A Physiological Time Series Dynamics-Based Approach toPatient Monitoring and Outcome Prediction
Cardiovascular variables such as heart rate (HR) and blood pressure (BP) are regulated by an underlying control system, and therefore, the time series of these vital signs exhibit rich dynamical patterns of interaction in response to external perturbations (e.g., drug administration), as well as pat...
| Main Authors: | , , , , , , |
|---|---|
| Other Authors: | |
| Format: | Article |
| Language: | en_US |
| Published: |
Institute of Electrical and Electronics Engineers (IEEE)
2016
|
| Online Access: | http://hdl.handle.net/1721.1/102997 https://orcid.org/0000-0002-6318-2978 |
| _version_ | 1826193078770204672 |
|---|---|
| author | Adams, Ryan P. Mayaud, Louis Moody, George B. Malhotra, Atul Lehman, Li-Wei Mark, Roger G Nemati, Shamim, 1980- |
| author2 | Massachusetts Institute of Technology. Institute for Medical Engineering & Science |
| author_facet | Massachusetts Institute of Technology. Institute for Medical Engineering & Science Adams, Ryan P. Mayaud, Louis Moody, George B. Malhotra, Atul Lehman, Li-Wei Mark, Roger G Nemati, Shamim, 1980- |
| author_sort | Adams, Ryan P. |
| collection | MIT |
| description | Cardiovascular variables such as heart rate (HR) and blood pressure (BP) are regulated by an underlying control system, and therefore, the time series of these vital signs exhibit rich dynamical patterns of interaction in response to external perturbations (e.g., drug administration), as well as pathological states (e.g., onset of sepsis and hypotension). A question of interest is whether “similar” dynamical patterns can be identified across a heterogeneous patient cohort, and be used for prognosis of patients' health and progress. In this paper, we used a switching vector autoregressive framework to systematically learn and identify a collection of vital sign time series dynamics, which are possibly recurrent within the same patient and may be shared across the entire cohort. We show that these dynamical behaviors can be used to characterize the physiological “state” of a patient. We validate our technique using simulated time series of the cardiovascular system, and human recordings of HR and BP time series from an orthostatic stress study with known postural states. Using the HR and BP dynamics of an intensive care unit (ICU) cohort of over 450 patients from the MIMIC II database, we demonstrate that the discovered cardiovascular dynamics are significantly associated with hospital mortality (dynamic modes 3 and 9, p = 0.001, p = 0.006 from logistic regression after adjusting for the APACHE scores). Combining the dynamics of BP time series and SAPS-I or APACHE-III provided a more accurate assessment of patient survival/mortality in the hospital than using SAPS-I and APACHE-III alone (p = 0.005 and p = 0.045). Our results suggest that the discovered dynamics of vital sign time series may contain additional prognostic value beyond that of the baseline acuity measures, and can potentially be used as an independent predictor of outcomes in the ICU. |
| first_indexed | 2024-09-23T09:33:25Z |
| format | Article |
| id | mit-1721.1/102997 |
| institution | Massachusetts Institute of Technology |
| language | en_US |
| last_indexed | 2024-09-23T09:33:25Z |
| publishDate | 2016 |
| publisher | Institute of Electrical and Electronics Engineers (IEEE) |
| record_format | dspace |
| spelling | mit-1721.1/1029972022-09-30T15:17:52Z A Physiological Time Series Dynamics-Based Approach toPatient Monitoring and Outcome Prediction Adams, Ryan P. Mayaud, Louis Moody, George B. Malhotra, Atul Lehman, Li-Wei Mark, Roger G Nemati, Shamim, 1980- Massachusetts Institute of Technology. Institute for Medical Engineering & Science Lehman, Li-wei H. Moody, George B. Mark, Roger G. Cardiovascular variables such as heart rate (HR) and blood pressure (BP) are regulated by an underlying control system, and therefore, the time series of these vital signs exhibit rich dynamical patterns of interaction in response to external perturbations (e.g., drug administration), as well as pathological states (e.g., onset of sepsis and hypotension). A question of interest is whether “similar” dynamical patterns can be identified across a heterogeneous patient cohort, and be used for prognosis of patients' health and progress. In this paper, we used a switching vector autoregressive framework to systematically learn and identify a collection of vital sign time series dynamics, which are possibly recurrent within the same patient and may be shared