Predictive approaches for acute dialysis requirement and death in COVID-19

Akhil Vaid, Lili Chan, Kumardeep Chaudhary, Suraj K. Jaladanki, Ishan Paranjpe, Adam Russak, Arash Kia, Prem Timsina, Matthew A. Levin, John Cijiang He, Erwin P. Böttinger, Alexander W. Charney, Zahi A. Fayad, Steven G. Coca, Benjamin S. Glicksberg, Girish N. Nadkarni, Alex Charney, Allan C. Just, Benjamin Glicksberg, Girish NadkarniLaura Huckins, Paul O’Reilly, Riccardo Miotto, Zahi Fayad, Adam J. Russak, Adeeb Rahman, Akhil Vaid, Amanda Le Dobbyn, Andrew Leader, Arden Moscati, Arjun Kapoor, Christie Chang, Christopher Bellaire, Daniel Carrion, Fayzan Chaudhry, Felix Richter, Georgios Soultanidis, Ishan Paranjpe, Ismail Nabeel, Jessica De Freitas, Jiayi Xu, Johnathan Rush, Kipp Johnson, Krishna Vemuri, Kumardeep Chaudhary, Lauren Lepow, Liam Cotter, Lora Liharska, Marco Pereanez, Mesude Bicak, Nicholas Defelice, Nidhi Naik, Noam Beckmann, Rajiv Nadukuru, Ross O’Hagan, Shan Zhao, Sulaiman Somani, Tielman T. Van Vleck, Tinaye Mutetwa, Tingyi Wanyan, Valentin Fauveau, Yang Yang, Yonit Lavin, Alona Lanksy, Ashish Atreja, Diane Del Valle, Dara Meyer, Eddye Golden, Farah Fasihuddin, Huei Hsun Wen, Jason Rogers, Jennifer Lilly Gutierrez, Laura Walker, Manbir Singh, Matteo Danieletto, Melissa A. Nieves, Micol Zweig, Renata Pyzik, Rima Fayad, Patricia Glowe, Sharlene Calorossi, Sparshdeep Kaur, Steven Ascolillo, Yovanna Roa, Anuradha Lala-Trindade, Steven G. Coca, Bethany Percha, Keith Sigel, Paz Polak, Robert Hirten, Talia Swartz, Ron Do, Ruth J.F. Loos, Dennis Charney, Eric Nestler, Barbara Murphy, David Reich, Erwin Böttinger, Kumar Chatani, Glenn Martin, Patricia Kovatch, Joseph Finkelstein, Barbara Murphy, Joseph Buxbaum, Judy Cho, Andrew Kasarskis, Carol Horowitz, Carlos Cordon-Cardo, Monica Sohn, Glenn Martin, Adolfo Garcia-Sastre, Emilia Bagiella, Florian Krammer, Judith Aberg, Jagat Narula, Robert Wright, Erik Lium, Rosalind Wright, Annetine Gelijns, Valentin Fuster, Miriam Merad

Research output: Contribution to journalArticlepeer-review

11 Scopus citations


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 theMount 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 theMount 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 precisionrecall 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.

Original languageEnglish
Pages (from-to)1158-1168
Number of pages11
JournalClinical Journal of the American Society of Nephrology
Issue number8
StatePublished - 1 Aug 2021


Dive into the research topics of 'Predictive approaches for acute dialysis requirement and death in COVID-19'. Together they form a unique fingerprint.

Cite this