","suffix":""},{"id":315187238,"identity":"08ca49e2-96ef-4fa9-a146-59f9803d86ef","order_by":2,"name":"Siyu Wang","email":"","orcid":"","institution":"Renmin Hospital of Wuhan University","correspondingAuthor":false,"prefix":"","firstName":"Siyu","middleName":"","lastName":"Wang","suffix":""},{"id":315187239,"identity":"04ba43e0-d1f1-4e49-9546-881be1dbd3a8","order_by":3,"name":"Ximing Xu","email":"data:image/png;base64,iVBORw0KGgoAAAANSUhEUgAAAZAAAAAyAQMAAABI0h/eAAAABlBMVEX///8AAABVwtN+AAAACXBIWXMAAA7EAAAOxAGVKw4bAAAA3klEQVRIiWNgGAWjYDCCA1Cajb2x8QFDgQRRWhgbQDQfz+HDBgwGpGiRk0hLk2AwIEIH3/Hm5w8+7jmc2MaQY1bxw8AiccPtBsYPH3Nwa5E8c8ywccazNKCWM2Y3ewwkEjfcOcAsOXMbbi0GN3IYm3kO2CS2MfaY3eABabmRwMbMS1iLRGIbM49Z4R8StABtYWNLYybKFpBfZs44kGbcxsN8WFrGQMJ45o3EZrx+AYbYgw8fDhyWnT//YePHNxV1sn03kg9++IhHCwZwbIBGFPHAnjTlo2AUjIJRMBIAAAYaWE6i48zKAAAAAElFTkSuQmCC","orcid":"","institution":"Renmin Hospital of Wuhan University","correspondingAuthor":true,"prefix":"","firstName":"Ximing","middleName":"","lastName":"Xu","suffix":""}],"badges":[],"createdAt":"2024-05-26 14:08:20","currentVersionCode":1,"declarations":"","doi":"10.21203/rs.3.rs-4480345/v1","doiUrl":"https://doi.org/10.21203/rs.3.rs-4480345/v1","draftVersion":[],"editorialEvents":[{"content":"https://doi.org/10.1038/s41598-024-79070-2","type":"published","date":"2024-11-11T15:57:36+00:00"}],"editorialNote":"","failedWorkflow":false,"files":[{"id":59137413,"identity":"6420acac-ff0a-48ad-afdb-f4d1b5fa94d4","added_by":"auto","created_at":"2024-06-26 18:59:08","extension":"png","order_by":1,"title":"Figure 1","display":"","copyAsset":false,"role":"figure","size":152803,"visible":true,"origin":"","legend":"\u003cp\u003eKaplan Meier survival curve in surgically treated nmRCC patients. (A) Radiotherapy; (B) Chemotherapy.\u003c/p\u003e","description":"","filename":"floatimage1.png","url":"https://assets-eu.researchsquare.com/files/rs-4480345/v1/9036793196bfbf98ecfe354b.png"},{"id":59137417,"identity":"74cf1743-d9f9-4d00-b6b4-cc891c597ef6","added_by":"auto","created_at":"2024-06-26 18:59:08","extension":"png","order_by":2,"title":"Figure 2","display":"","copyAsset":false,"role":"figure","size":166501,"visible":true,"origin":"","legend":"\u003cp\u003eKaplan Meier survival curve of no LND and LND in nmRCC patients after RN (A) or RNRP(B) or RNPU(C).\u003c/p\u003e","description":"","filename":"floatimage2.png","url":"https://assets-eu.researchsquare.com/files/rs-4480345/v1/57c56aac5c26444b5d805c64.png"},{"id":59137415,"identity":"761619c8-6b20-4965-b5b3-f82129a7da73","added_by":"auto","created_at":"2024-06-26 18:59:08","extension":"png","order_by":3,"title":"Figure 3","display":"","copyAsset":false,"role":"figure","size":202847,"visible":true,"origin":"","legend":"\u003cp\u003eKaplan Meier survival curve in nmRCC patients. (A) PN vs RN. (B) RNRP vs RNPU. (C) PN vs RNRP. (D) PN vs RNPU.\u003c/p\u003e","description":"","filename":"floatimage3.png","url":"https://assets-eu.researchsquare.com/files/rs-4480345/v1/defae769ea86d9ffd1469904.png"},{"id":59138232,"identity":"ce166cec-bd80-4d21-b99d-ecdb6df12dce","added_by":"auto","created_at":"2024-06-26 19:07:08","extension":"png","order_by":4,"title":"Figure 4","display":"","copyAsset":false,"role":"figure","size":298901,"visible":true,"origin":"","legend":"\u003cp\u003eEstablishing a prognostic prediction model. (A) Predictive efficacy of different deep learning algorithms. (B) Characteristic importance of prognostic models. C-index (C), ROC (D), calibration curve (E), and DCA curve (F) are used to evaluate models.\u003c/p\u003e","description":"","filename":"floatimage4.png","url":"https://assets-eu.researchsquare.com/files/rs-4480345/v1/d579f8eea1602a9a73e3cece.png"},{"id":59137419,"identity":"daa6a9ab-f6a1-4561-9ad4-3c712a280819","added_by":"auto","created_at":"2024-06-26 18:59:08","extension":"png","order_by":5,"title":"Figure 5","display":"","copyAsset":false,"role":"figure","size":211670,"visible":true,"origin":"","legend":"\u003cp\u003eKaplan Meier survival curve of nmRCC patients after RN and PN. (A) Prognostic differences with different stage. (B) Prognostic differences after PSM in stage Ⅰ. (C) Prognostic differences in patient populations screened by prognostic modeling.\u003c/p\u003e","description":"","filename":"floatimage5.png","url":"https://assets-eu.researchsquare.com/files/rs-4480345/v1/4e4a252096a345c2df23964f.png"},{"id":59138233,"identity":"1001d799-d3d6-44f5-80fe-09c95d8d6d4d","added_by":"auto","created_at":"2024-06-26 19:07:08","extension":"png","order_by":6,"title":"Figure 6","display":"","copyAsset":false,"role":"figure","size":152820,"visible":true,"origin":"","legend":"\u003cp\u003eKaplan Meier survival curve of nmRCC patients after RN and PN in grade Ⅰ(A), Ⅱ(B), Ⅲ(C), and Ⅲ+Ⅳ(D).\u003c/p\u003e","description":"","filename":"floatimage6.png","url":"https://assets-eu.researchsquare.com/files/rs-4480345/v1/2eb20b7e4b39f4418c0115a2.png"},{"id":69286971,"identity":"6b8161f6-e695-4e6d-b496-24e2a29de539","added_by":"auto","created_at":"2024-11-18 19:46:04","extension":"pdf","order_by":0,"title":"","display":"","copyAsset":false,"role":"manuscript-pdf","size":2217131,"visible":true,"origin":"","legend":"","description":"","filename":"manuscript.pdf","url":"https://assets-eu.researchsquare.com/files/rs-4480345/v1/8f293640-7524-4f1f-9e0e-3533087292f3.pdf"},{"id":59137414,"identity":"a2b95873-3386-4294-8d3d-34c2455b16f0","added_by":"auto","created_at":"2024-06-26 18:59:08","extension":"docx","order_by":1,"title":"","display":"","copyAsset":false,"role":"supplement","size":77677,"visible":true,"origin":"","legend":"","description":"","filename":"SupplementaryMaterial.docx","url":"https://assets-eu.researchsquare.com/files/rs-4480345/v1/52eab3217c023e135c894828.docx"}],"financialInterests":"No competing interests reported.","formattedTitle":"Predict Cancer-specific Survival After Nephrectomy for Nonmetastatic Renal Cancer: A Deep Learning-Based Prognostic Model","fulltext":[{"header":"1. Introduction","content":"\u003cp\u003eRenal cell carcinoma (RCC) is a complex malignancy with a multifactorial etiology, including genetic susceptibility, exposure to environmental carcinogens, and certain medical conditions [\u003cspan citationid=\"CR1\" class=\"CitationRef\"\u003e1\u003c/span\u003e]. RCC constitutes roughly 2.3% of all newly diagnosed malignant tumors in males and 1.3% in females [\u003cspan citationid=\"CR2\" class=\"CitationRef\"\u003e2\u003c/span\u003e], with a higher incidence rate observed in Western countries [\u003cspan citationid=\"CR3\" class=\"CitationRef\"\u003e3\u003c/span\u003e]. The incidence of RCC has been increasing at a rate of approximately 1% annually in recent times [\u003cspan citationid=\"CR2\" class=\"CitationRef\"\u003e2\u003c/span\u003e], and staging migration has contributed to a rise in the detection of early-stage RCC [\u003cspan citationid=\"CR4\" class=\"CitationRef\"\u003e4\u003c/span\u003e]. Consequently, surgical treatments for patients with low-stage RCC are attracting increasing interest [\u003cspan citationid=\"CR5\" class=\"CitationRef\"\u003e5\u003c/span\u003e].\u003c/p\u003e \u003cp\u003eFor localized RCC, surgical intervention remains the primary and most effective radical treatment modality [\u003cspan citationid=\"CR6\" class=\"CitationRef\"\u003e6\u003c/span\u003e]. The utilization of radiotherapy and chemotherapy is restricted in the management of nonmetastatic RCC (nmRCC) [\u003cspan citationid=\"CR7\" class=\"CitationRef\"\u003e7\u003c/span\u003e, \u003cspan citationid=\"CR8\" class=\"CitationRef\"\u003e8\u003c/span\u003e]. It is well-established that for patients with localized T1 RCC, partial nephrectomy (PN) is preferentially employed over radical nephrectomy (RN) [\u003cspan citationid=\"CR6\" class=\"CitationRef\"\u003e6\u003c/span\u003e]. However, the lack of an accepted standard for choosing between RN and PN for nmRCC patients necessitates further investigation, particularly in studies targeting specific patient populations to optimize benefits. Additionally, the therapeutic efficacy of lymph node dissection (LND) in the treatment of nmRCC remains controversial at best [\u003cspan citationid=\"CR9\" class=\"CitationRef\"\u003e9\u003c/span\u003e]. Determining the optimal treatment for nmRCC patients is challenging due to the diversity in tumor biology and patient characteristics [\u003cspan citationid=\"CR10\" class=\"CitationRef\"\u003e10\u003c/span\u003e]. The relative benefits of PN versus RN and the utility of LND are not fully resolved, highlighting the need for evidence-based guidelines and personalized treatment approaches. Post-nephrectomy survival outcomes are influenced by a multitude of factors, including tumor stage, grade, and TNM states [\u003cspan citationid=\"CR11\" class=\"CitationRef\"\u003e11\u003c/span\u003e]. Developing a prognostic model that accurately predicts cancer-specific survival (CSS) could inform treatment decisions and improve patient outcomes [\u003cspan citationid=\"CR12\" class=\"CitationRef\"\u003e12\u003c/span\u003e].