About this Journal Submit a Manuscript Table of Contents
Journal of Healthcare Engineering
Volume 2 (2011), Issue 1, Pages 97-110
http://dx.doi.org/10.1260/2040-2295.2.1.97
Research Article

A Clinical Database-Driven Approach to Decision Support: Predicting Mortality Among Patients with Acute Kidney Injury

Leo Anthony G. Celi,1 Robin J. Tang,2 Mauricio C. Villarroel,3 Guido A. Davidzon,4 William T. Lester,5 and Henry C. Chueh5

1Division of Pulmonary, Critical Care and Sleep Medicine, Beth Israel Deaconess Medical Center, Boston, MA, USA
2College of Physicians and Surgeons, Columbia University, New York, NY, USA
3Institute of Biomedical Engineering, Department of Engineering Science, University of Oxford, Oxford, UK
4Department of Radiology (Nuclear Medicine), Stanford University Medical Center, Stanford, CA, USA
5Laboratory of Computer Science, Massachusetts General Hospital, Boston, MA, USA

Received 1 January 2010; Accepted 1 November 2010

Copyright © 2011 Hindawi Publishing Corporation. This is an open access article distributed under the Creative Commons Attribution License, which permits unrestricted use, distribution, and reproduction in any medium, provided the original work is properly cited.

Abstract

In exploring an approach to decision support based on information extracted from a clinical database, we developed mortality prediction models of intensive care unit (ICU) patients who had acute kidney injury (AKI) and compared them against the Simplified Acute Physiology Score (SAPS). We used MIMIC, a public de-identified database of ICU patients admitted to Beth Israel Deaconess Medical Center, and identified 1400 patients with an ICD9 diagnosis of AKI and who had an ICU stay ≥3 days. Multivariate regression models were built using the SAPS variables from the first 72 hours of ICU admission. All the models developed on the training set performed better than SAPS (AUC = 0.64, Hosmer-Lemeshow p <0.001) on an unseen test set; the best model had an AUC = 0.74 and Hosmer-Lemeshow p = 0.53. These findings suggest that local customized modeling might provide more accurate predictions. This could be the first step towards an envisioned individualized point-of-care probabilistic modeling using one's clinical database.