TY - JOUR
T1 - Risk Prediction for Acute Kidney Injury in Patients Hospitalized With COVID-19
AU - McAdams, Meredith C.
AU - Xu, Pin
AU - Saleh, Sameh N
AU - Li, Michael
AU - Ostrosky-Frid, Mauricio
AU - Gregg, Lucile Parker
AU - Willett, Duwayne L.
AU - Velasco, Ferdinand
AU - Lehmann, Christoph U.
AU - Hedayati, S. Susan
N1 - Funding Information:
Dr. McAdams is supported by training grant 5T32DK007257-38 from the National Institutes of Diabetes and Digestive and Kidney Diseases (NIDDK). Dr. Gregg is supported by a VA CSR&D Career Development Award (IK2CX002368). Dr. Hedayati is supported by the Yin Quan-Yuen Distinguished Professorship in Nephrology at the University of Texas Southwestern Medical Center, Dallas, Texas. This work was also supported in part by the Houston VA Health Services Research & Development Center for Innovations grant (CIN13-413). The content is solely the responsibility of the authors and does not necessarily represent the official views of the NIDDK or the VA.
Funding Information:
Meredith C. McAdams, MD, Pin Xu, PhD, MS, Sameh N. Saleh, MD, Michael Li, BA, Mauricio Ostrosky-Frid, MD, L. Parker Gregg, MD, MSCS, Duwayne L. Willett, MD, Ferdinand Velasco, MD, Christoph U. Lehmann, MD, and S. Susan Hedayati, MD, MHSc. Research idea and study design: MCM, MOF, DLW, FV, CUL, SSH; data acquisition; DLW, FV; data analysis/interpretation: MCM, PX, SNS, ML, DLW, CUL, SSH; statistical analysis: PX, SSH; supervision and mentorship: LPG, CUL, SSH. Each author contributed important intellectual content during manuscript drafting or revision and accepts accountability for the overall work by ensuring that questions pertaining to the accuracy or integrity of any portion of the work are appropriately investigated and resolved. Dr. McAdams is supported by training grant 5T32DK007257-38 from the National Institutes of Diabetes and Digestive and Kidney Diseases (NIDDK). Dr. Gregg is supported by a VA CSR&D Career Development Award (IK2CX002368). Dr. Hedayati is supported by the Yin Quan-Yuen Distinguished Professorship in Nephrology at the University of Texas Southwestern Medical Center, Dallas, Texas. This work was also supported in part by the Houston VA Health Services Research & Development Center for Innovations grant (CIN13-413). The content is solely the responsibility of the authors and does not necessarily represent the official views of the NIDDK or the VA. The authors declare that they have no relevant financial interests. This study used the University of Texas Southwestern COVID-19 Registry Collaborative data source. We acknowledge the following people for their efforts in pulling data for this research: from the University of Texas Southwestern Medical Informatics group, Mereeja Varghese, Clarie Wang, and Ki Lai; and from the Texas Health Resources Medical Informatics group, Chaitanya Katterapalli, Sohal Sukhraj, and Andrew Masica. We extend a special thanks to Jeffrey SoRelle from Genomics and Molecular Pathology at UTSW for providing information on the COVID-19 variants. Received January 24, 2022 as a submission to the expedited consideration track with 2 external peer reviews. Direct editorial input from the Statistical Editor and the Editor-in-Chief. Accepted in revised form February 14, 2022.
