A new scoring model for the prediction of mortality in patients with acute kidney injury

Abstract

Currently, little information is available to stratify the risks and predict acute kidney injury (AKI)-associated death. In this present cross-sectional study, a novel scoring model was established to predict the probability of death within 90 days in patients with AKI diagnosis. For establishment of predictive scoring model, clinical data of 1169 hospitalized patients with AKI were retrospectively collected, and 731 patients of them as the first group were analyzed by the method of multivariate logistic regression analysis to create a scoring model and further predict patient death. Then 438 patients of them as the second group were used for validating this prediction model according to the established scoring method. Our results showed that Patient’s age, AKI types, respiratory failure, central nervous system failure, hypotension, and acute tubular necrosis-individual severity index (ATN-ISI) score are independent risk factors for predicting the death of AKI patients in the created scoring model. Moreover, our scoring model could accurately predict cumulative AKI and mortality rate in the second group. In conclusion, this study identified the risk factors of 90-day mortality for hospitalized AKI patients and established a scoring model for predicting 90-day prognosis, which could help to interfere in advance for improving the quality of life and reduce mortality rate of AKI patients.

Novel risk models to predict acute kidney disease and its outcomes in a Chinese hospitalized population with acute kidney injury

“…The model 2 was derived from 60% of the AKD cohort and prospectively validated by the remaining 40%. review of the literature 14,24,[31][32][33] . All the candidate variables in the derivation cohort were included as potential covariates in multivariable logistic regression models.…”

Mitophagy Plays a Protective Role in Iodinated Contrast-Induced Acute Renal Tubular Epithelial Cells Injury

“…Acute kidney injury (AKI) is a clinical syndrome with abnormal renal function or structure that occurs within 48 h and the leading clinical cause of chronic kidney disease, with high morbidity and mortality [1-3]. With the widely utilization of contrast media in the angiography and percutaneous coronary intervention, contrast-induced acute kidney injury (CI-AKI) has generally been considered as the third most common cause of hospital-acquired acute kidney injury (AKI) [4].…”

Real-Time Prediction of AKI Among Middle-Aged and Older in ICU: A Retrospective and Machine Learning Study

“…Despite the accuracy advantages and potential clinical implications of deep learning demonstrated in these analyses, there are certain obstacles to the application of computer models in the clinic settings, such as doctors do not believe and do not understand algorithms. First, a most of clinicians are more familiar with linear regression and logistical regression models than deep learning techniques, and logistic modeling shows the regression coe cient can be converted into OR value, which helps doctors to understand the strength of the relationship between variables and the outcome of the patient [28,29]. Despite deep neural network is excellent in building disease prediction models, the correlation between each variable and the outcome is poorly explained, so the deep learning algorithm is not good at giving suggestions of treatment advice based on the prediction.…”