Related Experiment Video
Updated: Nov 4, 2025
A Retrograde Implantation Approach for Peritoneal Dialysis Catheter Placement in Mice
Published on: July 20, 2022
Predictive Approaches for Acute Dialysis Requirement and Death in COVID-19
Akhil Vaid1,2, Lili Chan3,4, Kumardeep Chaudhary1,3
1The Mount Sinai Clinical Intelligence Center, Icahn School of Medicine at Mount Sinai, New York, New York.
Insights
Machine learning models can predict acute kidney injury (AKI) requiring dialysis or death in hospitalized COVID-19 patients. An eXtreme GradientBoosting (XGBoost) model demonstrated superior predictive performance compared to other methods.
Area of Science:
- Nephrology
- Data Science
- Infectious Diseases
Background:
- Acute kidney injury (AKI) is a frequent complication of coronavirus disease 2019 (COVID-19).
- Limited dialysis supplies and personnel pose challenges in managing AKI in COVID-19 patients.
Purpose of the Study:
- To develop and validate predictive models for dialysis initiation or death in hospitalized COVID-19 patients.
- To compare the performance of various machine learning models, including logistic regression, LASSO, random forest, and XGBoost.
Main Methods:
- Utilized data from 6093 adult COVID-19 patients admitted between March 2020 and December 2020.
- Developed and validated logistic regression, LASSO, random forest, and XGBoost models (with and without imputation).
- Predicted composite outcome of dialysis or death at 1, 3, 5, and 7 days post-admission.
Main Results:
- XGBoost without imputation achieved the highest predictive accuracy (AUROC 0.93-0.98, AUPRC 0.78-0.82 on internal validation).
- External validation confirmed XGBoost's superior performance (AUROC 0.85-0.87, AUPRC 0.27-0.54).
- Creatinine, BUN, and red cell distribution width were key predictors.
Conclusions:
- An XGBoost model without imputation effectively predicts the composite outcome of death or dialysis in COVID-19 patients.
- This model outperformed standard and other machine learning approaches in prediction accuracy.
Background And Objectives:
AKI treated with dialysis initiation is a common complication of coronavirus disease 2019 (COVID-19) among hospitalized patients. However, dialysis supplies and personnel are often limited.
Design, Setting, Participants, & Measurements:
Using data from adult patients hospitalized with COVID-19 from five hospitals from the Mount Sinai Health System who were admitted between March 10 and December 26, 2020, we developed and validated several models (logistic regression, Least Absolute Shrinkage and Selection Operator (LASSO), random forest, and eXtreme GradientBoosting [XGBoost; with and without imputation]) for predicting treatment with dialysis or death at various time horizons (1, 3, 5, and 7 days) after hospital admission. Patients admitted to the Mount Sinai Hospital were used for internal validation, whereas the other hospitals formed part of the external validation cohort. Features included demographics, comorbidities, and laboratory and vital signs within 12 hours of hospital admission.
Results:
A total of 6093 patients (2442 in training and 3651 in external validation) were included in the final cohort. Of the different modeling approaches used, XGBoost without imputation had the highest area under the receiver operating characteristic (AUROC) curve on internal validation (range of 0.93-0.98) and area under the precision-recall curve (AUPRC; range of 0.78-0.82) for all time points. XGBoost without imputation also had the highest test parameters on external validation (AUROC range of 0.85-0.87, and AUPRC range of 0.27-0.54) across all time windows. XGBoost without imputation outperformed all models with higher precision and recall (mean difference in AUROC of 0.04; mean difference in AUPRC of 0.15). Features of creatinine, BUN, and red cell distribution width were major drivers of the model's prediction.
Conclusions:
An XGBoost model without imputation for prediction of a composite outcome of either death or dialysis in patients positive for COVID-19 had the best performance, as compared with standard and other machine learning models.
Podcast:
This article contains a podcast at https://www.asn-online.org/media/podcast/CJASN/2021_07_09_CJN17311120.mp3.
Related Concept Videos
01:20Acute Kidney Injury V: Interprofessional Care
01:27Dialysis
Acute kidney injury develops suddenly and can be caused by pre-renal causes (e.g., hypovolemia, shock), intrinsic renal causes (e.g., acute tubular necrosis), or post-renal causes (e.g., urinary obstruction). In contrast, chronic renal failure progresses gradually over time and is often...
01:15Dialysis
01:30Acute Kidney Injury IV: Diagnostic Studies and Prevention
01:28Chronic Kidney Disease III: Interprofessional Care
01:28Drug Dosing in Renal Diseases: Estimation of Glomerular Filtration Rate Based on Serum Creatinine Concentration