Diego A Martinez1, Scott R Levin1, Eili Y Klein2, Chirag R Parikh3, Steven Menez3, Richard A Taylor4, Jeremiah S Hinson5. 1. Department of Emergency Medicine, Johns Hopkins University, Baltimore, MD; Division of Health Sciences Informatics, Johns Hopkins University, Baltimore, MD. 2. Department of Emergency Medicine, Johns Hopkins University, Baltimore, MD; Center for Disease Dynamics, Economics and Policy, Washington, DC. 3. Department of Medicine, Division of Nephrology, Johns Hopkins University, Baltimore, MD. 4. Department of Emergency Medicine, Yale University, New Haven, CT. 5. Department of Emergency Medicine, Johns Hopkins University, Baltimore, MD. Electronic address: hinson@jhmi.edu.
Abstract
STUDY OBJECTIVE: Acute kidney injury occurs commonly and is a leading cause of prolonged hospitalization, development and progression of chronic kidney disease, and death. Early acute kidney injury treatment can improve outcomes. However, current decision support is not able to detect patients at the highest risk of developing acute kidney injury. We analyzed routinely collected emergency department (ED) data and developed prediction models with capacity for early identification of ED patients at high risk for acute kidney injury. METHODS: A multisite, retrospective, cross-sectional study was performed at 3 EDs between January 2014 and July 2017. All adult ED visits in which patients were hospitalized and serum creatinine level was measured both on arrival and again with 72 hours were included. We built machine-learning-based classifiers that rely on vital signs, chief complaints, medical history and active medical visits, and laboratory results to predict the development of acute kidney injury stage 1 and 2 in the next 24 to 72 hours, according to creatinine-based international consensus criteria. Predictive performance was evaluated out of sample by Monte Carlo cross validation. RESULTS: The final cohort included 91,258 visits by 59,792 unique patients. Seventy-two-hour incidence of acute kidney injury was 7.9% for stages greater than or equal to 1 and 1.0% for stages greater than or equal to 2. The area under the receiver operating characteristic curve for acute kidney injury prediction ranged from 0.81 (95% confidence interval 0.80 to 0.82) to 0.74 (95% confidence interval 0.74 to 0.75), with a median time from ED arrival to prediction of 1.7 hours (interquartile range 1.3 to 2.5 hours). CONCLUSION: Machine learning applied to routinely collected ED data identified ED patients at high risk for acute kidney injury up to 72 hours before they met diagnostic criteria. Further prospective evaluation is necessary.
STUDY OBJECTIVE:Acute kidney injury occurs commonly and is a leading cause of prolonged hospitalization, development and progression of chronic kidney disease, and death. Early acute kidney injury treatment can improve outcomes. However, current decision support is not able to detect patients at the highest risk of developing acute kidney injury. We analyzed routinely collected emergency department (ED) data and developed prediction models with capacity for early identification of ED patients at high risk for acute kidney injury. METHODS: A multisite, retrospective, cross-sectional study was performed at 3 EDs between January 2014 and July 2017. All adult ED visits in which patients were hospitalized and serum creatinine level was measured both on arrival and again with 72 hours were included. We built machine-learning-based classifiers that rely on vital signs, chief complaints, medical history and active medical visits, and laboratory results to predict the development of acute kidney injury stage 1 and 2 in the next 24 to 72 hours, according to creatinine-based international consensus criteria. Predictive performance was evaluated out of sample by Monte Carlo cross validation. RESULTS: The final cohort included 91,258 visits by 59,792 unique patients. Seventy-two-hour incidence of acute kidney injury was 7.9% for stages greater than or equal to 1 and 1.0% for stages greater than or equal to 2. The area under the receiver operating characteristic curve for acute kidney injury prediction ranged from 0.81 (95% confidence interval 0.80 to 0.82) to 0.74 (95% confidence interval 0.74 to 0.75), with a median time from ED arrival to prediction of 1.7 hours (interquartile range 1.3 to 2.5 hours). CONCLUSION: Machine learning applied to routinely collected ED data identified ED patients at high risk for acute kidney injury up to 72 hours before they met diagnostic criteria. Further prospective evaluation is necessary.
Authors: Jeremiah S Hinson; Eili Klein; Aria Smith; Matthew Toerper; Trushar Dungarani; David Hager; Peter Hill; Gabor Kelen; Joshua D Niforatos; R Scott Stephens; Alexandra T Strauss; Scott Levin Journal: NPJ Digit Med Date: 2022-07-16
Authors: Eric R Gottlieb; Mathew Samuel; Joseph V Bonventre; Leo A Celi; Heather Mattie Journal: Adv Chronic Kidney Dis Date: 2022-09 Impact factor: 4.305
Authors: Yukai Ang; Siqi Li; Marcus Eng Hock Ong; Feng Xie; Su Hooi Teo; Lina Choong; Riece Koniman; Bibhas Chakraborty; Andrew Fu Wah Ho; Nan Liu Journal: Sci Rep Date: 2022-05-02 Impact factor: 4.996
Authors: Meriem Khairoun; Jan Willem Uffen; Gurbey Ocak; Romy Koopsen; Saskia Haitjema; Jan Jelrik Oosterheert; Karin Kaasjager Journal: PLoS One Date: 2021-12-08 Impact factor: 3.240