Literature DB >> 32235839

A Simple Scoring Method for Predicting the Low Risk of Persistent Acute Kidney Injury in Critically Ill Adult Patients.

Ryo Matsuura1,2,3, Masao Iwagami4, Hidekazu Moriya5, Takayasu Ohtake5, Yoshifumi Hamasaki1,2, Masaomi Nangaku1,2, Kent Doi6, Shuzo Kobayashi5, Eisei Noiri7,8,9.   

Abstract

The renal angina index has been proposed to identify patients at high risk of persistent AKI, based on slight changes in serum creatinine and patient conditions. However, a concise scoring method has only been proposed for pediatric patients, and not for adult patients yet. Here, we developed and validated a concise scoring method using data on patients admitted to ICUs in 21 Japanese hospitals from 2012 to 2014. We randomly assigned to either discovery or validation cohorts, identified the factors significantly associated with persistent AKI using a multivariable logistic regression model in the discovery cohort to establish a scoring system, and assessed the validity of the scoring in the validation cohort using receiver operating characteristic analysis and the calibration slope. Among 8,320 patients admitted to the ICUs, persistent AKI was present in 1,064 (12.8%) patients. In the discovery cohort (n = 4,151), 'hyperbilirubinemia', 'sepsis' and 'ventilator and/or vasoactive' with small changes in serum creatinine were selected to establish the scoring. In the validation cohort (n = 4,169), the predicting model based on this scoring had a c-statistic of 0.79 (95%CI, 0.77-0.81) and was well calibrated. In conclusion, we established a concise scoring method to identify potential patients with persistent AKI, which performed well in the validation cohort.

Entities:  

Year:  2020        PMID: 32235839     DOI: 10.1038/s41598-020-62479-w

Source DB:  PubMed          Journal:  Sci Rep        ISSN: 2045-2322            Impact factor:   4.379


  2 in total

1.  Machine learning for early discrimination between transient and persistent acute kidney injury in critically ill patients with sepsis.

Authors:  Xiao-Qin Luo; Ping Yan; Ning-Ya Zhang; Bei Luo; Mei Wang; Ying-Hao Deng; Ting Wu; Xi Wu; Qian Liu; Hong-Shen Wang; Lin Wang; Yi-Xin Kang; Shao-Bin Duan
Journal:  Sci Rep       Date:  2021-10-12       Impact factor: 4.379

Review 2.  Predicting renal function recovery and short-term reversibility among acute kidney injury patients in the ICU: comparison of machine learning methods and conventional regression.

Authors:  Xiujuan Zhao; Yunwei Lu; Shu Li; Fuzheng Guo; Haiyan Xue; Lilei Jiang; Zhenzhou Wang; Chong Zhang; Wenfei Xie; Fengxue Zhu
Journal:  Ren Fail       Date:  2022-12       Impact factor: 3.222

  2 in total

北京卡尤迪生物科技股份有限公司 © 2022-2023.