scholarly journals Predicting the risk of postoperative acute kidney injury: development and assessment of a novel predictive nomogram

2021 ◽  
Vol 49 (8) ◽  
pp. 030006052110328
Author(s):  
Yukun Wu ◽  
Junxing Chen ◽  
Cheng Luo ◽  
Lingwu Chen ◽  
Bin Huang
Keyword(s):  
Renal Cell Carcinoma ◽  
Acute Kidney Injury ◽  
Cell Carcinoma ◽  
Renal Cell ◽  
Filtration Rate ◽  
Estimated Glomerular Filtration Rate ◽  
Kidney Injury ◽  
Surgical Time ◽  
Blood Uric Acid ◽  
Postoperative Aki

Objective This study aimed to establish and internally verify the risk nomogram of postoperative acute kidney injury (AKI) in patients with renal cell carcinoma. Methods We retrospectively collected data from 559 patients with renal cell carcinoma from June 2016 to May 2019 and established a prediction model. Twenty-six clinical variables were examined by least absolute shrinkage and selection operator regression analysis, and variables related to postoperative AKI were determined. The prediction model was established by multiple logistic regression analysis. Decision curve analysis was conducted to evaluate the nomogram. Results Independent predictors of postoperative AKI were smoking, hypertension, surgical time, blood glucose, blood uric acid, alanine aminotransferase, estimated glomerular filtration rate, and radical nephrectomy. The C index of the nomogram was 0.825 (0.790–0.860) and 0.814 was still obtained in the internal validation. The nomogram had better clinical benefit when the intervention was decided at the threshold probabilities of >4% and <79% for patients and doctors, respectively. Conclusions This novel postoperative AKI nomogram incorporating smoking, hypertension, the surgical time, blood glucose, blood uric acid, alanine aminotransferase, the estimated glomerular filtration rate, and radical nephrectomy is convenient for facilitating the individual postoperative risk prediction of AKI in patients with renal cell carcinoma.

scholarly journals Machine learning-based prediction of acute kidney injury after nephrectomy in patients with renal cell carcinoma

2021 ◽  
Vol 11 (1) ◽  
Author(s):  
Yeonhee Lee ◽  
Jiwon Ryu ◽  
Min Woo Kang ◽  
Kyung Ha Seo ◽  
Jayoun Kim ◽  
...  
Keyword(s):  
Machine Learning ◽  
Renal Cell Carcinoma ◽  
Acute Kidney Injury ◽  
Cell Carcinoma ◽  
Renal Cell ◽  
Kidney Injury ◽  
Gradient Boosting ◽  
Scoring Model ◽  
Postoperative Aki ◽  
Better Than

AbstractThe precise prediction of acute kidney injury (AKI) after nephrectomy for renal cell carcinoma (RCC) is an important issue because of its relationship with subsequent kidney dysfunction and high mortality. Herein we addressed whether machine learning (ML) algorithms could predict postoperative AKI risk better than conventional logistic regression (LR) models. A total of 4104 RCC patients who had undergone unilateral nephrectomy from January 2003 to December 2017 were reviewed. ML models such as support vector machine, random forest, extreme gradient boosting, and light gradient boosting machine (LightGBM) were developed, and their performance based on the area under the receiver operating characteristic curve, accuracy, and F1 score was compared with that of the LR-based scoring model. Postoperative AKI developed in 1167 patients (28.4%). All the ML models had higher performance index values than the LR-based scoring model. Among them, the LightGBM model had the highest value of 0.810 (0.783–0.837). The decision curve analysis demonstrated a greater net benefit of the ML models than the LR-based scoring model over all the ranges of threshold probabilities. The application of ML algorithms improves the predictability of AKI after nephrectomy for RCC, and these models perform better than conventional LR-based models.

scholarly journals P0845INCREASING TOTAL RENAL VOLUME AFTER NEPHRECTOMY FOR RENAL CELL CARCINOMA IS ASSOCIATED WITH RENAL FUNCTION EVOLUTION

2020 ◽  
Vol 35 (Supplement_3) ◽  
Author(s):  
SAUL PAMPA-SAICO ◽  
M Soledad Pizarro-Sánchez ◽  
Simona Alexandru ◽  
Laura García Puente-Suárez ◽  
María López-Picasso ◽  
...  
Keyword(s):  
Renal Cell Carcinoma ◽  
Renal Function ◽  
Cell Carcinoma ◽  
Renal Cell ◽  
Filtration Rate ◽  
Estimated Glomerular Filtration Rate ◽  
Linear Regression Analysis ◽  
Multivariate Linear Regression Analysis ◽  
Renal Volume

