@article{TEXTUAL,
      recid = {11164},
      author = {Churpek, Matthew M. and Carey, Kyle A. and Edelson, Dana  P. and Singh, Tripti and Astor, Brad C. and Gilbert, Emily  R. and Winslow, Christopher and Shah, Nirav and Afshar,  Majid and Koyner, Jay L.},
      title = {Internal and External Validation of a Machine Learning  Risk Score for Acute Kidney Injury},
      journal = {JAMA Network Open},
      address = {2020-08-11},
      number = {TEXTUAL},
      abstract = {&lt;p&gt;Importance: Acute kidney injury (AKI) is associated  with increased morbidity and mortality in hospitalized  patients. Current methods to identify patients at high risk  of AKI are limited, and few prediction models have been  externally validated. &lt;/p&gt;&lt;p&gt;Objective: To internally and  externally validate a machine learning risk score to detect  AKI in hospitalized patients.&lt;/p&gt;&lt;p&gt;Design, Setting, and  Participants: This diagnostic study included 495971 adult  hospital admissions at the University of Chicago (UC) from  2008 to 2016 (n = 48463), at Loyola University Medical  Center (LUMC) from 2007 to 2017 (n = 200613), and at  NorthShore University Health System (NUS) from 2006 to 2016  (n = 246895) with serum creatinine (SCr) measurements.  Patients with an SCr concentration at admission greater  than 3.0 mg/dL, with a prior diagnostic code for chronic  kidney disease stage 4 or higher, or who received kidney  replacement therapy within 48 hours of admission were  excluded. A simplified version of a previously published  gradient boosted machine AKI prediction algorithm was used;  it was validated internally among patients at UC and  externally among patients at NUS and LUMC.&lt;/p&gt;&lt;p&gt;Main  Outcomes and Measures: Prediction of Kidney Disease  Improving Global Outcomes SCr-defined stage 2 AKI within a  48-hour interval was the primary outcome. Discrimination  was assessed by the area under the receiver operating  characteristic curve (AUC).&lt;/p&gt;&lt;p&gt;Results: The study  included 495971 adult admissions (mean [SD] age, 63 [18]  years; 87689 [17.7%] African American; and 266866 [53.8%]  women) across 3 health systems. The development of stage 2  or higher AKI occurred in 15664 of 48463 patients (3.4%) in  the UC cohort, 5711 of 200613 (2.8%) in the LUMC cohort,  and 3499 of 246895 (1.4%) in the NUS cohort. In the UC  cohort, 332 patients (0.7%) required kidney replacement  therapy compared with 672 patients (0.3%) in the LUMC  cohort and 440 patients (0.2%) in the NUS cohort. The AUCs  for predicting at least stage 2 AKI in the next 48 hours  were 0.86 (95% CI, 0.86-0.86) in the UC cohort, 0.85 (95%  CI, 0.84-0.85) in the LUMC cohort, and 0.86 (95% CI,  0.86-0.86) in the NUS cohort. The AUCs for receipt of  kidney replacement therapy within 48 hours were 0.96 (95%  CI, 0.96-0.96) in the UC cohort, 0.95 (95% CI, 0.94-0.95)  in the LUMC cohort, and 0.95 (95% CI, 0.94-0.95) in the NUS  cohort. In time-to-event analysis, a probability cutoff of  at least 0.057 predicted the onset of stage 2 AKI a median  (IQR) of 27 (6.5-93) hours before the eventual doubling in  SCr concentrations in the UC cohort, 34.5 (19-85) hours in  the NUS cohort, and 39 (19-108) hours in the LUMC  cohort.&lt;/p&gt;&lt;p&gt;Conclusions and Relevance: In this study, the  machine learning algorithm demonstrated excellent  discrimination in both internal and external validation,  supporting its generalizability and potential as a clinical  decision support tool to improve AKI detection and  outcomes.&lt;/p&gt;},
      url = {http://knowledge.uchicago.edu/record/11164},
}