\u003c/p\u003e \u003cp\u003eIn this study, we sought to characterize the population appropriate for nephrectomy based on SEER database, in which RN can be further classified based on the extent of resection: RN with removal of renal parenchyma alone (RNRP) and RN that includes simultaneous resection of the parenchyma, affected perirenal fascia, perirenal fat, and ureter (RNPU). We also evaluated risk factors and established prognostic model predicting cancer-specific survival (CSS) for nmRCC patients after nephrectomy. Our findings aim to contribute to the existing body of knowledge by providing insights into the optimal management strategies for nmRCC patients and guiding clinical decision-making.\u003c/p\u003e"},{"header":"2. Materials and Methods","content":"\u003cp\u003e \u003cb\u003eCohort Selection\u003c/b\u003e \u003c/p\u003e \u003cp\u003ePatients in our study were obtained from the SEER database using the following selection criteria for patients undergoing RCC surgery:(1) malignant tumor primary site limited to the \"kidney\"; (2) no evidence of distant metastasis; (3) pathologic subtypes of adenomas and adenocarcinomas, including 8140\u0026ndash;8389. Exclusion criteria were (1) age at diagnosis\u0026thinsp;\u0026lt;\u0026thinsp;20 years; (2) unknown characteristics; (3) survival time\u0026thinsp;\u0026lt;\u0026thinsp;30 days; (4) non-cancer death. Because publicly available data were used, no ethical approval or declaration was required in our study.\u003c/p\u003e \u003cp\u003e \u003cb\u003eData Collection\u003c/b\u003e \u003c/p\u003e \u003cp\u003eWe used SEER*Stat software version 8.4.1 to retrieve data (SEER Study data, 17 registry, November 2022 - sub \u0026minus;\u0026thinsp;2000\u0026ndash;2022) for our study. All patient data collected included: marital status, gender, age, tumor laterality, primary site surgery, radiation therapy, chemotherapy, year of diagnosis, primary tumor site, histologic type, T stage, N stage, tumor size, duration of treatment, number of tumors, stage, grading, and survival outcomes. Data were converted to binary or categorical variables when necessary to comply with specifications.\u003c/p\u003e \u003cp\u003e \u003cb\u003eModel Construction\u003c/b\u003e \u003c/p\u003e \u003cp\u003eAutogluon models deep learning framework (\u003cspan class=\"ExternalRef\"\u003e\u003cspan class=\"RefSource\"\u003ehttps://github.com/autogluon/autogluon\u003c/span\u003e\u003cspan address=\"https://github.com/autogluon/autogluon\" targettype=\"URL\" class=\"RefTarget\"\u003e\u003c/span\u003e\u003c/span\u003e) was utilized to construct a prognostic model of RCC patients for surgical decision making. The models were evaluated using Harrell\u0026rsquo;s Consistency Index (C-index), receiver operating characteristic (ROC) curve, calibration curve and decision curve analysis (DCA) [\u003cspan citationid=\"CR13\" class=\"CitationRef\"\u003e13\u003c/span\u003e] respectively. A user-friendly online website interactor was constructed using Dash (\u003cspan class=\"ExternalRef\"\u003e\u003cspan class=\"RefSource\"\u003ehttps://github.com/plotly/dash\u003c/span\u003e\u003cspan address=\"https://github.com/plotly/dash\" targettype=\"URL\" class=\"RefTarget\"\u003e\u003c/span\u003e\u003c/span\u003e).\u003c/p\u003e \u003cp\u003e \u003cb\u003eStatistical Analysis\u003c/b\u003e \u003c/p\u003e \u003cp\u003eThe Kaplan-Meier method was used to estimate survival. Cox regression analysis was used to determine the association between clinical variables and survival. Patients in the PN, RN, and other groups, were matched using 1:1 propensity score matching (PSM).\u003c/p\u003e"},{"header":"3. Results","content":"\u003cdiv id=\"Sec4\" class=\"Section2\"\u003e \u003ch2\u003e3.1. Univariate and multivariate COX regression analysis\u003c/h2\u003e \u003cp\u003eA total of 66,665 RCC patients from 2004 to 2020 were obtained from the SEER database. Univariate Cox regression analysis was used to screen for influential factors associated with survival of nmRCC patients. The results showed that marital status, gender, age, surgery, radiotherapy, chemotherapy, number of malignant tumors, tumor size, pathological grade, pathological stage, and TN stage were independent prognostic factors for nmRCC patients (Table\u0026nbsp;\u003cspan refid=\"Tab1\" class=\"InternalRef\"\u003e1\u003c/span\u003e).\u003c/p\u003e \u003cp\u003e \u003cdiv class=\"gridtable\"\u003e\u003ctable float=\"Yes\" id=\"Tab1\" border=\"1\"\u003e \u003ccaption language=\"En\"\u003e \u003cdiv class=\"CaptionNumber\"\u003eTable 1\u003c/div\u003e \u003cdiv class=\"CaptionContent\"\u003e \u003cp\u003eUnivariate and multivariate cox regression analysis in nmRCC patients.\u003c/p\u003e \u003c/div\u003e \u003c/caption\u003e \u003ccolgroup cols=\"5\"\u003e \u003cdiv align=\"left\" class=\"colspec\" colname=\"c1\" colnum=\"1\"\u003e\u003c/div\u003e \u003cdiv align=\"left\" class=\"colspec\" colname=\"c2\" colnum=\"2\"\u003e\u003c/div\u003e \u003cdiv align=\"left\" class=\"colspec\" colname=\"c3\" colnum=\"3\"\u003e\u003c/div\u003e \u003cdiv align=\"left\" class=\"colspec\" colname=\"c4\" colnum=\"4\"\u003e\u003c/div\u003e \u003cdiv align=\"left\" class=\"colspec\" colname=\"c5\" colnum=\"5\"\u003e\u003c/div\u003e \u003cthead\u003e \u003ctr\u003e \u003cth align=\"left\" colname=\"c1\" morerows=\"1\" rowspan=\"2\"\u003e \u003cp\u003e Variables\u003c/p\u003e \u003c/th\u003e \u003cth align=\"left\" colspan=\"2\" nameend=\"c3\" namest=\"c2\"\u003e \u003cp\u003eUnivariable\u003c/p\u003e \u003c/th\u003e \u003cth align=\"left\" colspan=\"2\" nameend=\"c5\" namest=\"c4\"\u003e \u003cp\u003eMultivariable\u003c/p\u003e \u003c/th\u003e \u003c/tr\u003e \u003ctr\u003e \u003cth align=\"left\" colname=\"c2\"\u003e \u003cp\u003eHR\u003c/p\u003e \u003c/th\u003e \u003cth align=\"left\" colname=\"c3\"\u003e \u003cp\u003eP value\u003c/p\u003e \u003c/th\u003e \u003cth align=\"left\" colname=\"c4\"\u003e \u003cp\u003eHR\u003c/p\u003e \u003c/th\u003e \u003cth align=\"left\" colname=\"c5\"\u003e \u003cp\u003eP value\u003c/p\u003e \u003c/th\u003e \u003c/tr\u003e \u003c/thead\u003e \u003ctbody\u003e \u003ctr\u003e \u003ctd align=\"left\" colname=\"c1\"\u003e \u003cp\u003eMarital Status\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c2\"\u003e\u0026nbsp;\u003c/td\u003e \u003ctd align=\"left\" colname=\"c3\"\u003e\u0026nbsp;\u003c/td\u003e \u003ctd align=\"left\" colname=\"c4\"\u003e\u0026nbsp;\u003c/td\u003e \u003ctd align=\"left\" colname=\"c5\"\u003e\u0026nbsp;\u003c/td\u003e \u003c/tr\u003e \u003ctr\u003e \u003ctd align=\"left\" colname=\"c1\"\u003e \u003cp\u003eSingle\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c2\"\u003e \u003cp\u003eReference\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c3\"\u003e \u003cp\u003eReference\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c4\"\u003e \u003cp\u003eReference\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c5\"\u003e \u003cp\u003eReference\u003c/p\u003e \u003c/td\u003e \u003c/tr\u003e \u003ctr\u003e \u003ctd align=\"left\" colname=\"c1\"\u003e \u003cp\u003eCoupled\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c2\"\u003e \u003cp\u003e0.876\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c3\"\u003e \u003cp\u003e\u0026lt;\u0026thinsp;0.0001\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c4\"\u003e \u003cp\u003e1.151\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c5\"\u003e \u003cp\u003e\u0026lt;\u0026thinsp;0.0001\u003c/p\u003e \u003c/td\u003e \u003c/tr\u003e \u003ctr\u003e \u003ctd align=\"left\" colname=\"c1\"\u003e \u003cp\u003eUnknown\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c2\"\u003e \u003cp\u003e0.771\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c3\"\u003e \u003cp\u003e\u0026lt;\u0026thinsp;0.0001\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c4\"\u003e \u003cp\u003e0.891\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c5\"\u003e \u003cp\u003e0.043\u003c/p\u003e \u003c/td\u003e \u003c/tr\u003e \u003ctr\u003e \u003ctd align=\"left\" colname=\"c1\"\u003e \u003cp\u003eGender\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c2\"\u003e\u0026nbsp;\u003c/td\u003e \u003ctd align=\"left\" colname=\"c3\"\u003e\u0026nbsp;\u003c/td\u003e \u003ctd align=\"left\" colname=\"c4\"\u003e\u0026nbsp;\u003c/td\u003e \u003ctd align=\"left\" colname=\"c5\"\u003e\u0026nbsp;\u003c/td\u003e \u003c/tr\u003e \u003ctr\u003e \u003ctd align=\"left\" colname=\"c1\"\u003e \u003cp\u003eMale\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c2\"\u003e \u003cp\u003eReference\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c3\"\u003e \u003cp\u003eReference\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c4\"\u003e \u003cp\u003eReference\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c5\"\u003e \u003cp\u003eReference\u003c/p\u003e \u003c/td\u003e \u003c/tr\u003e \u003ctr\u003e \u003ctd align=\"left\" colname=\"c1\"\u003e \u003cp\u003eFemale\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c2\"\u003e \u003cp\u003e1.251\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c3\"\u003e \u003cp\u003e\u0026lt;\u0026thinsp;0.0001\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c4\"\u003e \u003cp\u003e1.114\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c5\"\u003e \u003cp\u003e\u0026lt;\u0026thinsp;0.0001\u003c/p\u003e \u003c/td\u003e \u003c/tr\u003e \u003ctr\u003e \u003ctd align=\"left\" colname=\"c1\"\u003e \u003cp\u003eAge\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c2\"\u003e\u0026nbsp;\u003c/td\u003e \u003ctd align=\"left\" colname=\"c3\"\u003e\u0026nbsp;\u003c/td\u003e \u003ctd align=\"left\" colname=\"c4\"\u003e\u0026nbsp;\u003c/td\u003e \u003ctd align=\"left\" colname=\"c5\"\u003e\u0026nbsp;\u003c/td\u003e \u003c/tr\u003e \u003ctr\u003e \u003ctd align=\"left\" colname=\"c1\"\u003e \u003cp\u003e\u0026lt;\u0026thinsp;50\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c2\"\u003e \u003cp\u003eReference\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c3\"\u003e \u003cp\u003eReference\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c4\"\u003e \u003cp\u003eReference\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c5\"\u003e \u003cp\u003eReference\u003c/p\u003e \u003c/td\u003e \u003c/tr\u003e \u003ctr\u003e \u003ctd align=\"left\" colname=\"c1\"\u003e \u003cp\u003e50\u0026ndash;60\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c2\"\u003e \u003cp\u003e1.432\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c3\"\u003e \u003cp\u003e\u0026lt;\u0026thinsp;0.0001\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c4\"\u003e \u003cp\u003e1.400\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c5\"\u003e \u003cp\u003e\u0026lt;\u0026thinsp;0.0001\u003c/p\u003e \u003c/td\u003e \u003c/tr\u003e \u003ctr\u003e \u003ctd align=\"left\" colname=\"c1\"\u003e \u003cp\u003e60\u0026ndash;70\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c2\"\u003e \u003cp\u003e2.891\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c3\"\u003e \u003cp\u003e\u0026lt;\u0026thinsp;0.0001\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c4\"\u003e \u003cp\u003e2.706\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c5\"\u003e \u003cp\u003e\u0026lt;\u0026thinsp;0.0001\u003c/p\u003e \u003c/td\u003e \u003c/tr\u003e \u003ctr\u003e \u003ctd align=\"left\" colname=\"c1\"\u003e \u003cp\u003e\u0026ge;\u0026thinsp;70\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c2\"\u003e \u003cp\u003e0.592\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c3\"\u003e \u003cp\u003e\u0026lt;\u0026thinsp;0.0001\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c4\"\u003e \u003cp\u003e0.654\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c5\"\u003e \u003cp\u003e\u0026lt;\u0026thinsp;0.0001\u003c/p\u003e \u003c/td\u003e \u003c/tr\u003e \u003ctr\u003e \u003ctd align=\"left\" colname=\"c1\"\u003e \u003cp\u003eLaterality\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c2\"\u003e\u0026nbsp;\u003c/td\u003e \u003ctd align=\"left\" colname=\"c3\"\u003e\u0026nbsp;\u003c/td\u003e \u003ctd align=\"left\" colname=\"c4\"\u003e\u0026nbsp;\u003c/td\u003e \u003ctd align=\"left\" colname=\"c5\"\u003e\u0026nbsp;\u003c/td\u003e \u003c/tr\u003e \u003ctr\u003e \u003ctd align=\"left\" colname=\"c1\"\u003e \u003cp\u003eLeft\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c2\"\u003e \u003cp\u003eReference\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c3\"\u003e \u003cp\u003eReference\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c4\"\u003e \u003cp\u003eReference\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c5\"\u003e \u003cp\u003eReference\u003c/p\u003e \u003c/td\u003e \u003c/tr\u003e \u003ctr\u003e \u003ctd align=\"left\" colname=\"c1\"\u003e \u003cp\u003eRight\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c2\"\u003e \u003cp\u003e0.957\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c3\"\u003e \u003cp\u003e0.028\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c4\"\u003e \u003cp\u003e1.012\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c5\"\u003e \u003cp\u003e0.565\u003c/p\u003e \u003c/td\u003e \u003c/tr\u003e \u003ctr\u003e \u003ctd align=\"left\" colname=\"c1\"\u003e \u003cp\u003eUnknown\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c2\"\u003e \u003cp\u003e1.639\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c3\"\u003e \u003cp\u003e0.269\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c4\"\u003e \u003cp\u003e0.799\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c5\"\u003e \u003cp\u003e0.616\u003c/p\u003e \u003c/td\u003e \u003c/tr\u003e \u003ctr\u003e \u003ctd align=\"left\" colname=\"c1\"\u003e \u003cp\u003eSurgery\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c2\"\u003e\u0026nbsp;\u003c/td\u003e \u003ctd align=\"left\" colname=\"c3\"\u003e\u0026nbsp;\u003c/td\u003e \u003ctd align=\"left\" colname=\"c4\"\u003e\u0026nbsp;\u003c/td\u003e \u003ctd align=\"left\" colname=\"c5\"\u003e\u0026nbsp;\u003c/td\u003e \u003c/tr\u003e \u003ctr\u003e \u003ctd align=\"left\" colname=\"c1\"\u003e \u003cp\u003eComplete/total nephrectomy\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c2\"\u003e \u003cp\u003eReference\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c3\"\u003e \u003cp\u003eReference\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c4\"\u003e \u003cp\u003eReference\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c5\"\u003e \u003cp\u003eReference\u003c/p\u003e \u003c/td\u003e \u003c/tr\u003e \u003ctr\u003e \u003ctd align=\"left\" colname=\"c1\"\u003e \u003cp\u003ePartial/subtotal nephrectomy\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c2\"\u003e \u003cp\u003e4.056\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c3\"\u003e \u003cp\u003e\u0026lt;\u0026thinsp;0.0001\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c4\"\u003e \u003cp\u003e3.593\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c5\"\u003e \u003cp\u003e\u0026lt;\u0026thinsp;0.0001\u003c/p\u003e \u003c/td\u003e \u003c/tr\u003e \u003ctr\u003e \u003ctd align=\"left\" colname=\"c1\"\u003e \u003cp\u003eNo surgery\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c2\"\u003e \u003cp\u003e0.567\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c3\"\u003e \u003cp\u003e\u0026lt;\u0026thinsp;0.0001\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c4\"\u003e \u003cp\u003e1.059\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c5\"\u003e \u003cp\u003e0.612\u003c/p\u003e \u003c/td\u003e \u003c/tr\u003e \u003ctr\u003e \u003ctd align=\"left\" colname=\"c1\"\u003e \u003cp\u003eRadiotherapy\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c2\"\u003e\u0026nbsp;\u003c/td\u003e \u003ctd align=\"left\" colname=\"c3\"\u003e\u0026nbsp;\u003c/td\u003e \u003ctd align=\"left\" colname=\"c4\"\u003e\u0026nbsp;\u003c/td\u003e \u003ctd align=\"left\" colname=\"c5\"\u003e\u0026nbsp;\u003c/td\u003e \u003c/tr\u003e \u003ctr\u003e \u003ctd align=\"left\" colname=\"c1\"\u003e \u003cp\u003eNone/Unknown\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c2\"\u003e \u003cp\u003eReference\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c3\"\u003e \u003cp\u003eReference\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c4\"\u003e \u003cp\u003eReference\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c5\"\u003e \u003cp\u003eReference\u003c/p\u003e \u003c/td\u003e \u003c/tr\u003e \u003ctr\u003e \u003ctd align=\"left\" colname=\"c1\"\u003e \u003cp\u003eYes\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c2\"\u003e \u003cp\u003e9.368\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c3\"\u003e \u003cp\u003e\u0026lt;\u0026thinsp;0.0001\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c4\"\u003e \u003cp\u003e2.474\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c5\"\u003e \u003cp\u003e\u0026lt;\u0026thinsp;0.0001\u003c/p\u003e \u003c/td\u003e \u003c/tr\u003e \u003ctr\u003e \u003ctd align=\"left\" colname=\"c1\"\u003e \u003cp\u003eChemotherapy\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c2\"\u003e\u0026nbsp;\u003c/td\u003e \u003ctd align=\"left\" colname=\"c3\"\u003e\u0026nbsp;\u003c/td\u003e \u003ctd align=\"left\" colname=\"c4\"\u003e\u0026nbsp;\u003c/td\u003e \u003ctd align=\"left\" colname=\"c5\"\u003e\u0026nbsp;\u003c/td\u003e \u003c/tr\u003e \u003ctr\u003e \u003ctd align=\"left\" colname=\"c1\"\u003e \u003cp\u003eNone/Unknown\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c2\"\u003e \u003cp\u003eReference\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c3\"\u003e \u003cp\u003eReference\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c4\"\u003e \u003cp\u003eReference\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c5\"\u003e \u003cp\u003eReference\u003c/p\u003e \u003c/td\u003e \u003c/tr\u003e \u003ctr\u003e \u003ctd align=\"left\" colname=\"c1\"\u003e \u003cp\u003eYes\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c2\"\u003e \u003cp\u003e7.177\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c3\"\u003e \u003cp\u003e\u0026lt;\u0026thinsp;0.0001\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c4\"\u003e \u003cp\u003e1.791\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c5\"\u003e \u003cp\u003e\u0026lt;\u0026thinsp;0.0001\u003c/p\u003e \u003c/td\u003e \u003c/tr\u003e \u003ctr\u003e \u003ctd align=\"left\" colname=\"c1\"\u003e \u003cp\u003eMonths to Treatment\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c2\"\u003e \u003cp\u003e1.007\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c3\"\u003e \u003cp\u003e0.248\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c4\"\u003e\u0026nbsp;\u003c/td\u003e \u003ctd align=\"left\" colname=\"c5\"\u003e\u0026nbsp;\u003c/td\u003e \u003c/tr\u003e \u003ctr\u003e \u003ctd align=\"left\" colname=\"c1\"\u003e \u003cp\u003eNumber of Malignant Tumors\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c2\"\u003e \u003cp\u003e0.978\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c3\"\u003e \u003cp\u003e0.030\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c4\"\u003e \u003cp\u003e0.952\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c5\"\u003e \u003cp\u003e0.023\u003c/p\u003e \u003c/td\u003e \u003c/tr\u003e \u003ctr\u003e \u003ctd align=\"left\" colname=\"c1\"\u003e \u003cp\u003eNumber of Borderline Tumors\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c2\"\u003e \u003cp\u003e0.964\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c3\"\u003e \u003cp\u003e0.701\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c4\"\u003e\u0026nbsp;\u003c/td\u003e \u003ctd align=\"left\" colname=\"c5\"\u003e\u0026nbsp;\u003c/td\u003e \u003c/tr\u003e \u003ctr\u003e \u003ctd align=\"left\" colname=\"c1\"\u003e \u003cp\u003eTumor size\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c2\"\u003e \u003cp\u003e1.004\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c3\"\u003e \u003cp\u003e\u0026lt;\u0026thinsp;0.0001\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c4\"\u003e \u003cp\u003e1.002\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c5\"\u003e \u003cp\u003e\u0026lt;\u0026thinsp;0.0001\u003c/p\u003e \u003c/td\u003e \u003c/tr\u003e \u003ctr\u003e \u003ctd align=\"left\" colname=\"c1\"\u003e \u003cp\u003eGrade\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c2\"\u003e\u0026nbsp;\u003c/td\u003e \u003ctd align=\"left\" colname=\"c3\"\u003e\u0026nbsp;\u003c/td\u003e \u003ctd align=\"left\" colname=\"c4\"\u003e\u0026nbsp;\u003c/td\u003e \u003ctd align=\"left\" colname=\"c5\"\u003e\u0026nbsp;\u003c/td\u003e \u003c/tr\u003e \u003ctr\u003e \u003ctd align=\"left\" colname=\"c1\"\u003e \u003cp\u003eⅠ\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c2\"\u003e \u003cp\u003eReference\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c3\"\u003e \u003cp\u003eReference\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c4\"\u003e \u003cp\u003eReference\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c5\"\u003e \u003cp\u003eReference\u003c/p\u003e \u003c/td\u003e \u003c/tr\u003e \u003ctr\u003e \u003ctd align=\"left\" colname=\"c1\"\u003e \u003cp\u003eⅡ\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c2\"\u003e \u003cp\u003e1.320\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c3\"\u003e \u003cp\u003e\u0026lt;\u0026thinsp;0.0001\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c4\"\u003e \u003cp\u003e1.126\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c5\"\u003e \u003cp\u003e0.005\u003c/p\u003e \u003c/td\u003e \u003c/tr\u003e \u003ctr\u003e \u003ctd align=\"left\" colname=\"c1\"\u003e \u003cp\u003eⅢ\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c2\"\u003e \u003cp\u003e3.208\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c3\"\u003e \u003cp\u003e\u0026lt;\u0026thinsp;0.0001\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c4\"\u003e \u003cp\u003e1.890\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c5\"\u003e \u003cp\u003e\u0026lt;\u0026thinsp;0.0001\u003c/p\u003e \u003c/td\u003e \u003c/tr\u003e \u003ctr\u003e \u003ctd align=\"left\" colname=\"c1\"\u003e \u003cp\u003eⅣ\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c2\"\u003e \u003cp\u003e9.433\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c3\"\u003e \u003cp\u003e\u0026lt;\u0026thinsp;0.0001\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c4\"\u003e \u003cp\u003e3.432\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c5\"\u003e \u003cp\u003e\u0026lt;\u0026thinsp;0.0001\u003c/p\u003e \u003c/td\u003e \u003c/tr\u003e \u003ctr\u003e \u003ctd align=\"left\" colname=\"c1\"\u003e \u003cp\u003eStage\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c2\"\u003e\u0026nbsp;\u003c/td\u003e \u003ctd align=\"left\" colname=\"c3\"\u003e\u0026nbsp;\u003c/td\u003e \u003ctd align=\"left\" colname=\"c4\"\u003e\u0026nbsp;\u003c/td\u003e \u003ctd align=\"left\" colname=\"c5\"\u003e\u0026nbsp;\u003c/td\u003e \u003c/tr\u003e \u003ctr\u003e \u003ctd align=\"left\" colname=\"c1\"\u003e \u003cp\u003eⅠ\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c2\"\u003e \u003cp\u003eReference\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c3\"\u003e \u003cp\u003eReference\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c4\"\u003e \u003cp\u003eReference\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c5\"\u003e \u003cp\u003eReference\u003c/p\u003e \u003c/td\u003e \u003c/tr\u003e \u003ctr\u003e \u003ctd align=\"left\" colname=\"c1\"\u003e \u003cp\u003eⅡ\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c2\"\u003e \u003cp\u003e3.000\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c3\"\u003e \u003cp\u003e\u0026lt;\u0026thinsp;0.0001\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c4\"\u003e \u003cp\u003e1.742\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c5\"\u003e \u003cp\u003e\u0026lt;\u0026thinsp;0.0001\u003c/p\u003e \u003c/td\u003e \u003c/tr\u003e \u003ctr\u003e \u003ctd align=\"left\" colname=\"c1\"\u003e \u003cp\u003eⅢ\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c2\"\u003e \u003cp\u003e5.949\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c3\"\u003e \u003cp\u003e\u0026lt;\u0026thinsp;0.0001\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c4\"\u003e \u003cp\u003e2.450\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c5\"\u003e \u003cp\u003e\u0026lt;\u0026thinsp;0.0001\u003c/p\u003e \u003c/td\u003e \u003c/tr\u003e \u003ctr\u003e \u003ctd align=\"left\" colname=\"c1\"\u003e \u003cp\u003eⅣ\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c2\"\u003e \u003cp\u003e22.795\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c3\"\u003e \u003cp\u003e\u0026lt;\u0026thinsp;0.0001\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c4\"\u003e \u003cp\u003e2.977\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c5\"\u003e \u003cp\u003e\u0026lt;\u0026thinsp;0.0001\u003c/p\u003e \u003c/td\u003e \u003c/tr\u003e \u003ctr\u003e \u003ctd align=\"left\" colname=\"c1\"\u003e \u003cp\u003eTstage\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c2\"\u003e\u0026nbsp;\u003c/td\u003e \u003ctd align=\"left\" colname=\"c3\"\u003e\u0026nbsp;\u003c/td\u003e \u003ctd align=\"left\" colname=\"c4\"\u003e\u0026nbsp;\u003c/td\u003e \u003ctd align=\"left\" colname=\"c5\"\u003e\u0026nbsp;\u003c/td\u003e \u003c/tr\u003e \u003ctr\u003e \u003ctd align=\"left\" colname=\"c1\"\u003e \u003cp\u003eT1\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c2\"\u003e \u003cp\u003eReference\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c3\"\u003e \u003cp\u003eReference\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c4\"\u003e \u003cp\u003eReference\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c5\"\u003e \u003cp\u003eReference\u003c/p\u003e \u003c/td\u003e \u003c/tr\u003e \u003ctr\u003e \u003ctd align=\"left\" colname=\"c1\"\u003e \u003cp\u003eT2\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c2\"\u003e \u003cp\u003e3.120\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c3\"\u003e \u003cp\u003e\u0026lt;\u0026thinsp;0.0001\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c4\"\u003e \u003cp\u003e1.299\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c5\"\u003e \u003cp\u003e0.048\u003c/p\u003e \u003c/td\u003e \u003c/tr\u003e \u003ctr\u003e \u003ctd align=\"left\" colname=\"c1\"\u003e \u003cp\u003eT3\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c2\"\u003e \u003cp\u003e5.959\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c3\"\u003e \u003cp\u003e\u0026lt;\u0026thinsp;0.0001\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c4\"\u003e \u003cp\u003e1.365\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c5\"\u003e \u003cp\u003e0.004\u003c/p\u003e \u003c/td\u003e \u003c/tr\u003e \u003ctr\u003e \u003ctd align=\"left\" colname=\"c1\"\u003e \u003cp\u003eT4\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c2\"\u003e \u003cp\u003e20.874\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c3\"\u003e \u003cp\u003e\u0026lt;\u0026thinsp;0.0001\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c4\"\u003e \u003cp\u003e1.972\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c5\"\u003e \u003cp\u003e0.002\u003c/p\u003e \u003c/td\u003e \u003c/tr\u003e \u003ctr\u003e \u003ctd align=\"left\" colname=\"c1\"\u003e \u003cp\u003eNstage\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c2\"\u003e\u0026nbsp;\u003c/td\u003e \u003ctd align=\"left\" colname=\"c3\"\u003e\u0026nbsp;\u003c/td\u003e \u003ctd align=\"left\" colname=\"c4\"\u003e\u0026nbsp;\u003c/td\u003e \u003ctd align=\"left\" colname=\"c5\"\u003e\u0026nbsp;\u003c/td\u003e \u003c/tr\u003e \u003ctr\u003e \u003ctd align=\"left\" colname=\"c1\"\u003e \u003cp\u003eN0\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c2\"\u003e \u003cp\u003eReference\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c3\"\u003e \u003cp\u003eReference\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c4\"\u003e \u003cp\u003eReference\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c5\"\u003e \u003cp\u003eReference\u003c/p\u003e \u003c/td\u003e \u003c/tr\u003e \u003ctr\u003e \u003ctd align=\"left\" colname=\"c1\"\u003e \u003cp\u003eN1\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c2\"\u003e \u003cp\u003e10.573\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c3\"\u003e \u003cp\u003e\u0026lt;\u0026thinsp;0.0001\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c4\"\u003e \u003cp\u003e2.485\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c5\"\u003e \u003cp\u003e\u0026lt;\u0026thinsp;0.0001\u003c/p\u003e \u003c/td\u003e \u003c/tr\u003e \u003ctr\u003e \u003ctd align=\"left\" colname=\"c1\"\u003e \u003cp\u003eN2\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c2\"\u003e \u003cp\u003e13.346\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c3\"\u003e \u003cp\u003e\u0026lt;\u0026thinsp;0.0001\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c4\"\u003e \u003cp\u003e2.333\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c5\"\u003e \u003cp\u003e\u0026lt;\u0026thinsp;0.0001\u003c/p\u003e \u003c/td\u003e \u003c/tr\u003e \u003c/tbody\u003e \u003c/colgroup\u003e \u003c/table\u003e\u003c/div\u003e \u003c/p\u003e \u003c/div\u003e \u003cdiv id=\"Sec5\" class=\"Section2\"\u003e \u003ch2\u003e3.2. Benefits of radiotherapy and chemotherapy in surgically treated nmRCC patients\u003c/h2\u003e \u003cp\u003ePatients who received additional radiotherapy (Before PSM: HR\u0026thinsp;=\u0026thinsp;10.10, 95%CI: 6.62\u0026ndash;45.41, p\u0026thinsp;\u0026lt;\u0026thinsp;0.0001; After PSM: HR\u0026thinsp;=\u0026thinsp;3.73, 95%CI༚2.72\u0026ndash;5.13, p\u0026thinsp;\u0026lt;\u0026thinsp;0.0001) or chemotherapy (Before PSM: HR\u0026thinsp;=\u0026thinsp;6.83, 95%CI༚5.65\u0026ndash;8.25, p\u0026thinsp;\u0026lt;\u0026thinsp;0.0001; After PSM: HR\u0026thinsp;=\u0026thinsp;1.74, 95%CI༚1.46\u0026ndash;2.06, p\u0026thinsp;\u0026lt;\u0026thinsp;0.0001) following surgery had a poorer prognosis (Fig.\u0026nbsp;\u003cspan refid=\"Fig1\" class=\"InternalRef\"\u003e1\u003c/span\u003eA-B). The post-PSM baseline data are presented in Supplementary Tables\u0026nbsp;1\u0026ndash;2.\u003c/p\u003e \u003cp\u003e \u003c/p\u003e \u003c/div\u003e \u003cdiv id=\"Sec6\" class=\"Section2\"\u003e \u003ch2\u003e3.3. Benefit of lymph node dissection in nmRCC patients with RN\u003c/h2\u003e \u003cp\u003eLND was associated with improved outcomes (Before PSM: HR\u0026thinsp;=\u0026thinsp;0.99, 95%CI: 0.93\u0026ndash;1.07, p\u0026thinsp;=\u0026thinsp;0.88; After PSM: HR\u0026thinsp;=\u0026thinsp;0.81, 95%CI༚0.73\u0026ndash;0.91, p\u0026thinsp;=\u0026thinsp;0.00047) (Fig.\u0026nbsp;\u003cspan refid=\"Fig2\" class=\"InternalRef\"\u003e2\u003c/span\u003eA). Specifically, LND was effective in enhancing the prognosis for RNRP patients (Before PSM: HR\u0026thinsp;=\u0026thinsp;0.53, 95%CI༚0.38\u0026ndash;0.77, p\u0026thinsp;\u0026lt;\u0026thinsp;0.0001; After PSM: HR\u0026thinsp;=\u0026thinsp;0.41, 95%CI༚0.27\u0026ndash;0.64, p\u0026thinsp;\u0026lt;\u0026thinsp;0.0001) (Fig.\u0026nbsp;\u003cspan refid=\"Fig2\" class=\"InternalRef\"\u003e2\u003c/span\u003eB), while it did not confer a similar benefit for RNPU patients (Before PSM: HR\u0026thinsp;=\u0026thinsp;1.35, 95%CI༚1.27\u0026ndash;1.45, p\u0026thinsp;\u0026lt;\u0026thinsp;0.0001; After PSM: HR\u0026thinsp;=\u0026thinsp;1.08, 95%CI༚0.95\u0026ndash;1.20, p\u0026thinsp;=\u0026thinsp;0.23) (Fig.\u0026nbsp;\u003cspan refid=\"Fig2\" class=\"InternalRef\"\u003e2\u003c/span\u003eC). The post-PSM baseline data are presented in Supplementary Tables\u0026nbsp;3\u0026ndash;5.\u003c/p\u003e \u003cp\u003e \u003c/p\u003e \u003c/div\u003e \u003cdiv id=\"Sec7\" class=\"Section2\"\u003e \u003ch2\u003e3.4. Comparison of the prognosis between PN and RN in nmRCC patients\u003c/h2\u003e \u003cp\u003eBefore PSM, PN-treated patients had a better prognosis, but this was reversed after performing PSM (Before PSM: HR\u0026thinsp;=\u0026thinsp;1.80, 95%CI: 1.52\u0026ndash;2.13, p\u0026thinsp;\u0026lt;\u0026thinsp;0.0001; After PSM: HR\u0026thinsp;=\u0026thinsp;0.65, 95%CI༚0.47\u0026ndash;0.91, p\u0026thinsp;=\u0026thinsp;0.007) (Fig.\u0026nbsp;\u003cspan refid=\"Fig3\" class=\"InternalRef\"\u003e3\u003c/span\u003eA). The post-PSM baseline data are presented in Supplementary Tables\u0026nbsp;6\u0026ndash;9. RN can be divided into RNRP and RNRU, with RNRP showing a better prognosis (Before PSM: HR\u0026thinsp;=\u0026thinsp;0.22, 95%CI༚0.21\u0026ndash;0.23, p\u0026thinsp;\u0026lt;\u0026thinsp;0.0001; After PSM: HR\u0026thinsp;=\u0026thinsp;0.63, 95%CI༚0.57\u0026ndash;0.69, p\u0026thinsp;\u0026lt;\u0026thinsp;0.0001) (Fig.\u0026nbsp;\u003cspan refid=\"Fig3\" class=\"InternalRef\"\u003e3\u003c/span\u003eB). Analysis revealed that patients after RNRP exhibited superior CSS than PN (Before PSM: HR\u0026thinsp;=\u0026thinsp;0.52, 95%CI༚0.38\u0026ndash;0.71, p\u0026thinsp;\u0026lt;\u0026thinsp;0.0001; After PSM: HR\u0026thinsp;=\u0026thinsp;0.49, 95%CI༚0.34\u0026ndash;0.71, p\u0026thinsp;\u0026lt;\u0026thinsp;0.0001) (Fig.