1
|
Oh SW, Byun SS, Kim JK, Jeong CW, Kwak C, Hwang EC, Kang SH, Chung J, Kim YJ, Ha YS, Hong SH. Machine learning models for predicting the onset of chronic kidney disease after surgery in patients with renal cell carcinoma. BMC Med Inform Decis Mak 2024; 24:85. [PMID: 38519947 PMCID: PMC10960396 DOI: 10.1186/s12911-024-02473-8] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [Abstract] [Key Words] [MESH Headings] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Received: 09/28/2023] [Accepted: 03/03/2024] [Indexed: 03/25/2024] Open
Abstract
BACKGROUND Patients with renal cell carcinoma (RCC) have an elevated risk of chronic kidney disease (CKD) following nephrectomy. Therefore, continuous monitoring and subsequent interventions are necessary. It is recommended to evaluate renal function postoperatively. Therefore, a tool to predict CKD onset is essential for postoperative follow-up and management. METHODS We constructed a cohort using data from eight tertiary hospitals from the Korean Renal Cell Carcinoma (KORCC) database. A dataset of 4389 patients with RCC was constructed for analysis from the collected data. Nine machine learning (ML) models were used to classify the occurrence and nonoccurrence of CKD after surgery. The final model was selected based on the area under the receiver operating characteristic (AUROC), and the importance of the variables constituting the model was confirmed using the shapley additive explanation (SHAP) value and Kaplan-Meier survival analyses. RESULTS The gradient boost algorithm was the most effective among the various ML models tested. The gradient boost model demonstrated superior performance with an AUROC of 0.826. The SHAP value confirmed that preoperative eGFR, albumin level, and tumor size had a significant impact on the occurrence of CKD after surgery. CONCLUSIONS We developed a model to predict CKD onset after surgery in patients with RCC. This predictive model is a quantitative approach to evaluate post-surgical CKD risk in patients with RCC, facilitating improved prognosis through personalized postoperative care.
Collapse
Affiliation(s)
- Seol Whan Oh
- Department of Medical Informatics, College of Medicine, The Catholic University of Korea, 06591, Seoul, Korea
- Department of Biomedicine & Health Sciences, The Catholic University of Korea, 06591, Seoul, Korea
| | - Seok-Soo Byun
- Department of Urology, Seoul National University College of Medicine, Seoul National University Bundang Hospital, 13620, Seongnam, Korea
| | - Jung Kwon Kim
- Department of Urology, Seoul National University College of Medicine, Seoul National University Bundang Hospital, 13620, Seongnam, Korea
| | - Chang Wook Jeong
- Department of Urology, Seoul National University College of Medicine, Seoul National University Hospital, 03080, Seoul, Korea
| | - Cheol Kwak
- Department of Urology, Seoul National University College of Medicine, Seoul National University Hospital, 03080, Seoul, Korea
| | - Eu Chang Hwang
- Department of Urology, Chonnam National University Medical School, 61469, Gwangju, Korea
| | - Seok Ho Kang
- Department of Urology, Korea University School of Medicine, 02841, Seoul, Korea
| | - Jinsoo Chung
- Department of Urology, National Cancer Center, 10408, Goyang, Korea
| | - Yong-June Kim
- Department of Urology, Chungbuk National University College of Medicine, 28644, Cheongju, Korea
- Department of Urology, College of Medicine, Chungbuk National University, 28644, Cheongju, Korea
| | - Yun-Sok Ha
- Department of Urology, School of Medicine, Kyungpook National University Chilgok Hospital, Kyungpook National University, 41404, Daegu, Korea
| | - Sung-Hoo Hong
- Department of Urology, Seoul St. Mary's Hospital, College of Medicine, The Catholic University of Korea, Seoul, Republic of Korea.
