Forecasting of Continuous Vital Sign Using Multivariate Auto-Regressive Models

Søren M. Rasmussen; Jesper Mølgaard; Camilla Haahr-Raunkjær; Christian S. Meyhoff; Eske Aasvang; Helge B. D. Sørensen

doi:10.1109/EMBC48229.2022.9871010

Forecasting of Continuous Vital Sign Using Multivariate Auto-Regressive Models

Søren M. Rasmussen
, Jesper Mølgaard
, Camilla Haahr-Raunkjær
, Christian S. Meyhoff
, Eske Aasvang
, Helge B. D. Sørensen

Research output: Chapter in Book/Report/Conference proceeding › Article in proceedings › Research › peer-review

104 Downloads (Orbit)

Abstract

This project assessed the use of multivariate auto-regressive (MAR) models to create forecasts of continuous vital signs in hospitalized patients. A total of 20 hours continuous (1/60Hz) heart rate and respiration rate from eight postoperative patients, where used to fit a centered MAR model for forecasting in windows of 15 minutes. The model was fitted using Markov Chain Monte Carlo sampling, and the model was evaluated on data from five additional patients. The results demonstrate an average RMSE in the forecast window of 11.4 (SD: 7.30) beats per minute for heart rate and 3.3 (SD:1.3) breaths per minute for respiration rate. These results indicate potential for forecasting vital signs in a clinical setting.

Original language	English
Title of host publication	Proceedings of 44^th Annual International Conference of the IEEE Engineering in Medicine & Biology Society
Publisher	IEEE
Publication date	15 Jul 2022
Pages	385-388
Article number	9871010
ISBN (Print)	978-1-7281-2783-5
DOIs	https://doi.org/10.1109/EMBC48229.2022.9871010
Publication status	Published - 15 Jul 2022
Event	44th Annual International Conference of the IEEE Engineering in Medicine and Biology Society - Glasgow, United Kingdom Duration: 11 Jul 2022 → 15 Jul 2022 Conference number: 44 https://ieeexplore.ieee.org/xpl/conhome/9870821/proceeding

Conference

Conference	44th Annual International Conference of the IEEE Engineering in Medicine and Biology Society
Number	44
Country/Territory	United Kingdom
City	Glasgow
Period	11/07/2022 → 15/07/2022
Sponsor	Verasonics, Inc.
Internet address	https://ieeexplore.ieee.org/xpl/conhome/9870821/proceeding

Keywords

Heart rate
Monte Carlo methods
Time series analysis
Predictive models
Markov processes
Data models
Time measurement

Access to Document

10.1109/EMBC48229.2022.9871010

FulltextFinal published version, 753 KB

OpenUrl availability

Full text

Cite this

Rasmussen, S. M., Mølgaard, J., Haahr-Raunkjær, C., Meyhoff, C. S., Aasvang, E., & Sørensen, H. B. D. (2022). Forecasting of Continuous Vital Sign Using Multivariate Auto-Regressive Models. In Proceedings of 44^th Annual International Conference of the IEEE Engineering in Medicine & Biology Society (pp. 385-388). Article 9871010 IEEE. https://doi.org/10.1109/EMBC48229.2022.9871010

@inproceedings{fa32f1a625e24a09925429936d0f39cb,

title = "Forecasting of Continuous Vital Sign Using Multivariate Auto-Regressive Models",

abstract = "This project assessed the use of multivariate auto-regressive (MAR) models to create forecasts of continuous vital signs in hospitalized patients. A total of 20 hours continuous (1/60Hz) heart rate and respiration rate from eight postoperative patients, where used to fit a centered MAR model for forecasting in windows of 15 minutes. The model was fitted using Markov Chain Monte Carlo sampling, and the model was evaluated on data from five additional patients. The results demonstrate an average RMSE in the forecast window of 11.4 (SD: 7.30) beats per minute for heart rate and 3.3 (SD:1.3) breaths per minute for respiration rate. These results indicate potential for forecasting vital signs in a clinical setting.",

keywords = "Heart rate, Monte Carlo methods, Time series analysis, Predictive models, Markov processes, Data models, Time measurement",

author = "Rasmussen, \{S{\o}ren M.\} and Jesper M{\o}lgaard and Camilla Haahr-Raunkj{\ae}r and Meyhoff, \{Christian S.\} and Eske Aasvang and S{\o}rensen, \{Helge B. D.\}",