\u0026nbsp;\u003cspan refid=\"Fig3\" class=\"InternalRef\"\u003e3\u003c/span\u003eC). No significant prognostic disparity was detected between RNPU-treated patients and PN-treated patients (Before PSM: HR\u0026thinsp;=\u0026thinsp;2.61, 95%CI༚2.26\u0026ndash;3.01, p\u0026thinsp;\u0026lt;\u0026thinsp;0.0001; After PSM: HR\u0026thinsp;=\u0026thinsp;0.92, 95%CI༚0.67\u0026ndash;1.28, p\u0026thinsp;=\u0026thinsp;0.62) (Fig.\u0026nbsp;\u003cspan refid=\"Fig3\" class=\"InternalRef\"\u003e3\u003c/span\u003eD).\u003c/p\u003e \u003cp\u003e \u003c/p\u003e \u003c/div\u003e \u003cdiv id=\"Sec8\" class=\"Section2\"\u003e \u003ch2\u003e3.5. Establishing a prognostic prediction model for nmRCC patients using deep learning\u003c/h2\u003e \u003cp\u003eSurvival analyses have indicated that RN may confer potentially superior outcomes compared to PN, necessitating the identification of populations that optimally benefit from RN. Consequently, the 2,724 nmRCC patients, matched according to criteria, were subdivided into a training cohort (2,180 patients) and a testing cohort (544 patients) at an 8:2 ratio, excluding those with less than 365 days of survival data. Prognostic models for nmRCC patients after nephrectomy were developed utilizing various deep learning methodologies, with the model exhibiting the highest efficacy chosen for further analysis (Fig.\u0026nbsp;\u003cspan refid=\"Fig4\" class=\"InternalRef\"\u003e4\u003c/span\u003eA). The importance of each feature is illustrated in the graphic, with 'year' denoting different temporal milestones (1/3/5/7/9 years) for assessing survival status (Fig.\u0026nbsp;\u003cspan refid=\"Fig4\" class=\"InternalRef\"\u003e4\u003c/span\u003eB). The C-index and area under the curve (AUC) values were computed for 1/3/5/7/9 years survival prediction intervals, both in the training and testing cohorts (Figs.\u0026nbsp;\u003cspan refid=\"Fig4\" class=\"InternalRef\"\u003e4\u003c/span\u003eC-D). The calibration and DCA performed satisfactorily (Figs.\u0026nbsp;\u003cspan refid=\"Fig4\" class=\"InternalRef\"\u003e4\u003c/span\u003eE-F).\u003c/p\u003e \u003cp\u003e \u003c/p\u003e \u003c/div\u003e \u003cdiv id=\"Sec9\" class=\"Section2\"\u003e \u003ch2\u003e3.6. Stage I nmRCC patients undergoing surgery are candidates for RN\u003c/h2\u003e \u003cp\u003eIn tandem with modeling prognosis, we anticipated delineating the principal cohort that would derive the greatest benefit from RN. Notably, our analysis of the matched cohort revealed that 99.6% of patients were classified as stage I, suggesting that stage I nmRCC patients was the primary population to benefit most significantly (Supplementary Table\u0026nbsp;8). Consequently, we conducted a subgroup analysis to the stage of nmRCC patients. The findings indicated that RN was associated with a superior prognosis compared to PN, only in the stage I cohort (HR\u0026thinsp;=\u0026thinsp;0.80, 95%CI: 0.62\u0026ndash;1.03, p\u0026thinsp;=\u0026thinsp;0.055) (Fig.\u0026nbsp;\u003cspan refid=\"Fig5\" class=\"InternalRef\"\u003e5\u003c/span\u003eA). Subsequent PSM of stage I patients revealed a significant prognostic improvement with RN relative to PN (HR\u0026thinsp;=\u0026thinsp;0.49, 95%CI༚0.34\u0026ndash;0.72, p\u0026thinsp;\u0026lt;\u0026thinsp;0.0001) (Fig.\u0026nbsp;\u003cspan refid=\"Fig5\" class=\"InternalRef\"\u003e5\u003c/span\u003eB). The post-PSM baseline data are presented in Supplementary Table\u0026nbsp;11. RN was associated with higher CSS rates (Before PSM: HR\u0026thinsp;=\u0026thinsp;0.65, 95%CI༚0.45\u0026ndash;0.95, p\u0026thinsp;=\u0026thinsp;0.0057; After PSM: HR\u0026thinsp;=\u0026thinsp;0.39, 95%CI༚0.24\u0026ndash;0.65, p\u0026thinsp;=\u0026thinsp;0.0001) (Fig.\u0026nbsp;\u003cspan refid=\"Fig5\" class=\"InternalRef\"\u003e5\u003c/span\u003eC).\u003c/p\u003e \u003cp\u003e \u003c/p\u003e \u003c/div\u003e \u003cdiv id=\"Sec10\" class=\"Section2\"\u003e \u003ch2\u003e3.7. Grade II stage I T1N0M0 nmRCC patients are the primary beneficiary population of RN\u003c/h2\u003e \u003cp\u003eAnalogously, our model traversal identified a patient cohort with the following demographic traits: grade = Ⅱ in 62.7%, stage = Ⅰ, and TMN\u0026thinsp;=\u0026thinsp;T1N0M0 (Supplementary Table\u0026nbsp;10). Consequently, a subpopulation analysis by grade became imperative. We examined the survival rates of renal cell carcinoma patients with TNM staging of T1N0M0 and stage Ⅰ, stratified by grade. The findings revealed no discernible survival disparities among patients with grade I (HR\u0026thinsp;=\u0026thinsp;0.90, 95%CI: 0.53\u0026ndash;1.52, p\u0026thinsp;=\u0026thinsp;0.68) (Fig.\u0026nbsp;\u003cspan refid=\"Fig6\" class=\"InternalRef\"\u003e6\u003c/span\u003eA). Conversely, grade II patients demonstrated greater suitability for RN (HR\u0026thinsp;=\u0026thinsp;0.51, 95%CI༚0.35\u0026ndash;0.75, p\u0026thinsp;\u0026lt;\u0026thinsp;0.0001) (Fig.\u0026nbsp;\u003cspan refid=\"Fig6\" class=\"InternalRef\"\u003e6\u003c/span\u003eB). No significant differences were noted in patients with grade III (HR\u0026thinsp;=\u0026thinsp;1.15, 95%CI༚0.51\u0026ndash;2.61, p\u0026thinsp;=\u0026thinsp;0.75) and IV (HR\u0026thinsp;=\u0026thinsp;1.18, 95%CI༚0.56\u0026ndash;2.47, p\u0026thinsp;=\u0026thinsp;0.69) (Figs.\u0026nbsp;\u003cspan refid=\"Fig6\" class=\"InternalRef\"\u003e6\u003c/span\u003eC-D). Therefore, RCC patients with grade II, stage I, T1N0M0 classification represent the predominant cohort that benefits most significantly from RN.\u003c/p\u003e \u003cp\u003e \u003c/p\u003e \u003c/div\u003e"},{"header":"4. Discussion","content":"\u003cp\u003eIn recent years, the advancement of precision medicine in RCC has necessitated a comprehensive understanding of the individual risks and benefits for each patient [\u003cspan citationid=\"CR14\" class=\"CitationRef\"\u003e14\u003c/span\u003e, \u003cspan citationid=\"CR15\" class=\"CitationRef\"\u003e15\u003c/span\u003e]. The increasing trend is to stratify patients based on disease attributes and predicted risk scores, thereby enhancing personalized care. Our study presents a surgical prognostic model that exhibits independent prognostic significance and has identified a particular advantage of RN for grade II, stage I, and T1N0M0 RCC patients. While numerous prospective studies investigate the application of PN in nmRCC across various stages, with no significant disparity in postoperative complications and survival between PN (216 cases) and RN (156 cases) in clinical T1 RCC [\u003cspan citationid=\"CR16\" class=\"CitationRef\"\u003e16\u003c/span\u003e]. In contrast, the utilization of PN should be more judiciously considered for clinical T2 and clinical T3a RCC, taking into account specific patient characteristics as well as tumor factors [\u003cspan citationid=\"CR17\" class=\"CitationRef\"\u003e17\u003c/span\u003e, \u003cspan citationid=\"CR18\" class=\"CitationRef\"\u003e18\u003c/span\u003e]. Our model introduces a more granular evaluation by integrating stage and grade as determinants of surgical advantage, potentially facilitating more personalized treatment decisions. Indeed, the use of PN for T1 nmRCC remains heterogeneous, and the population should be more narrowly delineated [\u003cspan citationid=\"CR19\" class=\"CitationRef\"\u003e19\u003c/span\u003e].\u003c/p\u003e \u003cp\u003eFurthermore, alongside the selection of the optimal surgical approach, the integration of surgery with additional treatment modalities constitutes a significant strategy for enhancing the prognosis of nmRCC patients. Our findings suggest that the combined use of radiotherapy and chemotherapy with surgery may not significantly improve outcomes for nmRCC patients. Hence, the refinement of surgical treatments and the establishment of surgical benefit profiles for distinct patient subsets may represent a more auspicious strategy than multimodal therapy. Emerging studies, such as Hannan et al.'s work on the efficacy and safety of stereotactic ablative radiation for primary RCC [\u003cspan citationid=\"CR20\" class=\"CitationRef\"\u003e20\u003c/span\u003e], suggest potential avenues for future research. Moreover, targeted therapies have shown promise for localized and locally advanced RCC [\u003cspan citationid=\"CR5\" class=\"CitationRef\"\u003e5\u003c/span\u003e], although data limitations precluded further examination in our study.