Preterm Infant Cardio-Respiratory Signals Database

First Edition, January 2017

When referencing this material, please cite:

A. H. Gee, R. Barbieri, D. Paydarfar and P. Indic, Predicting Bradycardia in Preterm Infants Using Point Process Analysis of Heart Rate, in IEEE Transactions on Biomedical Engineering, vol. 64, no. 9, pp. 2300-2308, Sept. 2017. doi:10.1109/TBME.2016.2632746. [bib]
@article{PIADB,
  author  = {A. H. Gee, R. Barbieri, D. Paydarfar and P. Indic},
  title   = {Predicting Bradycardia in Preterm Infants Using Point Process Analysis of Heart Rate},
  journal = {IEEE Transactions on Biomedical Engineering},
  volume  = {64},
  number  = {9},
  pages   = {2300-2308},
  year    = {2017},
  doi     = {10.1109/TBME.2016.2632746},
}

Please also include the standard citation for PhysioNet:

Goldberger AL, Amaral LAN, Glass L, Hausdorff JM, Ivanov PCh, Mark RG, Mietus JE, Moody GB, Peng C-K, Stanley HE. PhysioBank, PhysioToolkit, and PhysioNet: Components of a New Research Resource for Complex Physiologic Signals. Circulation 101(23):e215-e220 [Circulation Electronic Pages; http://circ.ahajournals.org/content/101/23/e215]; 2000 (June 13). [bib]
@article{PhysioNet,
  author    = {Goldberger, Ary L. and Amaral, Luis A. N.
               and Glass, Leon and Hausdorff, Jeffrey M.
               and Ivanov, Plamen Ch. and Mark, Roger G.
               and Mietus, Joseph E. and Moody, George B.
               and Peng, Chung-Kang and Stanley, H. Eugene},
  title     = {{PhysioBank}, {PhysioToolkit}, and {PhysioNet}:
               Components of a New Research Resource for Complex
               Physiologic Signals},
  journal   = {Circulation},
  publisher = {American Heart Association, Inc.},
  volume    = {101},
  number    = {23},
  year      = {2000},
  month     = {June},
  pages     = {e215--e220},
  doi       = {10.1161/01.CIR.101.23.e215},
  issn      = {0009-7322},
  url       = {http://circ.ahajournals.org/content/101/23/e215}
}

The Preterm Infant Cardio-respiratory Signals (PICS) database contains simultaneous ECG and respiration recordings of ten preterm infants collected from the Neonatal Intensive Care Unit (NICU) of the University of Massachusetts Memorial Healthcare. Statistical features based on linear estimates of heart rate are used to predict episodes of bradycardia.

Data Collection

Ten preterm infants were studied, with post-conceptional age of 29 3/7 to 34 2/7 weeks (mean: 31 1/7 weeks) and study weights of 843 to 2100 grams (mean: 1468 grams). The infants were spontaneously breathing room air and did not have any congenital or perinatal infection of the central nervous system, intraventricular hemorrhage of grade II or higher, and hypoxic-ischemic encephalopathy. A single channel of a 3-lead electrocardiogram (ECG) signal was recorded at 500 Hz (when available) from bedside patient monitors (Intellivue MP70, Philips Medical Systems) for ~20-70 hours per infant. In absence of an ECG channel, a compound ECG signal was recorded (250Hz). The compound ECG signal is an integrated signal of the three ECG lead channels. The choice of ECG availability was subject to nursing preference, and the researchers did not interfere with signals displayed on the Philips monitor.

Respiratory signals, using external inductance bands placed around the chest wall and abdomen, were also recorded (50 Hz) and synchronized using VueLoggerTM , a data acquisition system developed at the Wyss Institute, Harvard University. See the referenced paper for more details.

Data Files

The single channel ECG and Respiration records are provided in standard WFDB format. Recording start times are synchronized within each infant. ECGs are recorded at 500Hz except for infants 1 and 5, which are recorded as a compound ECG signal at 250Hz. The ECG leads are specified in the header files. R-peaks are extracted from the ECGs using a modified Pan-Tompkins algorithm. The annotations are then visually inspected by researchers to remove artifacts due to movement, disconnection, and any erroneous peak detections.

Respiration signals are recorded at 50Hz from abdomen inductance bands, except for infant 1, which is recorded at 500Hz. The respiration signal for infant 1 was recorded using the respiration signal from the Philips monitor (i.e. abdomen inductance band information was not available at time of study). Respiration peaks are algorithmically extracted; however, these annotations have not been manually vetted yet.

Bradycardia onset annotations are also provided. We define bradycardia as events where the heart rate slows to less than 100 bpm (or equivalently R-R > 0.6 s) and for at least two beats (> 1.2 s) in duration. We also consider bradycardia clustering (i.e. successive bradycardias after a leading bradycardia). For our study, we aggregate any bradycardia within a 3-minute window of a leading bradycardia into one bradycardia to avoid statistical distortions during the prediction phase.

The ECG and respiration records are named in the form: infantN_ecg and infantN_resp, where N is the infant number.

Annotation files as described in the previous section are also provided, with record names matching the records they are associated with. The annotation file extensions are qrsc for ECG R locations, resp for respiration peaks, and atr for bradycardia onset times.

