Real time reconstruction of quasiperiodic multi parameter physiological signals
A modern intensive care unit (ICU) has automated analysis systems that depend on continuous uninterrupted real time monitoring of physiological signals such as electrocardiogram (ECG), arterial blood pressure (ABP), and photo-plethysmogram (PPG). These signals are often corrupted by noise, artifacts...
| Main Authors: | , |
|---|---|
| Other Authors: | |
| Format: | Article |
| Language: | English |
| Published: |
Springer Science + Business Media B.V.
2013
|
| Online Access: | http://hdl.handle.net/1721.1/77193 https://orcid.org/0000-0003-0992-0906 |
| _version_ | 1826200576007864320 |
|---|---|
| author | Ganeshapillai, Gartheeban Guttag, John V. |
| author2 | Massachusetts Institute of Technology. Computer Science and Artificial Intelligence Laboratory |
| author_facet | Massachusetts Institute of Technology. Computer Science and Artificial Intelligence Laboratory Ganeshapillai, Gartheeban Guttag, John V. |
| author_sort | Ganeshapillai, Gartheeban |
| collection | MIT |
| description | A modern intensive care unit (ICU) has automated analysis systems that depend on continuous uninterrupted real time monitoring of physiological signals such as electrocardiogram (ECG), arterial blood pressure (ABP), and photo-plethysmogram (PPG). These signals are often corrupted by noise, artifacts, and missing data. We present an automated learning framework for real time reconstruction of corrupted multi-parameter nonstationary quasiperiodic physiological signals. The key idea is to learn a patient-specific model of the relationships between signals, and then reconstruct corrupted segments using the information available in correlated signals. We evaluated our method on MIT-BIH arrhythmia data, a two-channel ECG dataset with many clinically significant arrhythmias, and on the CinC challenge 2010 data, a multi-parameter dataset containing ECG, ABP, and PPG. For each, we evaluated both the residual distance between the original signals and the reconstructed signals, and the performance of a heartbeat classifier on a reconstructed ECG signal. At an SNR of 0 dB, the average residual distance on the CinC data was roughly 3% of the energy in the signal, and on the arrhythmia database it was roughly 16%. The difference is attributable to the large amount of diversity in the arrhythmia database. Remarkably, despite the relatively high residual difference, the classification accuracy on the arrhythmia database was still 98%, indicating that our method restored the physiologically important aspects of the signal. |
| first_indexed | 2024-09-23T11:38:31Z |
| format | Article |
| id | mit-1721.1/77193 |
| institution | Massachusetts Institute of Technology |
| language | English |
| last_indexed | 2024-09-23T11:38:31Z |
| publishDate | 2013 |
| publisher | Springer Science + Business Media B.V. |
| record_format | dspace |
| spelling | mit-1721.1/771932022-09-27T20:56:14Z Real time reconstruction of quasiperiodic multi parameter physiological signals Ganeshapillai, Gartheeban Guttag, John V. Massachusetts Institute of Technology. Computer Science and Artificial Intelligence Laboratory Massachusetts Institute of Technology. Department of Electrical Engineering and Computer Science Guttag, John V. Ganeshapillai, Gartheeban A modern intensive care unit (ICU) has automated analysis systems that depend on continuous uninterrupted real time monitoring of physiological signals such as electrocardiogram (ECG), arterial blood pressure (ABP), and photo-plethysmogram (PPG). These signals are often corrupted by noise, artifacts, and missing data. We present an automated learning framework for real time reconstruction of corrupted multi-parameter nonstationary quasiperiodic physiological signals. The key idea is to learn a patient-specific model of the relationships between signals, and then reconstruct corrupted segments using the information available in correlated signals. We evaluated our method on MIT-BIH arrhythmia data, a two-channel ECG dataset with many clinically significant arrhythmias, and on the CinC challenge 2010 data, a multi-parameter dataset containing ECG, ABP, and PPG. For each, we evaluated both the residual distance between the original signals and the reconstructed signals, and the performance of a heartbeat classifier on a reconstructed ECG signal. At an SNR of 0 dB, the average residual distance on the CinC data was roughly 3% of the energy in the signal, and on the arrhythmia database it was roughly 16%. The difference is attributable to the large amount of diversity in the arrhythmia database. Remarkably, despite the relatively high residual difference, the classification accuracy on the arrhythmia database was still 98%, indicating that our method restored the physiologically important aspects of the signal. Quanta Computer (Firm) 2013-02-21T21:18:56Z 2013-02-21T21:18:56Z 2012-08 2011-10 2013-02-21T12:08:56Z Article http://purl.org/eprint/type/JournalArticle 1687-6172 1687-6180 http://hdl.handle.net/1721.1/77193 Ganeshapillai, Gartheeban, and John Guttag. “Real Time Reconstruction of Quasiperiodic Multi Parameter Physiological Signals.” EURASIP Journal on Advances in Signal Processing 2012.1 (2012): 173. CrossRef. Web. https://orcid.org/0000-0003-0992-0906 en http://dx.doi.org/10.1186/1687-6180-2012-173 EURASIP Journal on Advances in Signal Processing http://creativecommons.org/licenses/by/2.0 Gartheeban Ganeshapillai et al.; licensee BioMed Central Ltd. application/pdf Springer Science + Business Media B.V. |
| spellingShingle | Ganeshapillai, Gartheeban Guttag, John V. Real time reconstruction of quasiperiodic multi parameter physiological signals |
| title | Real time reconstruction of quasiperiodic multi parameter physiological signals |
| title_full | Real time reconstruction of quasiperiodic multi parameter physiological signals |
| title_fullStr | Real time reconstruction of quasiperiodic multi parameter physiological signals |
| title_full_unstemmed | Real time reconstruction of quasiperiodic multi parameter physiological signals |
| title_short | Real time reconstruction of quasiperiodic multi parameter physiological signals |
| title_sort | real time reconstruction of quasiperiodic multi parameter physiological signals |
| url | http://hdl.handle.net/1721.1/77193 https://orcid.org/0000-0003-0992-0906 |
| work_keys_str_mv | AT ganeshapillaigartheeban realtimereconstructionofquasiperiodicmultiparameterphysiologicalsignals AT guttagjohnv realtimereconstructionofquasiperiodicmultiparameterphysiologicalsignals |