\u003c/p\u003e \u003cp\u003eThe role of LND in enhancing survival for RCC patients with and without nodal involvement remains undetermined [\u003cspan citationid=\"CR9\" class=\"CitationRef\"\u003e9\u003c/span\u003e]. Our study contributes to this discussion by elucidating the differential benefits of LND in RNRP versus RNPU [\u003cspan citationid=\"CR21\" class=\"CitationRef\"\u003e21\u003c/span\u003e]. The impact of surgical waiting times on patient mortality is also an area of interest, with some studies indicating an increased risk of death [\u003cspan citationid=\"CR22\" class=\"CitationRef\"\u003e22\u003c/span\u003e]. Our study did not find treatment delay to be an independent risk factor, a finding that requires further validation.\u003c/p\u003e \u003cp\u003eTo our knowledge, this is the inaugural surgical prognostic model for RCC patients that can precisely identify the cohort that will derive the most benefit from surgery. The use of the PSM method has helped to mitigate bias and derive robust results. Nonetheless, the model retains certain limitations: it is a retrospective study, which makes avoiding selection bias difficult, and the sample size utilized for training is relatively small and derived from a single cohort. Consequently, prospective clinical trials and additional external validations are imperative.\u003c/p\u003e"},{"header":"5. Conclusions","content":"\u003cp\u003eFor nmRCC, combined nephrectomy with radiotherapy or chemotherapy are not recommended. In the choice of nephrectomy, RN is more suggested for grade II, stage I, and T1N0M0 patients. Moreover, LND is necessary when RNRP is performed.\u003c/p\u003e"},{"header":"Declarations","content":"\u003cp\u003e\u003cstrong\u003eEthics approval and consent to participate\u003c/strong\u003e\u003c/p\u003e\n\u003cp\u003ePatient consent was waived due to this article using data from the SEER database, which are publicly available deidentified patient data from the National Cancer Institute (NCI), USA.\u003c/p\u003e\n\u003cp\u003e\u003cstrong\u003eAvailability of data and materials\u003c/strong\u003e\u003c/p\u003e\n\u003cp\u003eThe datasets analysed in the current study are available from the corresponding author on reasonable request.\u003c/p\u003e\n\u003cp\u003e\u003cstrong\u003eCompeting interests\u003c/strong\u003e\u003c/p\u003e\n\u003cp\u003eNo conflict of interest existed in the present research.\u003c/p\u003e\n\u003cp\u003e\u003cstrong\u003eFunding\u003c/strong\u003e\u003c/p\u003e\n\u003cp\u003eNo funding in the present research.\u003c/p\u003e\n\u003cp\u003e\u003cstrong\u003eAuthors\u0026apos; contributions\u003c/strong\u003e\u003c/p\u003e\n\u003cp\u003eS.Y. and X.W. designed this research. S.Y. organized the processing flow. S.Y. and X.W. completed the whole analytic process of this study. S.W. organized and presented the results. S.Y., X.W., and S. W. contributed to the writing of the manuscript. X.X. provided administrative and technical support. All authors reviewed the manuscript, agreeing with the publishing.\u003c/p\u003e\n\u003cp\u003e\u003cstrong\u003eAcknowledgements\u003c/strong\u003e\u003c/p\u003e\n\u003cp\u003eWe want to be grateful for the SEER database.\u003c/p\u003e"},{"header":"References","content":"\u003col\u003e\n\u003cli\u003eLinehan WM, Ricketts CJ: \u003cstrong\u003eThe Cancer Genome Atlas of renal cell carcinoma: findings and clinical implications.\u003c/strong\u003e \u003cem\u003eNature Reviews Urology \u003c/em\u003e2019, \u003cstrong\u003e16:\u003c/strong\u003e539-552.\u003c/li\u003e\n\u003cli\u003eSiegel RL, Miller KD, Wagle NS, Jemal A: \u003cstrong\u003eCancer statistics, 2023.\u003c/strong\u003e \u003cem\u003eCa-a Cancer Journal for Clinicians \u003c/em\u003e2023, \u003cstrong\u003e73:\u003c/strong\u003e17-48.\u003c/li\u003e\n\u003cli\u003eFerlay J, Colombet M, Soerjomataram I, Dyba T, Randi G, Bettio M, Gavin A, Visser O, Bray F: \u003cstrong\u003eCancer incidence and mortality patterns in Europe: Estimates for 40 countries and 25 major cancers in 2018.\u003c/strong\u003e \u003cem\u003eEuropean Journal of Cancer \u003c/em\u003e2018, \u003cstrong\u003e103:\u003c/strong\u003e356-387.\u003c/li\u003e\n\u003cli\u003ePatel HD, Gupta M, Joice GA, Srivastava A, Alam R, Allaf ME, Pierorazio PM: \u003cstrong\u003eClinical Stage Migration and Survival for Renal Cell Carcinoma in the United States.\u003c/strong\u003e \u003cem\u003eEuropean Urology Oncology \u003c/em\u003e2019, \u003cstrong\u003e2:\u003c/strong\u003e343-348.\u003c/li\u003e\n\u003cli\u003eIngels A, Campi R, Capitanio U, Amparore D, Bertolo R, Carbonara U, Erdem S, Kara \u0026Ouml;, Klatte T, Kriegmair MC, et al: \u003cstrong\u003eComplementary roles of surgery and systemic treatment in clear cell renal cell carcinoma.\u003c/strong\u003e \u003cem\u003eNature Reviews Urology \u003c/em\u003e2022, \u003cstrong\u003e19:\u003c/strong\u003e391-418.\u003c/li\u003e\n\u003cli\u003eLjungberg B, Albiges L, Abu-Ghanem Y, Bedke J, Capitanio U, Dabestani S, Fern\u0026aacute;ndez-Pello S, Giles RH, Hofmann F, Hora M, et al: \u003cstrong\u003eEuropean Association of Urology Guidelines on Renal Cell Carcinoma: The 2022 Update.\u003c/strong\u003e \u003cem\u003eEuropean Urology \u003c/em\u003e2022, \u003cstrong\u003e82:\u003c/strong\u003e399-410.\u003c/li\u003e\n\u003cli\u003eGrabbert M, Grosu AL, Zamboglou C, Gratzke C: \u003cstrong\u003eNivolumab in Combination with Stereotactic Body Radiotherapy in Pretreated Patients with Metastatic Renal Cell Carcinoma. Results of the Phase II NIVES Study.\u003c/strong\u003e \u003cem\u003eEuropean Urology \u003c/em\u003e2022, \u003cstrong\u003e81:\u003c/strong\u003e622-622.\u003c/li\u003e\n\u003cli\u003eRyan CW, Tangen CM, Heath E, Stein MN, Meng M, Alva AS, Pal SK, Puzanov I, Clark J, Choueiri TK, et al: \u003cstrong\u003eAdjuvant everolimus after surgery for renal cell carcinoma (EVEREST): a double-blind, placebo-controlled, randomised, phase 3 trial.\u003c/strong\u003e \u003cem\u003eLancet \u003c/em\u003e2023, \u003cstrong\u003e402:\u003c/strong\u003e1043-1051.\u003c/li\u003e\n\u003cli\u003eNgai M, Chandrasekar T, Bratslavsky G, Goldberg H: \u003cstrong\u003eThe Current Role of Lymph Node Dissection in Nonmetastatic Localized Renal Cell Carcinoma.\u003c/strong\u003e \u003cem\u003eJournal of Clinical Medicine \u003c/em\u003e2023, \u003cstrong\u003e12\u003c/strong\u003e.\u003c/li\u003e\n\u003cli\u003eSingla N: \u003cstrong\u003eProgress Toward Precision Medicine in Frontline Treatment of Metastatic Renal Cell Carcinoma.\u003c/strong\u003e \u003cem\u003eJama Oncology \u003c/em\u003e2020, \u003cstrong\u003e6:\u003c/strong\u003e25-26.\u003c/li\u003e\n\u003cli\u003eCiccarese C, Strusi A, Arduini D, Russo P, Palermo G, Foschi N, Racioppi M, Tortora G, Iacovelli R: \u003cstrong\u003ePost nephrectomy management of localized renal cell carcinoma. From risk stratification to therapeutic evidence in an evolving clinical scenario.\u003c/strong\u003e \u003cem\u003eCancer Treatment Reviews \u003c/em\u003e2023, \u003cstrong\u003e115\u003c/strong\u003e.\u003c/li\u003e\n\u003cli\u003eZhanghuang C, Wang JK, Yao ZG, Li L, Xie YC, Tang HY, Zhang K, Wu CC, Yang Z, Yan B: \u003cstrong\u003eDevelopment and Validation of a Nomogram to Predict Cancer-Specific Survival in Elderly Patients With Papillary Renal Cell Carcinoma.\u003c/strong\u003e \u003cem\u003eFrontiers in Public Health \u003c/em\u003e2022, \u003cstrong\u003e10\u003c/strong\u003e.\u003c/li\u003e\n\u003cli\u003eVickers AJ, Elkin EB: \u003cstrong\u003eDecision curve analysis: A novel method for evaluating prediction models.\u003c/strong\u003e \u003cem\u003eMedical Decision Making \u003c/em\u003e2006, \u003cstrong\u003e26:\u003c/strong\u003e565-574.\u003c/li\u003e\n\u003cli\u003eElias R, Tcheuyap VT, Kaushik AK, Singla N, Gao M, Torras OR, Christie A, Mulgaonkar A, Woolford L, Stevens C, et al: \u003cstrong\u003eA renal cell carcinoma tumorgraft platform to advance precision medicine.\u003c/strong\u003e \u003cem\u003eCell Reports \u003c/em\u003e2021, \u003cstrong\u003e37\u003c/strong\u003e.\u003c/li\u003e\n\u003cli\u003eWu QY, Huang G, Wei WJ, Liu JJ: \u003cstrong\u003eMolecular Imaging of Renal Cell Carcinoma in Precision Medicine.\u003c/strong\u003e \u003cem\u003eMolecular Pharmaceutics \u003c/em\u003e2022.\u003c/li\u003e\n\u003cli\u003eLuis-Cardo A, Herranz-Amo F, Rodr\u0026iacute;guez-Cabero M, Quintana-Alvarez R, Esteban-Labrador L, Rodr\u0026iacute;guez-Fern\u0026aacute;ndez E, Mayor-de Castro J, Barbas-Bernardos G, Ram\u0026iacute;rez-Mart\u0026iacute;n D, Hern\u0026aacute;ndez-Fern\u0026aacute;ndez C: \u003cstrong\u003eLaparoscopic nephron sparing surgery and radical nephrectomy in cT1 renal tumors. Comparative analysis of complications and survival.