across the entire cohort. We show that these dynamical behaviors can be used to characterize the physiological “state” of a patient. We validate our technique using simulated time series of the cardiovascular system, and human recordings of HR and BP time series from an orthostatic stress study with known postural states. Using the HR and BP dynamics of an intensive care unit (ICU) cohort of over 450 patients from the MIMIC II database, we demonstrate that the discovered cardiovascular dynamics are significantly associated with hospital mortality (dynamic modes 3 and 9, p = 0.001, p = 0.006 from logistic regression after adjusting for the APACHE scores). Combining the dynamics of BP time series and SAPS-I or APACHE-III provided a more accurate assessment of patient survival/mortality in the hospital than using SAPS-I and APACHE-III alone (p = 0.005 and p = 0.045). Our results suggest that the discovered dynamics of vital sign time series may contain additional prognostic value beyond that of the baseline acuity measures, and can potentially be used as an independent predictor of outcomes in the ICU. National Institutes of Health (U.S.) (NIH grant R01-EB001659) National Institutes of Health (U.S.) (NIH grant R01GM104987) James S. McDonnell Foundation (Postdoctoral Grant) United States. Defense Advanced Research Projects Agency (DARPA Young Faculty Award N66001-12-1-4219 Grant) 2016-06-06T19:57:34Z 2016-06-06T19:57:34Z 2014-06 2014-03 Article http://purl.org/eprint/type/JournalArticle 2168-2194 2168-2208 http://hdl.handle.net/1721.1/102997 Lehman, Li-wei, Ryan P. Adams, Louis Mayaud, George B. Moody, Atul Malhotra, Roger G. Mark, and Shamim Nemati. "A Physiological Time Series Dynamics-Based Approach toPatient Monitoring and Outcome Prediction." IEEE Journal of Biomedical and Health Informatics 19:3 (May 2015), p. 1068-1076. https://orcid.org/0000-0002-6318-2978 en_US http://dx.doi.org/10.1109/jbhi.2014.2330827 IEEE Journal of Biomedical and Health Informatics Creative Commons Attribution-Noncommercial-Share Alike http://creativecommons.org/licenses/by-nc-sa/4.0/ application/pdf Institute of Electrical and Electronics Engineers (IEEE) PMC |
| spellingShingle | Adams, Ryan P. Mayaud, Louis Moody, George B. Malhotra, Atul Lehman, Li-Wei Mark, Roger G Nemati, Shamim, 1980- A Physiological Time Series Dynamics-Based Approach toPatient Monitoring and Outcome Prediction |
| title | A Physiological Time Series Dynamics-Based Approach toPatient Monitoring and Outcome Prediction |
| title_full | A Physiological Time Series Dynamics-Based Approach toPatient Monitoring and Outcome Prediction |
| title_fullStr | A Physiological Time Series Dynamics-Based Approach toPatient Monitoring and Outcome Prediction |
| title_full_unstemmed | A Physiological Time Series Dynamics-Based Approach toPatient Monitoring and Outcome Prediction |
| title_short | A Physiological Time Series Dynamics-Based Approach toPatient Monitoring and Outcome Prediction |
| title_sort | physiological time series dynamics based approach topatient monitoring and outcome prediction |
| url | http://hdl.handle.net/1721.1/102997 https://orcid.org/0000-0002-6318-2978 |
| work_keys_str_mv | AT adamsryanp aphysiologicaltimeseriesdynamicsbasedapproachtopatientmonitoringandoutcomeprediction AT mayaudlouis aphysiologicaltimeseriesdynamicsbasedapproachtopatientmonitoringandoutcomeprediction AT moodygeorgeb aphysiologicaltimeseriesdynamicsbasedapproachtopatientmonitoringandoutcomeprediction AT malhotraatul aphysiologicaltimeseriesdynamicsbasedapproachtopatientmonitoringandoutcomeprediction AT lehmanliwei aphysiologicaltimeseriesdynamicsbasedapproachtopatientmonitoringandoutcomeprediction AT markrogerg aphysiologicaltimeseriesdynamicsbasedapproachtopatientmonitoringandoutcomeprediction AT nematishamim1980 aphysiologicaltimeseriesdynamicsbasedapproachtopatientmonitoringandoutcomeprediction AT adamsryanp physiologicaltimeseriesdynamicsbasedapproachtopatientmonitoringandoutcomeprediction AT mayaudlouis physiologicaltimeseriesdynamicsbasedapproachtopatientmonitoringandoutcomeprediction AT moodygeorgeb physiologicaltimeseriesdynamicsbasedapproachtopatientmonitoringandoutcomeprediction AT malhotraatul physiologicaltimeseriesdynamicsbasedapproachtopatientmonitoringandoutcomeprediction AT lehmanliwei physiologicaltimeseriesdynamicsbasedapproachtopatientmonitoringandoutcomeprediction AT markrogerg physiologicaltimeseriesdynamicsbasedapproachtopatientmonitoringandoutcomeprediction AT nematishamim1980 physiologicaltimeseriesdynamicsbasedapproachtopatientmonitoringandoutcomeprediction |