| |
Collapse
|
2
|
Seethapathy H, Street S, Strohbehn I, Lee M, Zhao SH, Rusibamayila N, Chute DF, Gao X, Michaelson MD, Rahma OE, Choueiri TK, McGregor B, Sonpavde G, Salabao C, Kaymakcalan MD, Wei X, Gupta S, Motwani S, Leaf DE, Reynolds KL, Sise ME. Immune-related adverse events and kidney function decline in patients with genitourinary cancers treated with immune checkpoint inhibitors. Eur J Cancer 2021; 157:50-58. [PMID: 34482189 DOI: 10.1016/j.ejca.2021.07.031] [Citation(s) in RCA: 3] [Impact Index Per Article: 1.0] [Reference Citation Analysis] [Abstract] [Key Words] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Received: 03/20/2021] [Revised: 07/23/2021] [Accepted: 07/26/2021] [Indexed: 01/21/2023]
Abstract
BACKGROUND In patients with genitourinary cancers, the effect of immune checkpoint inhibitors (ICIs) on kidney function is unknown. PATIENTS AND METHODS This is a retrospective cohort study of patients with renal cell carcinoma (RCC) and urothelial carcinoma who received ICIs at two major cancer centers between 2012 and 2018. Cumulative incidence and Fine and Gray subdistribution hazard models were performed to determine predictors of the co-primary outcomes, (1) acute kidney injury (AKI) and (2) sustained estimated glomerular filtration rate (eGFR) loss, defined as a >20% decline in eGFR sustained ≥90 days. We also determined the association between immune-related adverse events (irAE) and adverse kidney outcomes among patients surviving ≥1 year. RESULTS 637 patients were included; 320 (50%) patients had RCC and 317 (50%) patients had urothelial carcinoma. Half of the cohort had eGFR<60 mL/min/1.73 m2 at baseline. irAEs, AKI, and sustained eGFR loss were common, occurring in 33%, 25% and 16%, respectively. Compared to patients with urothelial carcinoma, patients with RCC were more likely to develop irAEs (aHR 1.61, 95% CI 1.20-2.18) and sustained eGFR loss (aHR 1.97, 95% CI 1.24-3.12), but not AKI (aHR 1.53, 95% CI 0.97-2.41). Among patients surviving ≥1 years, experiencing a non-renal irAE was associated with a significantly higher risk of sustained eGFR loss (aHR 1.71, 95% CI 1.14-2.57). CONCLUSION AKI and sustained eGFR loss are common in patients with genitourinary cancers receiving ICIs. irAEs may be a novel risk factor for kidney function decline among patients receiving ICIs.
Collapse
Affiliation(s)
- Harish Seethapathy
- Department of Internal Medicine, Division of Nephrology, Massachusetts General Hospital, Boston, MA, USA.
| | - Sarah Street
- Department of Internal Medicine, Division of Nephrology, Massachusetts General Hospital, Boston, MA, USA
| | - Ian Strohbehn
- Department of Internal Medicine, Division of Nephrology, Massachusetts General Hospital, Boston, MA, USA
| | - Meghan Lee
- Department of Internal Medicine, Gastrointestinal Unit, Massachusetts General Hospital, Boston, MA, USA
| | - Sophia H Zhao
- Department of Internal Medicine, Division of Nephrology, Massachusetts General Hospital, Boston, MA, USA
| | - Nifasha Rusibamayila
- Department of Internal Medicine, Division of Nephrology, Massachusetts General Hospital, Boston, MA, USA
| | - Donald F Chute
- Department of Internal Medicine, Division of Nephrology, Massachusetts General Hospital, Boston, MA, USA
| | - Xin Gao
- Department of Internal Medicine, Division of Hematology and Oncology, Massachusetts General Hospital, Boston, MA, USA
| | - Marc D Michaelson
- Department of Internal Medicine, Division of Hematology and Oncology, Massachusetts General Hospital, Boston, MA, USA
| | - Osama E Rahma
- Department of Medical Oncology, Dana Farber Cancer Center, Boston, MA, USA
| | - Toni K Choueiri
- Department of Medical Oncology, Dana Farber Cancer Center, Boston, MA, USA
| | - Brad McGregor
- Department of Medical Oncology, Dana Farber Cancer Center, Boston, MA, USA
| | - Guru Sonpavde
- Department of Medical Oncology, Dana Farber Cancer Center, Boston, MA, USA
| | - Cristina Salabao
- Department of Medical Oncology, Dana Farber Cancer Center, Boston, MA, USA
| | | | - Xiao Wei