year = "2022",

month = jul,

day = "15",

doi = "10.1109/EMBC48229.2022.9871010",

language = "English",

isbn = "978-1-7281-2783-5",

pages = "385--388",

booktitle = "Proceedings of 44th Annual International Conference of the IEEE Engineering in Medicine \& Biology Society",

publisher = "IEEE",

address = "United States",

note = "44th Annual International Conference of the IEEE Engineering in Medicine and Biology Society, EMBC 2022 ; Conference date: 11-07-2022 Through 15-07-2022",

url = "https://ieeexplore.ieee.org/xpl/conhome/9870821/proceeding",

}

Rasmussen, SM, Mølgaard, J, Haahr-Raunkjær, C, Meyhoff, CS, Aasvang, E & Sørensen, HBD 2022, Forecasting of Continuous Vital Sign Using Multivariate Auto-Regressive Models. in Proceedings of 44^th Annual International Conference of the IEEE Engineering in Medicine & Biology Society., 9871010, IEEE, pp. 385-388, 44th Annual International Conference of the IEEE Engineering in Medicine and Biology Society, Glasgow, United Kingdom, 11/07/2022. https://doi.org/10.1109/EMBC48229.2022.9871010

Forecasting of Continuous Vital Sign Using Multivariate Auto-Regressive Models. / Rasmussen, Søren M.; Mølgaard, Jesper; Haahr-Raunkjær, Camilla et al.
Proceedings of 44^th Annual International Conference of the IEEE Engineering in Medicine & Biology Society. IEEE, 2022. p. 385-388 9871010.

Research output: Chapter in Book/Report/Conference proceeding › Article in proceedings › Research › peer-review

TY - GEN

T1 - Forecasting of Continuous Vital Sign Using Multivariate Auto-Regressive Models

AU - Rasmussen, Søren M.

AU - Mølgaard, Jesper

AU - Haahr-Raunkjær, Camilla

AU - Meyhoff, Christian S.

AU - Aasvang, Eske

AU - Sørensen, Helge B. D.

N1 - Conference code: 44

PY - 2022/7/15

Y1 - 2022/7/15

N2 - This project assessed the use of multivariate auto-regressive (MAR) models to create forecasts of continuous vital signs in hospitalized patients. A total of 20 hours continuous (1/60Hz) heart rate and respiration rate from eight postoperative patients, where used to fit a centered MAR model for forecasting in windows of 15 minutes. The model was fitted using Markov Chain Monte Carlo sampling, and the model was evaluated on data from five additional patients. The results demonstrate an average RMSE in the forecast window of 11.4 (SD: 7.30) beats per minute for heart rate and 3.3 (SD:1.3) breaths per minute for respiration rate. These results indicate potential for forecasting vital signs in a clinical setting.

AB - This project assessed the use of multivariate auto-regressive (MAR) models to create forecasts of continuous vital signs in hospitalized patients. A total of 20 hours continuous (1/60Hz) heart rate and respiration rate from eight postoperative patients, where used to fit a centered MAR model for forecasting in windows of 15 minutes. The model was fitted using Markov Chain Monte Carlo sampling, and the model was evaluated on data from five additional patients. The results demonstrate an average RMSE in the forecast window of 11.4 (SD: 7.30) beats per minute for heart rate and 3.3 (SD:1.3) breaths per minute for respiration rate. These results indicate potential for forecasting vital signs in a clinical setting.

KW - Heart rate

KW - Monte Carlo methods

KW - Time series analysis

KW - Predictive models

KW - Markov processes

KW - Data models

KW - Time measurement

U2 - 10.1109/EMBC48229.2022.9871010

DO - 10.1109/EMBC48229.2022.9871010

M3 - Article in proceedings

C2 - 36085852

SN - 978-1-7281-2783-5

SP - 385

EP - 388

BT - Proceedings of 44th Annual International Conference of the IEEE Engineering in Medicine & Biology Society

PB - IEEE

T2 - 44th Annual International Conference of the IEEE Engineering in Medicine and Biology Society

Y2 - 11 July 2022 through 15 July 2022

ER -

Forecasting of Continuous Vital Sign Using Multivariate Auto-Regressive Models

Abstract

Conference

Keywords

Access to Document

OpenUrl availability

Fingerprint

Cite this