Database Open Access

MIMIC-III Waveform Database Matched Subset

Benjamin Moody George Moody Mauricio Villarroel Gari Clifford Ikaro Silva

Published: April 7, 2020. Version: 1.0


When using this resource, please cite: (show more options)
Moody, B., Moody, G., Villarroel, M., Clifford, G., & Silva, I. (2020). MIMIC-III Waveform Database Matched Subset (version 1.0). PhysioNet. https://doi.org/10.13026/c2294b.

Additionally, please cite the original publication:

Johnson, A. E. W., Pollard, T. J., Shen, L., Lehman, L. H., Feng, M., Ghassemi, M., Moody, B., Szolovits, P., Celi, L. A., & Mark, R. G. (2016). MIMIC-III, a freely accessible critical care database. Scientific Data, 3, 160035.

Please include the standard citation for PhysioNet: (show more options)
Goldberger, A., Amaral, L., Glass, L., Hausdorff, J., Ivanov, P. C., Mark, R., ... & Stanley, H. E. (2000). PhysioBank, PhysioToolkit, and PhysioNet: Components of a new research resource for complex physiologic signals. Circulation [Online]. 101 (23), pp. e215–e220.

Abstract

The MIMIC-III Waveform Database Matched Subset contains 22,317 waveform records, and 22,247 numerics records, for 10,282 distinct ICU patients. These recordings typically include digitized signals such as ECG, ABP, respiration, and PPG, as well as periodic measurements such as heart rate, oxygen saturation, and systolic, mean, and diastolic blood pressure.

This database is a subset of the MIMIC-III Waveform Database, representing those records for which the patient has been identified, and their corresponding clinical records are available in the MIMIC-III Clinical Database.


Background

The MIMIC-III Waveform Database contains thousands of recordings of multiple physiologic signals (“waveforms”) and time series of vital signs (“numerics”) collected from bedside patient monitors in adult and neonatal intensive care units (ICUs).

An ICU bedside monitor collects a great deal of data, from which it is possible to infer something about a patient’s physiological state. However, in order to understand how these waveforms are influenced by disease state and treatment, and the extent to which phenomena observed in the waveform can serve as indicators of disease, it is necessary to look at the broader context: patient demographics, diagnoses, medications, lab tests, and other information that is recorded by caregivers in the electronic medical record.

Collecting this broad clinical context is the task of the MIMIC-III Clinical Database, which was created in parallel with the Waveform Database and contains information about many of the same patients. The Matched Subset consists of all of the waveform and numerics recordings for which the corresponding clinical record is also available.


Methods

The bedside monitors used for collecting this database were not directly linked to the hospital medical record system. The monitor could be configured to display the patient’s name and medical record number, for ease of identifying patients at the central station, but this was not automatically updated when a patient was admitted or transferred to the ICU. This information was only available when the ICU staff entered it manually into the monitoring system, and since entering this information was not critical to patient care, it was frequently omitted or incomplete. Furthermore, limitations of the data archiving software made it possible to identify the care unit from which a recording originated, but not the precise room or bed number.

As a result, only a subset of the waveform recordings actually contained enough information to reliably identify the patient, and of those, not all overlapped with the time period represented by the MIMIC-III Clinical Database [1]. Using all of the available information, through a process of mostly automated matching with some manual corrections, a total of 22,317 waveform records (34%) and 22,247 numerics records (35%) were found that could be linked to a corresponding patient in the Clinical Database.

For each of those records, a new WFDB header file was created, incorporating the subject ID as well as the surrogate date and time of the recording. Note that the raw signal files (such as 3314767_0004.dat and 3314767n.dat) and segment header files (such as 3314767_0004.hea) are identical to those in the original numbered records.

The project was approved by the Institutional Review Boards of Beth Israel Deaconess Medical Center (Boston, MA) and the Massachusetts Institute of Technology (Cambridge, MA). Requirement for individual patient consent was waived because the project did not impact clinical care and all protected health information was deidentified.


Data Description

All data associated with a particular patient have been placed into a single subdirectory, named according to the patient's MIMIC-III subject_ID. These subdirectories are further divided into ten intermediate-level directories (matched/p00 to matched/p09).