Icon  Name                    Last modified      Size  Description
[PARENTDIR] Parent Directory - [   ] infant10_ecg.qrsc 2017-01-20 16:39 804K unaudited annotations [   ] infant10_ecg.dat 2017-01-20 16:39 162M digitized signal(s) [   ] infant10_ecg.hea 2017-01-20 16:39 81 header file [   ] infant10_resp.dat 2017-01-20 16:39 16M digitized signal(s) [   ] infant10_resp.hea 2017-01-20 16:39 91 header file [   ] infant10_resp.resp 2017-01-20 16:39 266K [   ] infant1_ecg.qrsc 2017-01-20 16:39 819K unaudited annotations [   ] infant1_ecg.dat 2017-01-20 16:39 78M digitized signal(s) [   ] infant1_resp.dat 2017-01-20 16:39 157M digitized signal(s) [   ] infant1_resp.hea 2017-01-20 16:39 94 header file [   ] infant1_resp.resp 2017-01-20 16:39 506K [   ] infant2_ecg.qrsc 2017-01-20 16:39 652K unaudited annotations [   ] infant2_ecg.dat 2017-01-20 16:39 151M digitized signal(s) [   ] infant2_ecg.hea 2017-01-20 16:39 88 header file [   ] infant2_resp.dat 2017-01-20 16:39 15M digitized signal(s) [   ] infant2_resp.hea 2017-01-20 16:39 91 header file [   ] infant2_resp.resp 2017-01-20 16:39 255K [   ] infant3_ecg.qrsc 2017-01-20 16:39 655K unaudited annotations [   ] infant3_ecg.dat 2017-01-20 16:39 150M digitized signal(s) [   ] infant3_ecg.hea 2017-01-20 16:39 87 header file [   ] infant3_resp.dat 2017-01-20 16:39 15M digitized signal(s) [   ] infant3_resp.hea 2017-01-20 16:39 92 header file [   ] infant3_resp.resp 2017-01-20 16:39 243K [   ] infant4_ecg.qrsc 2017-01-20 16:39 909K unaudited annotations [   ] infant4_ecg.dat 2017-01-20 16:40 161M digitized signal(s) [   ] infant4_ecg.hea 2017-01-20 16:40 85 header file [   ] infant4_resp.dat 2017-01-20 16:40 16M digitized signal(s) [   ] infant4_resp.hea 2017-01-20 16:40 89 header file [   ] infant4_resp.resp 2017-01-20 16:40 402K [   ] infant5_ecg.qrsc 2017-01-20 16:40 803K unaudited annotations [   ] infant5_ecg.dat 2017-01-20 16:40 84M digitized signal(s) [   ] infant5_resp.dat 2017-01-20 16:40 17M digitized signal(s) [   ] infant5_resp.hea 2017-01-20 16:40 89 header file [   ] infant5_resp.resp 2017-01-20 16:40 160K [   ] infant6_ecg.qrsc 2017-01-20 16:40 772K unaudited annotations [   ] infant6_ecg.dat 2017-01-20 16:40 167M digitized signal(s) [   ] infant6_ecg.hea 2017-01-20 16:40 80 header file [   ] infant6_resp.dat 2017-01-20 16:40 17M digitized signal(s) [   ] infant6_resp.hea 2017-01-20 16:40 87 header file [   ] infant6_resp.resp 2017-01-20 16:40 404K [   ] infant7_ecg.qrsc 2017-01-20 16:40 381K unaudited annotations [   ] infant7_ecg.dat 2017-01-20 16:40 70M digitized signal(s) [   ] infant7_ecg.hea 2017-01-20 16:40 87 header file [   ] infant7_resp.dat 2017-01-20 16:40 7.0M digitized signal(s) [   ] infant7_resp.hea 2017-01-20 16:40 90 header file [   ] infant7_resp.resp 2017-01-20 16:40 130K [   ] infant8_ecg.qrsc 2017-01-20 16:40 400K unaudited annotations [   ] infant8_ecg.dat 2017-01-20 16:40 84M digitized signal(s) [   ] infant8_ecg.hea 2017-01-20 16:40 86 header file [   ] infant8_resp.dat 2017-01-20 16:40 8.4M digitized signal(s) [   ] infant8_resp.hea 2017-01-20 16:40 91 header file [   ] infant8_resp.resp 2017-01-20 16:40 174K [   ] infant9_ecg.qrsc 2017-01-20 16:40 1.2M unaudited annotations [   ] infant9_ecg.dat 2017-01-20 16:40 241M digitized signal(s) [   ] infant9_ecg.hea 2017-01-20 16:40 81 header file [   ] infant9_resp.dat 2017-01-20 16:40 24M digitized signal(s) [   ] infant9_resp.hea 2017-01-20 16:40 90 header file [   ] infant9_resp.resp 2017-01-20 16:40 464K [   ] RECORDS 2017-01-20 16:43 252 list of record names [   ] infant1_ecg.hea 2017-01-30 10:24 82 header file [   ] infant5_ecg.hea 2017-01-30 10:24 81 header file [   ] MD5SUMS 2017-02-08 17:30 3.1K [   ] SHA1SUMS 2017-02-08 17:31 3.6K [   ] SHA256SUMS 2017-02-08 17:31 5.1K [   ] ANNOTATORS 2017-09-27 18:10 118 list of annotators [   ] infant10_ecg.atr 2017-09-27 18:22 416 reference annotations [   ] infant1_ecg.atr 2017-09-27 18:22 712 reference annotations [   ] infant2_ecg.atr 2017-09-27 18:22 672 reference annotations [   ] infant3_ecg.atr 2017-09-27 18:22 736 reference annotations [   ] infant4_ecg.atr 2017-09-27 18:22 624 reference annotations [   ] infant5_ecg.atr 2017-09-27 18:22 672 reference annotations [   ] infant6_ecg.atr 2017-09-27 18:22 544 reference annotations [   ] infant7_ecg.atr 2017-09-27 18:22 368 reference annotations [   ] infant8_ecg.atr 2017-09-27 18:22 320 reference annotations [   ] infant9_ecg.atr 2017-09-27 18:22 872 reference annotations

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 Friday, 28 October 2016 at 16:58 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.