Computers in Cardiology Challenge 2004 Top Scores (Final)

Over twenty teams participated in this year’s Challenge, on the topic of predicting if (or when) an episode of atrial fibrillation will self-terminate.

During September’s Computers in Cardiology conference, we presented four awards to eligible participants in this year’s challenge. In each event, an overall best award went to the top-scoring team, and a “best open source” award went to the top-scoring team among those who contributed the source code for their entries. The overall award in event 1 was presented to Dieter Hayn and his colleagues, and the overall award in event 2, as well as the “best open source” awards in both events, were won by Federico Cantini and his colleagues.

Award ceremony, 22 September 2004

The challenge organizers congratulate the top scorers in Challenge 2004.
Left to right: Steve Swiryn, George Moody, Simona Petrutiu, Federico Cantini, Dieter Hayn.

We wish to thank all those who participated in the challenge and in the lively and illuminating discussions during the scientific sessions of Computers in Cardiology. Brief descriptions of the methods used can be viewed by following the links in the tables below to abstracts submitted by the entrants for presentation at Computers in Cardiology 2004.

Event 1 (sustained vs. self-terminating AF)

The maximum possible score in event 1 was 30. The top scorers were:

Score Entrant
29 (97%)* S Petrutiu, AV Sahakian, J Ng, S Swiryn
Northwestern University, Evanston, Illinois, USA
28 (93%) D Hayn, K Edegger, D Scherr, P Lercher, B Rotman, W Klein, G Schreier
ARC Seibersdorf Research GmbH
Medical University of Graz, Austria
27 (90%) F Cantini, F Conforti, M Varanini, F Chiarugi, G Vrouchos
CNR Institute of Clinical Physiology, Pisa, Italy
ICS-FORTH, Heraklion, Greece
ICU-CCU Dept,. Venizeleio-Pananeio Hospital, Heraklion, Greece
[Software]
27 (90%) M Lemay, Z Ihara, JM Vesin, L Kappenberger
EPFL - CHUV, Lausanne, Switzerland
27 (90%) F Castells, C Mora, R Ruiz, JJ Rieta, J Millet, C Sanchez, S Morell
Universidad Politécnica de Valencia
Hospital Clinico Universitario de Valencia
Universidaa de Castilla la Mancha, Cuenca, Spain
27 (90%) F Nilsson, M Stridh, A Bollmann, L Sörnmo
Lund University, Sweden
Good Samaritan Hospital and Harbor-UCLA Medical Center, Los Angeles, California, USA

Event 2 (AF terminating in one minute vs. immediately)

The maximum possible score in event 1 was 20. The top scorers were:

Score Entrant
20 (100%)* S Petrutiu, AV Sahakian, J Ng, S Swiryn
Northwestern University, Evanston, Illinois, USA
18 (90%) F Cantini, F Conforti, M Varanini, F Chiarugi, G Vrouchos
CNR Institute of Clinical Physiology, Pisa, Italy
ICS-FORTH, Heraklion, Greece
ICU-CCU Dept,. Venizeleio-Pananeio Hospital, Heraklion, Greece
[Software]
18 (90%) B Logan, J Healey
Hewlett Packard Laboratories, Cambridge, MA, USA
16 (80%) Q Xi, S Shkurovich
St. Jude Medical, Sylmar, CA, USA
16 (80%) D Hayn, K Edegger, D Scherr, P Lercher, B Rotman, W Klein, G Schreier
ARC Seibersdorf Research GmbH
Medical University of Graz, Austria

* The top-scoring entry in each of the two events came from the research group of Steven Swiryn of Northwestern University, who had contributed the data used in the challenge. Although these entries were thus ineligible for an award, Simona Petrutiu and her coauthors did not have access to any information beyond what was available to all of the participants, and we wish to recognize her extraordinary achievement in achieving a near-perfect score in event 1 and a perfect score in event 2.

Four additional teams of participants also described their approaches to the challenge:


Supported by the National Institute of Biomedical Imaging and Bioengineering (NIBIB) under NIH grant number R01EB030362.

© PhysioNet Challenges. Website content licensed under the Creative Commons Attribution 4.0 International Public License.

Back