The name of each matched waveform record is of the form matched/pXX/pXXNNNN/pXXNNNN-YYYY-MM-DD-hh-mm, where XXNNNN is the matching MIMIC-III Clinical Database Subject_ID, and YYYY, MM, DD, hh, and mm are the surrogate year, month (01-12), and day (01-31), and the real hour (00-23) and minute (00-59), derived from the starting date and time of day of the record. The surrogate dates match those of the corresponding MIMIC-III Clinical Database records.

In most cases, the waveform record is paired with a numerics record, which has the same name as the associated waveform record, with an n added to the end.

Frequently there are multiple waveform and numerics record pairs associated with a given clinical record; all of them will appear in the same subdirectory in such a case, and their names will indicate their chronologic sequence. For example, MIMIC-III Clinical Database record p000079 has been matched with two waveform and numerics record pairs, named:

  • p000079-2175-09-26-01-25 and p000079-2175-09-26-01-25n
  • p000079-2175-09-26-12-28 and p000079-2175-09-26-12-28n

Each mimic3wdb/matched record is also an undated mimic3wdb record (i.e., it also belongs to the full MIMIC-III Waveform Database). Only the surrogate-dated mimic3wdb/matched header (.hea) files are unique to the Matched Subset; the others, with names of the form 3*.hea and 3*.dat, are copies of the like-named files in the full database.


Usage Notes

The following example illustrates the organization of the database:

  • Intermediate directory p04 contains all records with names that begin with p04 (patients with a subject_id between 40000 and 49999.)
  • All files associated with patient 44083 are contained within the directory p04/p044083. This directory contains two waveform records (p044083-2112-05-04-19-50 and p044083-2112-05-23-12-22) and two corresponding numerics records (p044083-2112-05-04-19-50n and p044083-2112-05-23-12-22n), recorded from two separate ICU stays.
  • The master waveform header file for the first stay (p044083-2112-05-04-19-50.hea) indicates that the record is 20342033 sample intervals (about 45 hours) in length, and begins at 19:50 on May 4, 2112. This date, as with all dates in MIMIC-III, has been anonymized by shifting it by a random number of days into the future. See header(5) in the WFDB Applications Guide for more information about the format of this file.
  • This waveform record consists of 41 segments (3314767_0001 through to 3314767_0041), as indicated by the master header file. The layout header file (3314767_layout.hea) indicates that four ECG signals (II, AVR, V, and MCL) were recorded, along with a respiration signal, photoplethysmogram, and arterial blood pressure. Not all of these signals are available simultaneously.
  • The header file for segment number 4 (3314767_0004.hea) shows us that during this segment, five signals are available: three ECG leads (II, V, and AVR), a respiration signal (RESP), and a PPG signal (PLETH).
  • The numerics header file (p044083-2112-05-04-19-50n.hea) shows us that a variety of measurements were recorded, including heart rate, invasive and non-invasive blood pressure, respiratory rate, ST segment elevation, oxygen saturation, and cardiac rhythm statistics. Just as with waveforms, not all of these measurements are available at all times.

Referring to the MIMIC-III Clinical Database Demo, we can see from the PATIENTS table that this patient was male, and his anonymized date of birth was November 15, 2057 (making him 54 years old at the time of this ICU stay):

subject_id gender dob dod
44083 M 2057-11-15 00:00:00 2114-02-20 00:00:00

The ICUSTAYS table shows us that he was admitted once to the SICU and twice to the CCU:

subject_id hadm_id icustay_id first_careunit intime outtime
44083 125157 265615 SICU 2112-05-04 19:03:39 2112-05-06 17:21:01
44083 131048 282640 CCU 2112-05-23 12:32:06 2112-05-25 14:59:50
44083 198330 286428 CCU 2112-05-29 02:01:33 2112-06-01 16:50:40

The first of these admissions corresponds to the waveform record above, as indicated by the date (2112-05-04). Note that the starting and ending date and time of the waveform record will not always match the precise admission or discharge time.

The hadm_id (125157) and icustay_id (265615) are linked to other tables in MIMIC-III that provide further information about this particular ICU stay, such as vital signs, laboratory tests, medications, and diagnoses.


