RT Journal Article
SR Electronic
T1 Prediction of Acute Kidney Injury with a Machine Learning Algorithm using Electronic Health Record Data
JF bioRxiv
FD Cold Spring Harbor Laboratory
SP 223354
DO 10.1101/223354
A1 Hamid Mohamadlou
A1 Anna Lynn-Palevsky
A1 Christopher Barton
A1 Uli Chettipally
A1 Lisa Shieh
A1 Jacob Calvert
A1 Ritankar Das
YR 2017
UL http://biorxiv.org/content/early/2017/11/22/223354.abstract
AB Background A major problem in treating acute kidney injury (AKI) is that clinical criteria for recognition are markers of established kidney damage or impaired function; treatment before such damage manifests is desirable. Clinicians could intervene during what may be a crucial stage for preventing permanent kidney injury if patients with incipient AKI and those at high risk of developing AKI could be identified.Methods We used a machine learning technique, boosted ensembles of decision trees, to train an AKI prediction tool on retrospective data from inpatients at Stanford Medical Center and intensive care unit patients at Beth Israel Deaconess Medical Center. We tested the algorithm’s ability to detect AKI at onset, and to predict AKI 12, 24, 48, and 72 hours before onset, and compared its 3-fold cross-validation performance to the SOFA score for AKI identification in terms of Area Under the Receiver Operating Characteristic (AUROC).Results The prediction algorithm achieves AUROC of 0.872 (95% CI 0.867, 0.878) for AKI onset detection, superior to the SOFA score AUROC of 0.815 (P < 0.01). At 72 hours before onset, the algorithm achieves AUROC of 0.728 (95% CI 0.719, 0.737), compared to the SOFA score AUROC of 0.720 (P < 0.01).Conclusions The results of these experiments suggest that a machine-learning-based AKI prediction tool may offer important prognostic capabilities for determining which patients are likely to suffer AKI, potentially allowing clinicians to intervene before kidney damage manifests.