MIMIC II: Waveform Database Overview

The MIMIC II Waveform Database is one of the two MIMIC II Databases. The Waveform Database contains many thousands of records of continuously digitized physiologic waveforms and simultaneously recorded time series (trends) of physiologic measurements. Some records also contain alarm annotations and signal quality indexes. The Waveform Database is open to public access free of charge.

Version 3 (August 2011; updated March 2012) of the Waveform Database includes 23,180 sets of recordings and over 3 TB of data in all.

The MIMIC II Waveform Database Matched Subset contains all MIMIC II Waveform Database records that have been associated with MIMIC II Clinical Database records. The record matching process is ongoing, and more records may be added to the matched subset in the future.

Version 2 of the Waveform Database, as described in the MIMIC II User's Guide, remains available to support ongoing studies, but it should not be used for new work.

Waveforms and time series:

For a general description of PhysioNet's signal acronyms and types please see the Signal Classification page. Note that each record contains only a subset of the waveforms (signals) and time series("numerics") listed below.

Signals (125 samples/second)

Numerics/Trends (1 sample/second or 1 sample/minute):

Note that some of these numerics, such as temperature and cardiac output, are recalculated at irregular intervals; in such cases, the samples recorded once per second or per minute are the most recent calculated values (not interpolated intermediate values). Other numerics, such as heart rate and systolic/mean/diastolic blood pressure, are recalculated for each recorded sample; these are typically short-term averages of raw measurements that are made each cardiac cycle.

Related Links:

Questions and Comments

If you would like help understanding, using, or downloading content, please see our Frequently Asked Questions.

If you have any comments, feedback, or particular questions regarding this page, please send them to the webmaster.

Comments and issues can also be raised on PhysioNet's GitHub page.

Updated Wednesday, 23 September 2015 at 14:51 EDT

PhysioNet is supported by the National Institute of General Medical Sciences (NIGMS) and the National Institute of Biomedical Imaging and Bioengineering (NIBIB) under NIH grant number 2R01GM104987-09.