Release Notes

This database is a subset of version 1.0 of the MIMIC-III Waveform Database. It also represents a superset of the records in the previously-released MIMIC-II Waveform Database Matched Subset. However, it uses a different directory structure (see Data Description above), as well as different subject IDs and surrogate dates. This version corresponds to version 1.4 of the MIMIC-III Clinical Database.


Acknowledgements

We wish to thank Philips Healthcare, as well as the Beth Israel Deaconess Medical Center, for their invaluable support in making this project possible.

Many people have contributed to this project over the past 18 years, and it would be impossible to list them all. In particular, we would like to acknowledge Michael Craig, Tin Kyaw, and Mohammed Saeed, for their efforts in collecting and organizing the original MIMIC-II Waveform Database, upon which this database is based.


Conflicts of Interest

The authors have no conflicts of interests to declare.


References

  1. Johnson, A. E. W., Pollard, T. J., Shen, L., Lehman, L. H., Feng, M., Ghassemi, M., Moody, B., Szolovits, P., Celi, L. A., & Mark, R. G. (2016). MIMIC-III, a freely accessible critical care database. Scientific Data, 3, 160035. https://dx.doi.org/10.1038/sdata.2016.35

Parent Projects
MIMIC-III Waveform Database Matched Subset was derived from: Please cite them when using this project.
Share
Access

Access Policy:
Anyone can access the files, as long as they conform to the terms of the specified license.

License (for files):
Open Data Commons Open Database License v1.0

Corresponding Author
You must be logged in to view the contact information.

Files

Total uncompressed size: 2.4 TB.