- Department of Medical Oncology, Dana Farber Cancer Center, Boston, MA, USA
| | - Shruti Gupta
- Department of Medicine, Division of Renal Medicine, Brigham and Women's Hospital, Boston, MA, USA
| | - Shveta Motwani
- Department of Medicine, Division of Renal Medicine, Brigham and Women's Hospital, Boston, MA, USA
| | - David E Leaf
- Department of Medicine, Division of Renal Medicine, Brigham and Women's Hospital, Boston, MA, USA
| | - Kerry L Reynolds
- Department of Internal Medicine, Division of Hematology and Oncology, Massachusetts General Hospital, Boston, MA, USA
| | - Meghan E Sise
- Department of Internal Medicine, Division of Nephrology, Massachusetts General Hospital, Boston, MA, USA
| |
Collapse
|
3
|
Zhang Y, Wu T, Xie J, Yan L, Guo X, Xu W, Wang L. Effects of metabolic syndrome on renal function after radical nephrectomy in patients with renal cell carcinoma. Int Urol Nephrol 2021; 53:2127-2135. [PMID: 33459957 DOI: 10.1007/s11255-020-02759-6] [Citation(s) in RCA: 3] [Impact Index Per Article: 1.0] [Reference Citation Analysis] [Abstract] [Key Words] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Received: 08/19/2020] [Accepted: 12/15/2020] [Indexed: 11/30/2022]
Abstract
PURPOSE Nephrectomy, partial or radical, remains the standard treatment for renal cell carcinoma (RCC). However, increased risk of chronic kidney disease (CKD) must still be considered. This study aimed to evaluate the effects of concomitant metabolic syndrome (MetS) on renal function in patients with RCC after radical nephrectomy. METHODS Medical records of 310 patients who underwent radical nephrectomy for clear-cell RCC at 900th Hospital of the Joint Logistics Support Force, PLA from December 2012 to January 2017 were reviewed retrospectively. Estimated glomerular filtration rate (eGFR) and CKD stages were calculated at one week preoperative as baseline and then at postoperative 1 week, 3 months, 12 months and 24 months. MetS patients were identified and enrolled in the MetS group (n = 31), and a non-MetS group was selected by propensity score matching (n = 31). Non-neoplastic renal parenchyma specimens taken at least 2 cm from edge of tumor were evaluated. RESULTS Baseline characteristics between the two groups were comparable. At 24 months postoperative, mean eGFR levels of the MetS group were significantly lower than those in the non-MetS group (62.7 vs. 73.3 ml/min/1.73 m2; p = 0.004). CKD stages were still more severe in the MetS group than those in the non-MetS group (p = 0.006). The proportions of global sclerosis, tubular atrophy and interstitial fibrosis were all significantly more prevalent in MetS patients, compared to non-MetS patients (all p < 0.05). CONCLUSION In RCC patients with MetS, the possibility of declining eGFR and CKD progression must be considered after radical nephrectomy. Routine monitoring of renal function must be emphasized.
Collapse
Affiliation(s)
- Yong Zhang
- Fuzong Clinical Medical College of Fujian Medical University, Fuzhou, People's Republic of China.,Division of Nephrology, The 900th Hospital of Joint Logistic Support Force, PLA, 156 West Second Ring Road, Fuzhou, 350025, People's Republic of China
| | - Tingkun Wu
- Fuzong Clinical Medical College of Fujian Medical University, Fuzhou, People's Republic of China
| | - Jingjing Xie
- Fuzong Clinical Medical College of Fujian Medical University, Fuzhou, People's Republic of China
| | - Liqun Yan
- Fuzong Clinical Medical College of Fujian Medical University, Fuzhou, People's Republic of China
| | - Xiuli Guo
- Fuzong Clinical Medical College of Fujian Medical University, Fuzhou, People's Republic of China
| | - Weijia Xu
- Fuzong Clinical Medical College of Fujian Medical University, Fuzhou, People's Republic of China
| | - Liping Wang
- Fuzong Clinical Medical College of Fujian Medical University, Fuzhou, People's Republic of China. .,Division of Nephrology, The 900th Hospital of Joint Logistic Support Force, PLA, 156 West Second Ring Road, Fuzhou, 350025, People's Republic of China.
| |
Collapse
|