@article{32856c3f0caf484fafe568d2d75a59e3,
title = "Real-Time Prediction of Acute Kidney Injury in Hospitalized Adults: Implementation and Proof of Concept",
abstract = "Rationale & Objective: Acute kidney injury (AKI) is diagnosed based on changes in serum creatinine concentration, a late marker of this syndrome. Algorithms that predict elevated risk for AKI are of great interest, but no studies have incorporated such an algorithm into the electronic health record to assist with clinical care. We describe the experience of implementing such an algorithm. Study Design: Prospective observational cohort study. Setting & Participants: 2,856 hospitalized adults in a single urban tertiary-care hospital with an algorithm-predicted risk for AKI in the next 24 hours >15%. Alerts were also used to target a convenience sample of 100 patients for measurement of 16 urine and 6 blood biomarkers. Exposure: Clinical characteristics at the time of pre-AKI alert. Outcome: AKI within 24 hours of pre-AKI alert (AKI24). Analytical Approach: Descriptive statistics and univariable associations. Results: At enrollment, mean predicted probability of AKI24 was 19.1%; 18.9% of patients went on to develop AKI24. Outcomes were generally poor among this population, with 29% inpatient mortality among those who developed AKI24 and 14% among those who did not (P < 0.001). Systolic blood pressure < 100 mm Hg (28% of patients with AKI24 vs 18% without), heart rate > 100 beats/min (32% of patients with AKI24 vs 24% without), and oxygen saturation < 92% (15% of patients with AKI24 vs 6% without) were all more common among those who developed AKI24. Of all biomarkers measured, only hyaline casts on urine microscopy (72% of patients with AKI24 vs 25% without) and fractional excretion of urea nitrogen (20% [IQR, 12%-36%] among patients with AKI24 vs 34% [IQR, 25%-44%] without) differed between those who did and did not develop AKI24. Limitations: Single-center study, reliance on serum creatinine level for AKI diagnosis, small number of patients undergoing biomarker evaluation. Conclusions: A real-time AKI risk model was successfully integrated into the EHR.",
keywords = "AKI risk, Acute kidney injury (AKI), IL-18, KIM-1, MCP-1, NGAL, [TIMP-2] × [IGFBP-7], algorithm implementation, biomarker assessment, electronic health record (EHR), hospitalized patients, inpatient mortality, kidney injury marker, prediction, prognostic model, prospective, renal function trajectory, serum creatinine (Scr)",
author = "Ugochukwu Ugwuowo and Yu Yamamoto and Tanima Arora and Ishan Saran and Caitlin Partridge and Aditya Biswas and Melissa Martin and Moledina, {Dennis G.} and Greenberg, {Jason H.} and Michael Simonov and Mansour, {Sherry G.} and Ricardo Vela and Testani, {Jeffrey M.} and Veena Rao and Keith Rentfro and Wassim Obeid and Parikh, {Chirag R.} and Wilson, {F. Perry}",
note = "Funding Information: This work was supported by National Institutes of Health grants R01DK113191 and P30DK079310 to Dr Wilson, K08DK110536 and a Charles H. Hood Foundation grant to Dr Greenberg, K23DK117065 to Dr Moledina, R01HL128973 , R01HL148354 , R01HL139629 to Dr Testani, and R01HL08757 to Dr Parikh. Dr Mansour is supported by the American Heart Association ( 18CDA34110151 ) and Patterson Trust Fund. The funders had no role in study design; data collection, analysis, or reporting; or the decision to submit for publication. Funding Information: Ugochukwu Ugwuowo, MBBS, Yu Yamamoto, MS, Tanima Arora, MBBS, Ishan Saran, BS, Caitlin Partridge, BA, Aditya Biswas, BS, Melissa Martin, MS, Dennis G. Moledina, MD, PhD, Jason H. Greenberg, MD, Michael Simonov, MD, Sherry G. Mansour, MD, Ricardo Vela, BA, Jeffrey M. Testani, MD, MTR, Veena Rao, PhD, Keith Rentfro, MBA, Wassim Obeid, PhD, Chirag R. Parikh, MD, PhD, and F. Perry Wilson, MD, MSCE. Study conception or design: UU, JMT, CP, FPW; acquisition, analysis, or interpretation of data: UU, YY, TA, IS, CRP, AB, MM, DGM, JHG, VR, KR, MS, SGM, RV, JMT, WO, CP, FPW. Each author contributed important intellectual content during manuscript drafting or revision and agrees to be personally accountable for the individual's own contributions and to ensure that questions pertaining to the accuracy or integrity of any portion of the work, even one in which the author was not directly involved, are appropriately investigated and resolved, including with documentation in the literature if appropriate. This work was supported by National Institutes of Health grants R01DK113191 and P30DK079310 to Dr Wilson, K08DK110536 and a Charles H. Hood Foundation grant to Dr Greenberg, K23DK117065 to Dr Moledina, R01HL128973, R01HL148354, R01HL139629 to Dr Testani, and R01HL08757 to Dr Parikh. Dr Mansour is supported by the American Heart Association (18CDA34110151) and Patterson Trust Fund. The funders had no role in study design; data collection, analysis, or reporting; or the decision to submit for publication. The authors declare that they have no relevant financial interests. The authors thank the Joint Data Analytics Team at Yale for help in data acquisition and model integration. Received March 9, 2020, as a submission to the expedited consideration track with 4 external peer reviews. Direct editorial input from a Statistics/Methods Editor and an Associate Editor, who served as Acting Editor-in-Chief. Accepted in revised form May 5, 2020. The involvement of an Acting Editor-in-Chief was to comply with AJKD's procedures for potential conflicts of interest for editors, described in the Information for Authors & Journal Policies, which also provides further information on expedited consideration (AJKD Express). Publisher Copyright: {\textcopyright} 2020 National Kidney Foundation, Inc.",
year = "2020",
month = dec,
doi = "10.1053/j.ajkd.2020.05.003",
language = "English (US)",
volume = "76",
pages = "806--814.e1",
journal = "American Journal of Kidney Diseases",
issn = "0272-6386",
publisher = "W.B. Saunders Ltd",
number = "6",
}