\u003c/strong\u003e \u003cem\u003eActas Urologicas Espanolas \u003c/em\u003e2022, \u003cstrong\u003e46:\u003c/strong\u003e340-347.\u003c/li\u003e\n\u003cli\u003eMir MC, Derweesh I, Porpiglia F, Zargar H, Mottrie A, Autorino R: \u003cstrong\u003ePartial Nephrectomy Versus Radical Nephrectomy for Clinical T1b and T2 Renal Tumors: A Systematic Review and Meta-analysis of Comparative Studies.\u003c/strong\u003e \u003cem\u003eEuropean Urology \u003c/em\u003e2017, \u003cstrong\u003e71:\u003c/strong\u003e606-617.\u003c/li\u003e\n\u003cli\u003eStout TE, Gellhaus PT, Tracy CR, Steinberg RL: \u003cstrong\u003eRobotic Partial Radical Nephrectomy for Clinical T3a Tumors: A Narrative Review.\u003c/strong\u003e \u003cem\u003eJournal of Endourology \u003c/em\u003e2023, \u003cstrong\u003e37:\u003c/strong\u003e978-985.\u003c/li\u003e\n\u003cli\u003eLiu N, Qu F, Shi QC, Zhuang WY, Ma WL, Yang ZH, Sun J, Xu W, Zhang LH, Jia RP, et al: \u003cstrong\u003eNephron-Sparing Surgery for Adult Xp11.2 Translocation Renal Cell Carcinoma at Clinical T1 Stage: A Multicenter Study in China.\u003c/strong\u003e \u003cem\u003eAnnals of Surgical Oncology \u003c/em\u003e2021, \u003cstrong\u003e28:\u003c/strong\u003e1238-1246.\u003c/li\u003e\n\u003cli\u003eHannan R, McLaughlin MF, Pop LM, Pedrosa I, Kapur P, Garant A, Ahn C, Christie A, Zhu J, Wangg T, et al: \u003cstrong\u003ePhase 2 Trial of Stereotactic Ablative Radiotherapy for Patients with Renal Cancer.\u003c/strong\u003e \u003cem\u003eEuropean Urology \u003c/em\u003e2023, \u003cstrong\u003e84\u003c/strong\u003e.\u003c/li\u003e\n\u003cli\u003eBekku K, Kawada T, Yanagisawa T, Karakiewicz PI, Shariat SF: \u003cstrong\u003eRole of lymphadenectomy during primary surgery for kidney cancer.\u003c/strong\u003e \u003cem\u003eCurrent Opinion in Urology \u003c/em\u003e2023, \u003cstrong\u003e33:\u003c/strong\u003e294-301.\u003c/li\u003e\n\u003cli\u003eRosenblad AK, Sundqvist P, Harmenberg U, Hellstr\u0026ouml;m M, Hofmann F, Kjellman A, Dahlin BIK, Lindblad P, Lindskog M, Lundstam S, Ljungberg B: \u003cstrong\u003eSurgical waiting times and all-cause mortality in patients with non-metastatic renal cell carcinoma.\u003c/strong\u003e \u003cem\u003eScandinavian Journal of Urology \u003c/em\u003e2022, \u003cstrong\u003e56:\u003c/strong\u003e383-390.\u003c/li\u003e\n\u003c/ol\u003e"}],"fulltextSource":"","fullText":"","funders":[],"hasAdminPriorityOnWorkflow":false,"hasManuscriptDocX":true,"hasOptedInToPreprint":true,"hasPassedJournalQc":"","hasAnyPriority":false,"hideJournal":false,"highlight":"","institution":"","isAcceptedByJournal":true,"isAuthorSuppliedPdf":false,"isDeskRejected":"","isHiddenFromSearch":false,"isInQc":false,"isInWorkflow":false,"isPdf":false,"isPdfUpToDate":true,"isWithdrawnOrRetracted":false,"journal":{"display":true,"email":"[email protected]","identity":"scientific-reports","isNatureJournal":false,"hasQc":true,"allowDirectSubmit":false,"externalIdentity":"scirep","sideBox":"Learn more about [Scientific Reports](http://www.nature.com/srep/)","snPcode":"","submissionUrl":"","title":"Scientific Reports","twitterHandle":"","acdcEnabled":true,"dfaEnabled":true,"editorialSystem":"stoa","reportingPortfolio":"Scientific Reports","inReviewEnabled":true,"inReviewRevisionsEnabled":true},"keywords":"renal cell carcinoma, nephrectomy, SEER, deep learning, prognostic model","lastPublishedDoi":"10.21203/rs.3.rs-4480345/v1","lastPublishedDoiUrl":"https://doi.org/10.21203/rs.3.rs-4480345/v1","license":{"name":"CC BY 4.0","url":"https://creativecommons.org/licenses/by/4.0/"},"manuscriptAbstract":"\u003ch2\u003eBackground\u003c/h2\u003e \u003cp\u003eThere are few analyses comparing radical nephrectomy with resection of the renal parenchyma only (RNRP) or radical nephrectomy that includes simultaneous resection of the parenchyma, affected perirenal fascia, perirenal fat, and ureter (RNPU) relative to partial nephrectomy (PN) for patients with nonmetastatic (M0) renal cell carcinoma (RCC) in terms of cancer-specific survival (CSS). This study aimed to evaluate the effect of different nephrectomy on the CSS of nonmetastatic RCC (nmRCC) and to identify the main beneficiaries of different nephrectomy.\u003c/p\u003e\u003ch2\u003eMethods\u003c/h2\u003e \u003cp\u003eThe 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 nmRCC patients after nephrectomy was established using the deep learning framework.\u003c/p\u003e\u003ch2\u003eResults\u003c/h2\u003e \u003cp\u003eKaplan-Meier analysis after PSM showed that lymph node dissection (LND) was effective in patients after RNRP (HR\u0026thinsp;=\u0026thinsp;0.41, 95%CI: 0.27\u0026ndash;0.64, p\u0026thinsp;\u0026lt;\u0026thinsp;0.0001). RNRP demonstrated less strongly association with CSS than was PN (HR\u0026thinsp;=\u0026thinsp;0.49, 95%CI༚0.34\u0026ndash;0.71, p\u0026thinsp;\u0026lt;\u0026thinsp;0.0001). The established prognostic model showed that grade II stage I T1N0M0 patients were the primary beneficiary population of RN.\u003c/p\u003e\u003ch2\u003eConclusions\u003c/h2\u003e \u003cp\u003eRN is more recommended than PN for grade II stage I T1N0M0 RCC patients. LND is necessary when performing RNRP.\u003c/p\u003e","manuscriptTitle":"Predict Cancer-specific Survival After Nephrectomy for Nonmetastatic Renal Cancer: A Deep Learning-Based Prognostic Model","msid":"","msnumber":"","nonDraftVersions":[{"code":1,"date":"2024-06-26 18:59:03","doi":"10.21203/rs.3.rs-4480345/v1","editorialEvents":[{"type":"communityComments","content":0},{"type":"decision","content":"Revision requested","date":"2024-08-12T07:40:01+00:00","index":"","fulltext":""},{"type":"editorInvitedReview","content":"","date":"2024-08-10T13:54:01+00:00","index":"hide","fulltext":""},{"type":"reviewerAgreed","content":"99527828719444632357472551236741191807","date":"2024-08-03T01:57:57+00:00","index":"hide","fulltext":""},{"type":"editorInvitedReview","content":"","date":"2024-07-26T23:14:50+00:00","index":"hide","fulltext":""},{"type":"reviewerAgreed","content":"253572405967946584353465293266142394822","date":"2024-07-23T15:17:50+00:00","index":"hide","fulltext":""},{"type":"reviewersInvited","content":"","date":"2024-07-18T15:02:49+00:00","index":"","fulltext":""},{"type":"editorAssigned","content":"","date":"2024-07-18T14:58:37+00:00","index":"","fulltext":""},{"type":"editorInvited","content":"","date":"2024-06-07T01:29:20+00:00","index":"","fulltext":""},{"type":"checksComplete","content":"","date":"2024-06-07T01:27:41+00:00","index":"","fulltext":""},{"type":"submitted","content":"Scientific Reports","date":"2024-05-26T14:02:11+00:00","index":"","fulltext":""}],"status":"published","journal":{"display":true,"email":"[email protected]","identity":"scientific-reports","isNatureJournal":false,"hasQc":true,"allowDirectSubmit":false,"externalIdentity":"scirep","sideBox":"Learn more about [Scientific Reports](http://www.nature.com/srep/)","snPcode":"","submissionUrl":"","title":"Scientific Reports","twitterHandle":"","acdcEnabled":true,"dfaEnabled":true,"editorialSystem":"stoa","reportingPortfolio":"Scientific Reports","inReviewEnabled":true,"inReviewRevisionsEnabled":true}}],"origin":"","ownerIdentity":"89afabe3-4c5c-4f69-a98f-92129d026cb1","owner":[],"postedDate":"June 26th, 2024","published":true,"recentEditorialEvents":[],"rejectedJournal":[],"revision":"","amendment":"","status":"published-in-journal","subjectAreas":[{"id":33327507,"name":"Biological sciences/Cancer/Urological cancer/Renal cancer"},{"id":33327508,"name":"Health sciences/Risk factors"},{"id":33327509,"name":"Health sciences/Nephrology/Kidney diseases/Renal cancer"}],"tags":[],"updatedAt":"2024-11-18T19:37:59+00:00","versionOfRecord":{"articleIdentity":"rs-4480345","link":"https://doi.org/10.1038/s41598-024-79070-2","journal":{"identity":"scientific-reports","isVorOnly":false,"title":"Scientific Reports"},"publishedOn":"2024-11-11 15:57:36","publishedOnDateReadable":"November 11th, 2024"},"versionCreatedAt":"2024-06-26 18:59:03","video":"","vorDoi":"10.1038/s41598-024-79070-2","vorDoiUrl":"https://doi.org/10.1038/s41598-024-79070-2","workflowStages":[]},"version":"v1","identity":"rs-4480345","journalConfig":"researchsquare"},"__N_SSP":true},"page":"/article/[identity]/[[...version]]","query":{"redirect":"/article/rs-4480345","identity":"rs-4480345","version":["v1"]},"buildId":"qtupq5eGEP_6zYnWcrvyt","isFallback":false,"isExperimentalCompile":false,"dynamicIds":[84888],"gssp":true,"scriptLoader":[]}