Access the files

Visualize waveforms

Folder Navigation: <base>/p08
Name Size Modified
Parent Directory
p080007
p080015
p080018
p080020
p080024
p080030
p080041
p080046
p080048
p080059
p080081
p080097
p080105
p080106
p080108
p080120
p080130
p080132
p080134
p080136
p080142
p080144
p080154
p080156
p080158
p080160
p080162
p080163
p080180
p080185
p080190
p080204
p080209
p080210
p080220
p080237
p080254
p080260
p080286
p080287
p080313
p080317
p080320
p080334
p080335
p080339
p080344
p080350
p080375
p080383
p080410
p080423
p080425
p080429
p080430
p080436
p080442
p080449
p080472
p080490
p080492
p080497
p080534
p080536
p080538
p080547
p080559
p080561
p080580
p080586
p080587
p080602
p080606
p080644
p080656
p080670
p080671
p080675
p080678
p080688
p080726
p080729
p080737
p080744
p080764
p080765
p080767
p080778
p080779
p080789
p080790
p080802
p080823
p080824
p080826
p080843
p080847
p080860
p080880
p080885
p080903
p080942
p080970
p080977
p080985
p080987
p081002
p081007
p081011
p081025
p081037
p081041
p081050
p081057
p081058
p081063
p081067
p081074
p081083
p081099
p081103
p081107
p081109
p081150
p081157
p081166
p081167
p081193
p081194
p081202
p081203
p081212
p081215
p081216
p081229
p081233
p081237
p081242
p081247
p081258
p081295
p081303
p081334
p081342
p081349
p081350
p081354
p081363
p081371
p081378
p081387
p081405
p081408
p081410
p081425
p081432
p081436
p081439
p081443
p081449
p081464
p081475
p081478
p081480
p081491
p081507
p081515
p081519
p081529
p081535
p081536
p081543
p081558
p081560
p081583
p081593
p081630
p081633
p081636
p081660
p081661
p081662
p081675
p081694
p081700
p081715
p081723
p081729
p081745
p081750
p081754
p081758
p081763
p081766
p081786
p081787
p081797
p081807
p081810
p081815
p081817
p081818
p081827
p081846
p081847
p081848
p081849
p081850
p081866
p081871
p081875
p081876
p081885
p081886
p081888
p081893
p081918
p081923
p081926
p081939
p081946
p081978
p081980
p081990
p081992
p081998
p082000
p082001
p082003
p082010
p082011
p082015
p082021
p082035
p082038
p082041
p082055
p082065
p082068
p082079
p082090
p082091
p082104
p082111
p082115
p082127
p082128
p082130
p082132
p082148
p082159
p082160
p082178
p082179
p082184
p082187
p082195
p082205
p082209
p082228
p082229
p082235
p082238
p082244
p082245
p082257
p082258
p082290
p082291
p082296
p082299
p082324
p082338
p082360
p082375
p082381
p082393
p082405
p082418
p082432
p082433
p082434
p082445
p082454
p082462
p082466
p082474
p082481
p082482
p082494
p082496
p082512
p082518
p082520
p082534
p082541
p082545
p082563
p082565
p082569
p082574
p082575
p082579
p082585
p082599
p082609
p082629
p082641
p082681
p082685
p082694
p082713
p082715
p082736
p082746
p082759
p082762
p082765
p082785
p082799
p082816
p082831
p082843
p082847
p082898
p082901
p082915
p082921
p082928
p082938
p082939
p082943
p082947
p082950
p082960
p082973
p082982
p082986
p083013
p083014
p083020
p083058
p083060
p083065
p083088
p083091
p083120
p083122
p083124
p083128
p083129
p083143
p083151
p083180
p083182
p083191
p083197
p083203
p083206
p083210
p083224
p083225
p083228
p083261
p083263
p083272
p083278
p083288
p083300
p083310
p083314
p083324
p083338
p083341
p083349
p083351
p083375
p083382
p083383
p083393
p083401
p083406
p083418
p083430
p083441
p083464
p083498
p083499
p083514
p083528
p083532
p083537
p083542
p083543
p083555
p083561
p083584
p083593
p083598
p083599
p083607
p083608
p083617
p083629
p083633
p083653
p083678
p083691
p083692
p083700
p083702
p083728
p083734
p083749
p083751
p083752
p083773
p083776
p083782
p083794
p083799
p083817
p083818
p083831
p083838
p083856
p083857
p083860
p083865
p083873
p083887
p083892
p083899
p083908
p083913
p083922
p083932
p083947
p083962
p083968
p083976
p083981
p084020
p084023
p084042
p084046
p084052
p084057
p084061
p084063
p084071
p084078
p084084
p084089
p084095
p084107
p084116
p084120
p084130
p084137
p084142
p084150
p084179
p084186
p084187
p084198
p084206
p084208
p084209
p084223
p084249
p084251
p084286
p084292
p084297
p084307
p084310
p084318
p084329
p084332
p084347
p084350
p084362
p084378
p084382
p084392
p084402
p084449
p084454
p084458
p084461
p084463
p084468
p084469
p084473
p084478
p084479
p084495
p084499
p084505
p084531
p084534
p084544
p084595
p084601
p084603
p084629
p084630
p084632
p084633
p084649
p084669
p084692
p084708
p084711
p084717
p084721
p084726
p084734
p084748
p084749
p084750
p084766
p084775
p084776
p084802
p084818
p084826
p084837
p084842
p084845
p084854
p084874
p084875
