Dataset Information

Prediction and Clinically Important Factors of Acute Kidney Injury Non-recovery

ABSTRACT:

Objective

This study aimed to identify phenotypic clinical features associated with acute kidney injury (AKI) to predict non-recovery from AKI at hospital discharge using electronic health record data.

Methods

Data for hospitalized patients in the AKI Recovery Evaluation Study were derived from a large healthcare delivery system in Taiwan between January 2011 and December 2017. Living patients with AKI non-recovery were used to derive and validate multiple predictive models. In total, 64 candidates variables, such as demographic characteristics, comorbidities, healthcare services utilization, laboratory values, and nephrotoxic medication use, were measured within 1 year before the index admission and during hospitalization for AKI.

Results

Among the top 20 important features in the predictive model, 8 features had a positive effect on AKI non-recovery prediction: AKI during hospitalization, serum creatinine (SCr) level at admission, receipt of dialysis during hospitalization, baseline comorbidity of cancer, AKI at admission, baseline lymphocyte count, baseline potassium, and low-density lipoprotein cholesterol levels. The predicted AKI non-recovery risk model using the eXtreme Gradient Boosting (XGBoost) algorithm achieved an area under the receiver operating characteristic (AUROC) curve statistic of 0.807, discrimination with a sensitivity of 0.724, and a specificity of 0.738 in the temporal validation cohort.

Conclusion

The machine learning model approach can accurately predict AKI non-recovery using routinely collected health data in clinical practice. These results suggest that multifactorial risk factors are involved in AKI non-recovery, requiring patient-centered risk assessments and promotion of post-discharge AKI care to prevent AKI complications.

SUBMITTER: Liu C

PROVIDER: S-EPMC8801583 | biostudies-literature |

REPOSITORIES: biostudies-literature

ACCESS DATA

Similar Datasets

Project description:Background and objectivesAKI requiring dialysis is a contributor to the growing burden of kidney failure, yet little is known about the frequency and patterns of recovery of AKI and its effect on outcomes in patients on incident dialysis.Design, setting, participants, & measurementsUsing the US Renal Data System, we evaluated a cohort of 1,045,540 patients on incident dialysis from January 1, 2005 to December 31, 2014, retrospectively. We examined the association of kidney failure due to AKI with the outcome of all-cause mortality and the associations of sex and race with kidney recovery.ResultsMean age was 63±15 years, and 32,598 (3%) patients on incident dialysis had kidney failure due to AKI. Compared with kidney failure due to diabetes mellitus, kidney failure attributed to AKI was associated with a higher mortality in the first 0-3 months following dialysis initiation (adjusted hazard ratio, 1.28; 95% confidence interval, 1.24 to 1.32) and 3-6 months (adjusted hazard ratio, 1.16; 95% confidence interval, 1.11 to 1.20). Of the patients with kidney failure due to AKI, 11,498 (35%) eventually recovered their kidney function, 95% of those within 12 months. Women had a lower likelihood of kidney recovery than men (adjusted hazard ratio, 0.86; 95% confidence interval, 0.83 to 0.90). Compared with whites, blacks (adjusted hazard ratio, 0.68; 95% confidence interval, 0.64 to 0.72), Asians (adjusted hazard ratio, 0.82; 95% confidence interval, 0.69 to 0.96), Hispanics (adjusted hazard ratio, 0.82; 95% confidence interval, 0.76 to 0.89), and Native Americans (adjusted hazard ratio, 0.72; 95% confidence interval, 0.54 to 0.95) had lower likelihoods of kidney recovery.ConclusionsKidney failure due to AKI confers a higher risk of mortality in the first 6 months compared with kidney failure due to diabetes or other causes. Recovery within 12 months is common, although less so among women than men and among black, Asian, Hispanic, and Native American patients than white patients.