Session S42.1

Predicting The Onset Of Paroxysmal Atrial Fibrillation: The Computers In Cardiology Challenge 2001

G.B. Moody, A.L. Goldberger, S. McClennen,
S.P. Swiryn

Harvard-MIT
Cambridge, MA, USA

Following the success of the first Computers in Cardiology Challenge, we are pleased to offer a new challenge from PhysioNet and Computers in Cardiology 2001. The challenge is to develop a fully automated method to predict the onset of paroxysmal atrial fibrillation/flutter (PAF), based on the electrocardiogram (ECG) prior to the event. The development of accurate predictors of the acute onset of PAF is clinically important because of the increasing possibility of electrically stabilizing and preventing the onset of atrial arrhythmias with different atrial pacing techniques. Currently, no reliable validated methods exist to predict the onset of PAF; previous studies have suggested that characteristics of the 12-lead ECG, signal-averaged P-wave morphology, R-R interval dynamics, and atrial ectopy may be useful predictors.
The PAF Prediction Challenge Database may be downloaded from http://www.physionet.org/physiobank/database/afpdb/, and consists of 100 pairs of half-hour ECG recordings. Each pair of recordings is obtained from a single 24-hour ECG. Subjects in group A experienced PAF; for these subjects, one recording ends just before the onset of PAF, and the other recording is distant in time from any PAF (there is no PAF within 45 minutes before or after the excerpt). Subjects in group N do not have PAF; in these, the times of the recordings have been chosen at random. The database is divided into a learning set and a test set of equal size, each containing approximately equal numbers of subjects from groups A and N. The classifications of the recordings in the learning set are provided; those for the test set will be revealed after the conclusion of the challenge.
Entrants have participated in two events. Event 1 asks if individuals at risk of PAF (i.e., those in group A) can be identified within a larger population, based on their ECGs, and event 2 asks if the imminent onset of PAF is predictable in an individual known to be at risk. Early results suggest that these questions can be answered successfully for 70% to 80% of subjects, using a variety of methods.