Predictors of 30-day acute kidney injury following radical and partial nephrectomy for renal cell carcinoma

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.

Download Full-text

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

Nephrology Dialysis Transplantation ◽

10.1093/ndt/gfy104.sao032 ◽

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

Download Full-text

Post-operative acute kidney injury in patients with renal cell carcinoma is a potent risk factor for new-onset chronic kidney disease after radical nephrectomy

Nephrology Dialysis Transplantation ◽

10.1093/ndt/gfr094 ◽

2011 ◽

Vol 26 (11) ◽

pp. 3496-3501 ◽

Cited By ~ 53

Author(s):

A. Cho ◽

J. E. Lee ◽

G.-Y. Kwon ◽

W. Huh ◽

H. M. Lee ◽

...

Keyword(s):

Chronic Kidney Disease ◽

Renal Cell Carcinoma ◽

Acute Kidney Injury ◽

Risk Factor ◽

Kidney Disease ◽

Cell Carcinoma ◽

Renal Cell ◽

Radical Nephrectomy ◽

Kidney Injury ◽

New Onset

Download Full-text

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

Journal of International Medical Research ◽

10.1177/03000605211032838 ◽

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.

Download Full-text