Session S91.1

Predicting Acute Hypotensive Episodes: The 10th Annual PhysioNet/Computers in Cardiology Challenge

GB Moody*, LH Lehman

Massachusetts Institute of Technology
Cambridge, MA, USA

Among the most critical events that occur in intensive care units (ICUs), acute hypotensive episodes (AHEs) require effective, prompt intervention. Left untreated, such episodes may result in irreversible organ damage and death. Timely and appropriate interventions can reduce these risks.
Of the 2320 ICU patients whose monitored waveforms and accompanying clinical data were included in the MIMIC II Database as of December 2008, arterial blood pressure was recorded in 1237 (53%); among these 1237 patients, 511 (41%) experienced recorded AHEs during their ICU stays. The mortality rate for these 511 patients is more than twice that of the MIMIC II population as a whole. To the extent that one might forecast AHEs in the ICU, there is a possibility of improving care and survival of patients at risk of these events.
The goal of this year's challenge is to stimulate the development of methods for identifying patients at imminent risk of AHEs. For the challenge datasets, we selected previously unposted MIMIC II records of subjects who had AHEs, and others who did not, and provided truncated versions of these records on PhysioNet (http://physionet.org/). Challenge participants were asked to predict which of these records were followed (within an hour) by an AHE.
As of 7 May, 17 teams had submitted entries to one or both of the challenge events, and eight had achieved perfect classification in the first event (to predict AHEs in 10 subjects receiving pressor medication). The best entry so far in second event, involving subjects with a wider variety of histories, classified 36 of the 40 cases correctly. Following the conclusion of the challenge in September, the missing portions of the challenge dataset will be posted on PhysioNet, to support followup studies.

(Abstract Control Number: 265)