Publisher Copyright:
© 2022 The Authors
PY - 2022/6
Y1 - 2022/6
N2 - Rationale & Objective: Acute kidney injury (AKI) is common in patients hospitalized with COVID-19, but validated, predictive models for AKI are lacking. We aimed to develop the best predictive model for AKI in hospitalized patients with coronavirus disease 2019 and assess its performance over time with the emergence of vaccines and the Delta variant. Study Design: Longitudinal cohort study. Setting & Participants: Hospitalized patients with a positive severe acute respiratory syndrome coronavirus 2 polymerase chain reaction result between March 1, 2020, and August 20, 2021 at 19 hospitals in Texas. Exposures: Comorbid conditions, baseline laboratory data, inflammatory biomarkers. Outcomes: AKI defined by KDIGO (Kidney Disease: Improving Global Outcomes) creatinine criteria. Analytical Approach: Three nested models for AKI were built in a development cohort and validated in 2 out-of-time cohorts. Model discrimination and calibration measures were compared among cohorts to assess performance over time. Results: Of 10,034 patients, 5,676, 2,917, and 1,441 were in the development, validation 1, and validation 2 cohorts, respectively, of whom 776 (13.7%), 368 (12.6%), and 179 (12.4%) developed AKI, respectively (P = 0.26). Patients in the validation cohort 2 had fewer comorbid conditions and were younger than those in the development cohort or validation cohort 1 (mean age, 54 ± 16.8 years vs 61.4 ± 17.5 and 61.7 ± 17.3 years, respectively, P < 0.001). The validation cohort 2 had higher median high-sensitivity C-reactive protein level (81.7 mg/L) versus the development cohort (74.5 mg/L; P < 0.01) and higher median ferritin level (696 ng/mL) versus both the development cohort (444 ng/mL) and validation cohort 1 (496 ng/mL; P < 0.001). The final model, which added high-sensitivity C-reactive protein, ferritin, and D-dimer levels, had an area under the curve of 0.781 (95% CI, 0.763-0.799). Compared with the development cohort, discrimination by area under the curve (validation 1: 0.785 [0.760-0.810], P = 0.79, and validation 2: 0.754 [0.716-0.795], P = 0.53) and calibration by estimated calibration index (validation 1: 0.116 [0.041-0.281], P = 0.11, and validation 2: 0.081 [0.045-0.295], P = 0.11) showed stable performance over time. Limitations: Potential billing and coding bias. Conclusions: We developed and externally validated a model to accurately predict AKI in patients with coronavirus disease 2019. The performance of the model withstood changes in practice patterns and virus variants.
AB - Rationale & Objective: Acute kidney injury (AKI) is common in patients hospitalized with COVID-19, but validated, predictive models for AKI are lacking. We aimed to develop the best predictive model for AKI in hospitalized patients with coronavirus disease 2019 and assess its performance over time with the emergence of vaccines and the Delta variant. Study Design: Longitudinal cohort study. Setting & Participants: Hospitalized patients with a positive severe acute respiratory syndrome coronavirus 2 polymerase chain reaction result between March 1, 2020, and August 20, 2021 at 19 hospitals in Texas. Exposures: Comorbid conditions, baseline laboratory data, inflammatory biomarkers. Outcomes: AKI defined by KDIGO (Kidney Disease: Improving Global Outcomes) creatinine criteria. Analytical Approach: Three nested models for AKI were built in a development cohort and validated in 2 out-of-time cohorts. Model discrimination and calibration measures were compared among cohorts to assess performance over time. Results: Of 10,034 patients, 5,676, 2,917, and 1,441 were in the development, validation 1, and validation 2 cohorts, respectively, of whom 776 (13.7%), 368 (12.6%), and 179 (12.4%) developed AKI, respectively (P = 0.26). Patients in the validation cohort 2 had fewer comorbid conditions and were younger than those in the development cohort or validation cohort 1 (mean age, 54 ± 16.8 years vs 61.4 ± 17.5 and 61.7 ± 17.3 years, respectively, P < 0.001). The validation cohort 2 had higher median high-sensitivity C-reactive protein level (81.7 mg/L) versus the development cohort (74.5 mg/L; P < 0.01) and higher median ferritin level (696 ng/mL) versus both the development cohort (444 ng/mL) and validation cohort 1 (496 ng/mL; P < 0.001). The final model, which added high-sensitivity C-reactive protein, ferritin, and D-dimer levels, had an area under the curve of 0.781 (95% CI, 0.763-0.799). Compared with the development cohort, discrimination by area under the curve (validation 1: 0.785 [0.760-0.810], P = 0.79, and validation 2: 0.754 [0.716-0.795], P = 0.53) and calibration by estimated calibration index (validation 1: 0.116 [0.041-0.281], P = 0.11, and validation 2: 0.081 [0.045-0.295], P = 0.11) showed stable performance over time. Limitations: Potential billing and coding bias. Conclusions: We developed and externally validated a model to accurately predict AKI in patients with coronavirus disease 2019. The performance of the model withstood changes in practice patterns and virus variants.
KW - Acute kidney injury
KW - COVID-19
KW - Delta variant
KW - model validation
KW - predictive model
UR - http://www.scopus.com/inward/record.url?scp=85129929968&partnerID=8YFLogxK
UR - http://www.scopus.com/inward/citedby.url?scp=85129929968&partnerID=8YFLogxK
U2 - 10.1016/j.xkme.2022.100463
DO - 10.1016/j.xkme.2022.100463
M3 - Article
C2 - 35434597
AN - SCOPUS:85129929968
SN - 2590-0595
VL - 4
JO - Kidney Medicine
JF - Kidney Medicine
IS - 6
M1 - 100463
ER -