Abstract Background and Aims Renal cell carcinoma is the most common form of kidney cancer. Reduction of renal mass after radical nephrectomy (RN) in these patients, results in compensatory hypertrophy of the contralateral kidney. The capacity of compensation will determine the renal function (RF) evolution. Measuring of total renal volume (TRV) of the remaining kidney pre and post RN can help assess the RF evolution. Aims To determine the correlation between TRV pre and post nephrectomy (a year of follow-up) with RF and the factors that modify. Method A retrospective cohort study was carried out in our institution, in 62 patients who had underwent RN from 2014 to 2018, due to renal cell carcinoma (confirmed by histopathology). The demographic data included age, gender, body mass index (BMI), associated comorbidities, smoking habits were collected. Serum creatinine, estimated glomerular filtration rate (eGFR) and proteinuria were collected in the preoperative period and in the follow-up. The TRV was calculated pre and post (a year of follow-up) RN, using ellipsoid formula equation (computed tomography scan or magnetic resonance imaging). Renal function evolution was assessed by eGFR using the modification of diet in Renal Disease formula. Multivariate linear regression analysis was used to determine the predictor of TRV at 1 year of follow-up. Results The median age at the time of RN was 71 years old (range, 43-86 years). Most of them were men, 69% (43/19). The estimated glomerular filtration rate (FGe) pre and post nephrectomy was 74 (41-102) and 52.1 ml/min/ m2 (22-89) respectively (P=0.013). The TRV pre and post-nephrectomy was 165.3 (102.3-259.7) and 188.3 ml (115.3-271.2) respectively (P=0.001). On multivariate linear regression analysis, controlling for age and sex; the pre-nephrectomy FGe (β = 0.42; P = 0.023) and the pre TRV (β = 1.23; P &lt;0.0001) were positively correlated with the post-nephrectomy TRV, while the FGe at year of follow-up was correlated negatively (β = -1.11; P = 0.024) Conclusion The post nephrectomy TRV was positively correlated with TRV and FGe pre nephrectomy. While with the FGe at one year post nephrectomy was negatively correlated. The increasing TRV pre and post nephrectomy can help to predict renal function at a year of follow-up in this group of patients.

scholarly journals SaO032PAPILLARY RENAL CELL CARCINOMA ORIGINATES FROM A POPULATION OF RENAL PROGENITOR CELLS AND IS PROMOTED BY ACUTE KIDNEY INJURY

2018 ◽  
Vol 33 (suppl_1) ◽  
pp. i328-i328
Author(s):  
Anna Peired ◽  
Giulia Antonelli ◽  
Maria Lucia Angelotti ◽  
Alessandro Sisti ◽  
Marco Allinovi ◽  
...  
Keyword(s):  
Renal Cell Carcinoma ◽  
Acute Kidney Injury ◽  
Cell Carcinoma ◽  
Progenitor Cells ◽  
Renal Cell ◽  
Kidney Injury ◽  
Renal Progenitor Cells ◽  
Renal Progenitor

scholarly journals Parcial Nephrectomies - results of 12 years from an Oncology Institution

2016 ◽  
Vol 29 (2) ◽  
pp. 123
Author(s):  
Rui Freitas ◽  
Ricardo Cruz ◽  
Luís Antunes ◽  
Paulo Araújo ◽  
Pedro Silva ◽  
...  
Keyword(s):  
Renal Cell Carcinoma ◽  
Renal Function ◽  
Glomerular Filtration Rate ◽  
Cell Carcinoma ◽  
Glomerular Filtration ◽  
Renal Cell ◽  
Filtration Rate ◽  
Estimated Glomerular Filtration Rate ◽  
Warm Ischemia ◽  
Ischemia Time

<p><strong>Introduction:</strong> The diagnosis of renal cell carcinoma has been increasing in recent years, especially due to incidental cases, and thus indication for nephron-preserving surgery has also risen.<br /><strong>Objectives:</strong> To review a series of partial nephrectomies from an oncology institution namely technique features, survival and change in renal function.<br /><strong>Material and Methods:</strong> A retrospective analysis of all patients with renal tumors that were submitted to partial nephrectomy at our institution between January 2000 and December 2012.<br /><strong>Results:</strong> A total 156 partial nephrectomies were performed, 85 in men and 71 in women, with mean overall age of 62 ± 15 years. Surgical approach was transperitoneal laparoscopic in 23 cases with the remainder 133 through lumbotomy. Mean ischemic time was &lt; 25 min in all patients and complication rate was 10.9 %, mostly corresponding grade 2 and 3 of the Clavien-Dindo scale. Mean tumor size was 2.9 ± 1.4 cm and the surgical margin was focally affected by tumor in 9.6% of cases. Histologically, 26.2% of cases corresponded to clear cell renal cell carcinoma, with oncocytomas being the most common benign neoplasm with 14.7% of the total. There were 4 cases of recurrence and one case death at follow-up. The mean change in estimated glomerular filtration rate was -5.3 mL/min per 1.73 m2 (p &lt; 0.001). There was no association between warm ischemia time, body mass index, age, ASA score, presence of complications with this decrease in glomerular filtration rate.<br /><strong>Discussion:</strong> Our positive surgical margins cases were slightly above what is described in literature, however we didn’t find any predictive factor for such finding and ultimately there was no evidence of tumor recurrence or influence in survival in all these cases. Even though there was a significant decrease in estimated glomerular filtration rate, warm ischemia time was very low and only five patients presented with de novo eGFR &lt; 60 mL/min per 1.73 m2, and two patients started hemodialysis. A high volume center seems to be critical for technique optimization and complication management.<br /><strong>Conclusion:</strong> Our series of partial nephrectomies presents oncological results and preservation of renal function similar to those published in literature. This is a safe technique with good results, justifying its growth.</p><p> </p>

Sign in / Sign up

Export Citation Format

Share Document