p084884
p084886
p084891
p084909
p084912
p084914
p084934
p084938
p084941
p084952
p084958
p084970
p084972
p084998
p085010
p085011
p085025
p085027
p085033
p085036
p085039
p085042
p085071
p085079
p085095
p085124
p085125
p085134
p085138
p085143
p085160
p085163
p085171
p085181
p085184
p085196
p085202
p085205
p085235
p085248
p085255
p085258
p085286
p085291
p085293
p085327
p085350
p085352
p085361
p085371
p085375
p085389
p085393
p085397
p085401
p085402
p085407
p085417
p085421
p085424
p085441
p085456
p085457
p085460
p085489
p085490
p085493
p085495
p085506
p085508
p085519
p085533
p085535
p085541
p085551
p085552
p085559
p085562
p085566
p085572
p085575
p085586
p085607
p085615
p085620
p085639
p085644
p085649
p085655
p085658
p085673
p085685
p085698
p085700
p085704
p085710
p085714
p085725
p085730
p085753
p085755
p085757
p085767
p085802
p085828
p085840
p085844
p085852
p085866
p085883
p085885
p085889
p085892
p085895
p085899
p085901
p085929
p085938
p085953
p085958
p085962
p085974
p085976
p085979
p085980
p085987
p085994
p085999
p086018
p086026
p086041
p086068
p086078
p086086
p086090
p086108
p086137
p086143
p086144
p086148
p086158
p086165
p086176
p086191
p086193
p086206
p086209
p086210
p086220
p086245
p086249
p086254
p086276
p086279
p086294
p086300
p086318
p086320
p086348
p086355
p086359
p086377
p086379
p086381
p086382
p086383
p086392
p086394
p086402
p086411
p086428
p086436
p086487
p086502
p086511
p086516
p086531
p086546
p086555
p086556
p086561
p086570
p086585
p086589
p086590
p086628
p086629
p086645
p086648
p086662
p086663
p086675
p086678
p086684
p086692
p086711
p086712
p086719
p086722
p086731
p086757
p086765
p086773
p086782
p086805
p086824
p086831
p086845
p086846
p086864
p086880
p086899
p086907
p086921
p086934
p086942
p086948
p086961
p086965
p086968
p086976
p086980
p086984
p087018
p087048
p087049
p087056
p087074
p087078
p087082
p087119
p087125
p087133
p087134
p087158
p087161
p087172
p087187
p087196
p087203
p087216
p087225
p087228
p087239
p087247
p087251
p087253
p087257
p087259
p087266
p087272
p087275
p087283
p087287
p087308
p087310
p087325
p087336
p087344
p087352
p087376
p087394
p087428
p087450
p087461
p087470
p087474
p087481
p087497
p087498
p087500
p087526
p087552
p087566
p087577
p087586
p087605
p087608
p087616
p087621
p087630
p087640
p087659
p087674
p087675
p087683
p087687
p087692
p087716
p087754
p087758
p087769
p087770
p087782
p087789
p087794
p087800
p087801
p087803
p087817
p087825
p087835
p087846
p087847
p087858
p087864
p087876
p087879
p087891
p087905
p087913
p087934
p087936
p087948
p087949
p087953
p087957
p087962
p087965
p087969
p087975
p087976
p087978
p087980
p087986
p087989
p087990
p087992
p088003
p088013
p088018
p088025
p088065
p088089
p088099
p088106
p088111
p088112
p088117
p088146
p088152
p088164
p088166
p088174
p088175
p088180
p088186
p088191
p088202
p088206
p088214
p088220
p088224
p088236
p088258
p088265
p088266
p088267
p088269
p088276
p088280
p088286
p088296
p088308
p088309
p088312
p088325
p088340
p088343
p088356
p088401
p088406
p088407
p088411
p088432
p088445
p088466
p088471
p088472
p088481
p088483
p088493
p088503
p088514
p088521
p088523
p088531
p088532
p088540
p088552
p088560
p088571
p088591
p088608
p088632
p088635
p088638
p088647
p088657
p088660
p088665
p088685
p088691
p088695
p088696
p088702
p088726
p088731
p088734
p088738
p088740
p088747
p088764
p088774
p088778
p088790
p088809
p088817
p088819
p088851
p088856
p088883
p088907
p088911
p088921
p088928
p088937
p088941
p088951
p088952
p088953
p088976
p088982
p088986
p088991
p088994
p089002
p089012
p089026
p089030
p089046
p089091
p089092
p089095
p089107
p089132
p089137
p089148
p089158
p089179
p089180
p089192
p089193
p089195
p089197
p089212
p089223
p089225
p089232
p089265
p089277
p089287
p089291
p089292
p089297
p089303
p089316
p089324
p089329
p089334
p089336
p089347
p089356
p089368
p089394
p089402
p089404
p089405
p089415
p089416
p089419
p089437
p089445
p089447
p089459
p089460
p089481
p089488
p089502
p089528
p089544
p089546
p089556
p089560
p089563
p089565
p089579
p089585
p089600
p089606
p089643
p089688
p089689
p089697
p089698
p089714
p089717
p089721
p089734
p089742
p089752
p089755
p089760
p089768
p089769
p089772
p089782
p089792
p089797
p089802
p089806
p089811
p089816
p089818
p089840
p089849
p089854
p089870
p089873
p089894
p089895
p089897
p089900
p089901
p089906
p089909
p089914
p089934
p089953
p089956
p089964
p089965
p089973
p089978
p089984
p089992
p089996