A hypotensive episode predictor for intensive care based on heart rate and blood pressure time series
In the intensive care unit (ICU), prompt therapeutic intervention to hypotensive episodes (HEs) is a critical task. Advance alerts that can prospectively identify patients at risk of developing an HE in the next few hours would be of considerable clinical value. In this study, we developed an automa...
| Κύριοι συγγραφείς: | , |
|---|---|
| Άλλοι συγγραφείς: | |
| Μορφή: | Άρθρο |
| Γλώσσα: | en_US |
| Έκδοση: |
IEEE Computer Society
2011
|
| Διαθέσιμο Online: | http://hdl.handle.net/1721.1/65394 https://orcid.org/0000-0001-8593-9321 https://orcid.org/0000-0002-6318-2978 |
| _version_ | 1826200195321298944 |
|---|---|
| author | Lee, J. Mark, Roger Greenwood |
| author2 | Harvard University--MIT Division of Health Sciences and Technology |
| author_facet | Harvard University--MIT Division of Health Sciences and Technology Lee, J. Mark, Roger Greenwood |
| author_sort | Lee, J. |
| collection | MIT |
| description | In the intensive care unit (ICU), prompt therapeutic intervention to hypotensive episodes (HEs) is a critical task. Advance alerts that can prospectively identify patients at risk of developing an HE in the next few hours would be of considerable clinical value. In this study, we developed an automated, artificial neural network HE predictor based on heart rate and blood pressure time series from the MIMIC II database. The gap between prediction time and the onset of the 30-minute target window was varied from 1 to 4 hours. A 30-minute observation window preceding the prediction time provided input information to the predictor. While individual gap sizes were evaluated independently, weighted posterior probabilities based on different gap sizes were also investigated. The results showed that prediction performance degraded as gap size increased and the weighting scheme induced negligible performance improvement. Despite low positive predictive values, the best mean area under ROC curve was 0.934. |
| first_indexed | 2024-09-23T11:32:37Z |
| format | Article |
| id | mit-1721.1/65394 |
| institution | Massachusetts Institute of Technology |
| language | en_US |
| last_indexed | 2024-09-23T11:32:37Z |
| publishDate | 2011 |
| publisher | IEEE Computer Society |
| record_format | dspace |
| spelling | mit-1721.1/653942022-09-27T20:14:11Z A hypotensive episode predictor for intensive care based on heart rate and blood pressure time series Lee, J. Mark, Roger Greenwood Harvard University--MIT Division of Health Sciences and Technology Mark, Roger Greenwood Mark, Roger Greenwood Lee, J. In the intensive care unit (ICU), prompt therapeutic intervention to hypotensive episodes (HEs) is a critical task. Advance alerts that can prospectively identify patients at risk of developing an HE in the next few hours would be of considerable clinical value. In this study, we developed an automated, artificial neural network HE predictor based on heart rate and blood pressure time series from the MIMIC II database. The gap between prediction time and the onset of the 30-minute target window was varied from 1 to 4 hours. A 30-minute observation window preceding the prediction time provided input information to the predictor. While individual gap sizes were evaluated independently, weighted posterior probabilities based on different gap sizes were also investigated. The results showed that prediction performance degraded as gap size increased and the weighting scheme induced negligible performance improvement. Despite low positive predictive values, the best mean area under ROC curve was 0.934. National Institute of Biomedical Imaging and Bioengineering (U.S.) (grant number R01-EB001659) 2011-08-26T14:40:43Z 2011-08-26T14:40:43Z 2011-03 2010-09 Article http://purl.org/eprint/type/ConferencePaper 0276-6574 INSPEC Accession Number: 11883625 http://hdl.handle.net/1721.1/65394 Lee, J., and R.G. Mark. “A Hypotensive Episode Predictor for Intensive Care Based on Heart Rate and Blood Pressure Time Series.” Computing in Cardiology, 2010;37:81−84. © 2010 IEEE. https://orcid.org/0000-0001-8593-9321 https://orcid.org/0000-0002-6318-2978 en_US http://ieeexplore.ieee.org/xpls/abs_all.jsp?arnumber=5737914 Computing in Cardiology Article is made available in accordance with the publisher's policy and may be subject to US copyright law. Please refer to the publisher's site for terms of use. application/pdf IEEE Computer Society IEEE |
| spellingShingle | Lee, J. Mark, Roger Greenwood A hypotensive episode predictor for intensive care based on heart rate and blood pressure time series |
| title | A hypotensive episode predictor for intensive care based on heart rate and blood pressure time series |
| title_full | A hypotensive episode predictor for intensive care based on heart rate and blood pressure time series |
| title_fullStr | A hypotensive episode predictor for intensive care based on heart rate and blood pressure time series |
| title_full_unstemmed | A hypotensive episode predictor for intensive care based on heart rate and blood pressure time series |
| title_short | A hypotensive episode predictor for intensive care based on heart rate and blood pressure time series |
| title_sort | hypotensive episode predictor for intensive care based on heart rate and blood pressure time series |
| url | http://hdl.handle.net/1721.1/65394 https://orcid.org/0000-0001-8593-9321 https://orcid.org/0000-0002-6318-2978 |
| work_keys_str_mv | AT leej ahypotensiveepisodepredictorforintensivecarebasedonheartrateandbloodpressuretimeseries AT markrogergreenwood ahypotensiveepisodepredictorforintensivecarebasedonheartrateandbloodpressuretimeseries AT leej hypotensiveepisodepredictorforintensivecarebasedonheartrateandbloodpressuretimeseries AT markrogergreenwood hypotensiveepisodepredictorforintensivecarebasedonheartrateandbloodpressuretimeseries |