2016 News

The neuroQWERTY MIT-CSXPD database contains keystroke logs collected from 85 subjects with and without parkinsons disease (PD). This dataset has been collected and analyzed in order to indicate that the routine interaction with computer keyboards can be used to detect motor signs in the early stages of PD.

The Cerebral Haemodynamic Autoregulatory Information System (CHARIS) GUI toolkit contains a Matlab GUI used to display and process intracranial pressure features and relationships with other physiological signals.

The journal Physiological Measurement is hosting a special issue on “Recent advances in heart sound analysis”. We encourage all Challenge2016 entrants (and those who missed the opportunity to compete or attend CinC 2016) to submit extended analyses and articles to that issue, taking into account the publications and discussions at CinC 2016.

Papers and corresponding source code from the 2016 Challenge are now online.

The ECG effects of Dofetilide, Moxifloxacin, Dofetilide+Mexiletine, Dofetilide+Lidocaine and Moxifloxacin+Diltiazem in Healthy Subjects database contains data from a randomized, double-blind, 5-period crossover clinical trial in healthy male and female subjects, 18 to 35 years of age, to compare the electrophysiological response of hERG potassium channel blocking drugs with and without the addition of late sodium or calcium channel blocking drugs.

The MAMEM steady state visually evoked potentials database has been updated with a third experimental dataset.

The ECG Effects of Ranolazine, Dofetilide, Verapamil, and Quinidine in Healthy Subjects database contains multi-channel ECG recordings of subjects partaking in a randomized, double-blind, 5-period crossover clinical trial aimed at comparing the effects of four known QT prolonging drugs versus placebo on electrophysiological and other clinical parameters.

The Long Term Movement Monitoring database contains 3-day 3D accelerometer recordings of 71 elder community residents, used to study gait, stability, and fall risk.

The Indwelling Arterial Catheter Clinical dataset contains clinical data for 1776 patients from the MIMIC-II clinical database. It was the basis for the article: Hsu DJ, et al. The association between indwelling arterial catheters and mortality in hemodynamically stable patients with respiratory failure: A propensity score analysis. Chest, 148(6):1470–1476, Aug. 2015. This dataset was also used by Raffa et al. in Chapter 5 "Data Analysis" of the forthcoming book: Secondary Analysis of Electronic Health Records, published by Springer in 2016.

The MAMEM steady state visually evoked potentials database containing 256 channel EEG recordings of 11 subjects under the stimulation of flickering lights has been expanded with a second experimental dataset.

The Human Balance Evaluation database contains force platform recordings from 193 subjects undergoing stabilography tests.

The fetal ECG synthetic database is a large database of simulated adult and non-invasive fetal ECG (NI-FECG) signals, which provides a robust resource that enables reproducible research in the field. The data is generated using the FECGSYN simulator.

The Association for the Advancement of Medical Instrumentation (AAMI) has awarded the Foundation’s highest honor, the Laufman-Greatbatch Award for 2016, to PhysioNet’s founders Ary L. Goldberger, Roger G. Mark, and George B. Moody for the creation and development of the PhysioNet Resource. The AAMI website states:

Named after two pioneers in the field—Harold Laufman, MD and Wilson Greatbatch, PhD—this highly regarded award honors an individual or group that has made a unique and significant contribution to the advancement of healthcare technology and systems, service, patient care, or patient safety.

Ary L. Goldberger, MD; Roger G. Mark, MD, PhD; and George Moody—founders of PhysioNet—were selected to receive this award for their work over the last 20 years to collect and provide access to “big data” through the creation of PhysioNet. PhysioNet is a free collection of recorded physiologic signals and related open-source software intended to stimulate current research and new investigations.

The Squid Giant Axon Membrane Potential database contains single-unit neuronal recordings of squid giant axons in response to stimulus currents. The membrane potential and stimulus current are given for a total of 170 trials across 8 different axons.

The MAMEM steady state visually evoked potentials database contains 256 channel EEG recordings of 11 subjects under the stimulation of flickering lights.

The Multiscale Poincare Plots package contains MATLAB scripts used to visualize time series by plotting Poincare plots of the original signal course grained at multiple time scales.

The Logistic Regression HSMM based Heart Sound Segmentation package contains MATLAB code used to segment phonocardiogram (PCG) recordings, and detect the four states of the heart cycle. This state of the art segmentation code by Springer is used in the sample entry of the 2016 PhysioNet/CinC Challenge.

Example code for Matlab and Octave has been released.

The newly contributed software for Modeling of Heart Rate Variability Including the Effect of Sleep Stages implements a model for simulating healthy nighttime heart rate variability based on the properties of sleep observed in real data. Also included are 20 RR time series generated by the model. The model was first proposed in “Modeling heart rate variability including the effect of sleep stages,” by Soliński et al in CHAOS 26, 023101 (2016).

We are pleased to announce the 2016 PhysioNet/Computing in Cardiology Challenge: Classification of Normal/Abnormal Heart Sound Recordings. For this year's Challenge, we have released a collection of 3,125 phonocardiograms from a variety of clinical and non-clinical sources. We invite participants to develop algorithms to determine, based on a short heart sound recording, whether the patient should be referred on for an expert diagnosis.

The Transfer Entropy With Partitioning package is a repository of MATLAB functions that can estimate transfer entropy (information flow) from one time series to another using a non-parametric partitioning algorithm. Also included is an example data set that the implemented algorithms can be applied to.

The MMG Database contains uterine magnetomyographic (MMG) signals recorded using the 151 channel SARA (SQUID Array for Reproductive Assessment) system installed at UAMS, Little Rock, USA.

If you have any questions or comments regarding this challenge, please post it directly in our Community Discussion Forum. This will increase transparency (benefiting all the competitors) and ensure that all the challenge organizers see your question.

The Physiologic Response to Changes in Posture Database contains a collection of physiological recordings (ECG and ABP) from tenhealthy subjects in response to a slow tilt, a fast tilt, and a standing-up maneuver.

If you have any questions or comments regarding this challenge, please post it directly in our Community Discussion Forum. This will increase transparency (benefiting all the competitors) and ensure that all the challenge organizers see your question.

The official scores and source code for the top open-source entries have been posted. The winners of Event 1 were Filip Plesinger, Petr Klimes, Josef Halamek, and Pavel Jurak, with a score of 81.39. In Event 2, the winners were Sibylle Fallet, Sasan Yazdani, and Jean-Marc Vesin, with a score of 85.04.