The PhysioNet Challenges are an activity of PhysioNet (the moniker of the Research Resource for Complex Physiologic Signals).
PhysioNet was established in 1999 under the auspices of the National Institutes of Health (NIH), co-founded by Principal Investigators Ary L. Goldberger at Beth Israel Deaconess Medical Center’s/Harvard Medical School’s Margret & H. A. Rey Institute for Nonlinear Dynamics in Medicine (ReyLab) and Roger G. Mark at MIT’s Laboratory for Computational Physiology (LCP). The PhysioNet resource’s original and ongoing missions focus on conducting and catalyzing biomedical research and education, in part by offering free access to large collections of physiological and clinical data and related open-source software.
In cooperation with this annual conference, PhysioNet also hosts an annual series of biomedical ‘Challenges’, focusing research on unsolved problems in clinical and basic science. These Challenges have been supported by the NIH, Google, MathWorks and the Gordon and Betty Moore Foundation. For the first 15 years, these Challenges were led by George Moody at the LCP. Since 2015, the Challenges have been led by Gari Clifford at Emory University and the Georgia Institute of Technology.
Currently supported by the National Institute of Biomedical Imaging and Bioengineering (NIBIB) (R01EB030362), PhysioNet has three specific aims, managed by its three interactive research groups:
The Laboratory for Computational Physiology (LCP) at MIT runs the PhysioNet.org website to distribute data and resources such as open-source software. It maintains the software, including the WFDB libraries for accessing waveform data.
The ReyLab at Beth Israel Deaconess/Harvard Medical school, which develops computational software for time series analysis and other open-source resources and research posted though PhysioNet.org.
The Department of Biomedical Informatics (BMI) at Emory, which runs the Challenges and physionetchallenges.org. It supports the code and data provided by the organizers for the current Challenge but not for past Challenges or other projects.
For support of all libraries and code provided on PhysioNet.org, please contact the LCP, which can be reached directly for support at https://physionet.org/about/#contact.
For support about Computing and Cardiology (CinC), please email contact[at]cinc.org. Although we partner with CinC, we cannot provide exceptions to the conference rules, discounts on fees, visa support letters for attendance, or other specific information about the conference not directly related to the Challenge.
For support on the current Challenge, please contact help[at]physionetchallenges.org. Previous Challenges are not generally supported, but requests will be considered, particularly if resources are available. The submission of open-source code to be re-run on past Challenge data will be considered if the requestor can provide resources to assist in this. Unfortunately, the funding from the NIH and our generous sponsors cannot always match the large number of requests that we receive. Test data from previous Challenges will not be released under any circumstance to prevent overfitting on the test data.
If you are interested in contributing to, or posing a Challenge, please feel free to contact us with details of the databases you can provide, the nature of the problem you wish to solve, and some demo code which makes a basic attempt to solve the problem. We strongly recommend having at least three independent databases, two to become public, and one to remain private/hidden. For more information on the general aims and framework of the Challenge, and the criteria for a successful event, please see here.
Supported by the National Institute of Biomedical Imaging and Bioengineering (NIBIB) under NIH grant R01EB030362.