Multiple model analytics for adverse event prediction in remote health monitoring systems

Mohammad Pourhomayoun, Nabil Alshurafa, Bobak Mortazavi, Hassan Ghasemzadeh, Konstantinos Sideris, Bahman Sadeghi, Michael Ong, Lorraine Evangelista, Patrick Romano, Andrew Auerbach, Asher Kimchi, Majid Sarrafzadeh

Research output: Chapter in Book/Report/Conference proceedingConference contribution

9 Citations (Scopus)

Abstract

Remote health monitoring systems (RHMS) are gaining an important role in healthcare by collecting and transmitting patient vital information and providing data analysis and medical adverse event prediction (e.g. hospital readmission prediction). Reduction in the readmission rate is typically achieved by early prediction of the readmission based on the data collected from RHMS, and then applying early intervention to prevent the readmission. Given the diversity of patient populations and the continuous nature of patient monitoring, a single static predictive model is insufficient for accurately predicting adverse events. To address this issue, we propose a multiple prediction modeling technique that includes a set of accurate prediction models rather than one single universal predictor. In this paper, we propose a novel analytics framework based on the physiological data collected from RHMS, advanced clustering algorithms and multiple-model-classification. We tested our proposed method on a subset of data collected through a remote health monitoring system from 600 Heart Failure patients. Our proposed method provides significant improvements in prediction accuracy and performance over single predictive models.

Original languageEnglish (US)
Title of host publication2014 IEEE Healthcare Innovation Conference, HIC 2014
PublisherInstitute of Electrical and Electronics Engineers Inc.
Pages106-110
Number of pages5
ISBN (Electronic)9781467363648
DOIs
StatePublished - Feb 10 2014
Externally publishedYes
Event2014 IEEE Healthcare Innovation Conference, HIC 2014 - Seattle, United States
Duration: Oct 8 2014Oct 10 2014

Publication series

Name2014 IEEE Healthcare Innovation Conference, HIC 2014

Other

Other2014 IEEE Healthcare Innovation Conference, HIC 2014
CountryUnited States
CitySeattle
Period10/8/1410/10/14

Fingerprint

Health
Monitoring
Patient Readmission
Physiologic Monitoring
Cluster Analysis
Patient monitoring
Heart Failure
Delivery of Health Care
Clustering algorithms
Population

ASJC Scopus subject areas

  • Medicine(all)
  • Biomedical Engineering

Cite this

Pourhomayoun, M., Alshurafa, N., Mortazavi, B., Ghasemzadeh, H., Sideris, K., Sadeghi, B., ... Sarrafzadeh, M. (2014). Multiple model analytics for adverse event prediction in remote health monitoring systems. In 2014 IEEE Healthcare Innovation Conference, HIC 2014 (pp. 106-110). [7038886] (2014 IEEE Healthcare Innovation Conference, HIC 2014). Institute of Electrical and Electronics Engineers Inc.. https://doi.org/10.1109/HIC.2014.7038886

Multiple model analytics for adverse event prediction in remote health monitoring systems. / Pourhomayoun, Mohammad; Alshurafa, Nabil; Mortazavi, Bobak; Ghasemzadeh, Hassan; Sideris, Konstantinos; Sadeghi, Bahman; Ong, Michael; Evangelista, Lorraine; Romano, Patrick; Auerbach, Andrew; Kimchi, Asher; Sarrafzadeh, Majid.

2014 IEEE Healthcare Innovation Conference, HIC 2014. Institute of Electrical and Electronics Engineers Inc., 2014. p. 106-110 7038886 (2014 IEEE Healthcare Innovation Conference, HIC 2014).

Research output: Chapter in Book/Report/Conference proceedingConference contribution

Pourhomayoun, M, Alshurafa, N, Mortazavi, B, Ghasemzadeh, H, Sideris, K, Sadeghi, B, Ong, M, Evangelista, L, Romano, P, Auerbach, A, Kimchi, A & Sarrafzadeh, M 2014, Multiple model analytics for adverse event prediction in remote health monitoring systems. in 2014 IEEE Healthcare Innovation Conference, HIC 2014., 7038886, 2014 IEEE Healthcare Innovation Conference, HIC 2014, Institute of Electrical and Electronics Engineers Inc., pp. 106-110, 2014 IEEE Healthcare Innovation Conference, HIC 2014, Seattle, United States, 10/8/14. https://doi.org/10.1109/HIC.2014.7038886
Pourhomayoun M, Alshurafa N, Mortazavi B, Ghasemzadeh H, Sideris K, Sadeghi B et al. Multiple model analytics for adverse event prediction in remote health monitoring systems. In 2014 IEEE Healthcare Innovation Conference, HIC 2014. Institute of Electrical and Electronics Engineers Inc. 2014. p. 106-110. 7038886. (2014 IEEE Healthcare Innovation Conference, HIC 2014). https://doi.org/10.1109/HIC.2014.7038886
Pourhomayoun, Mohammad ; Alshurafa, Nabil ; Mortazavi, Bobak ; Ghasemzadeh, Hassan ; Sideris, Konstantinos ; Sadeghi, Bahman ; Ong, Michael ; Evangelista, Lorraine ; Romano, Patrick ; Auerbach, Andrew ; Kimchi, Asher ; Sarrafzadeh, Majid. / Multiple model analytics for adverse event prediction in remote health monitoring systems. 2014 IEEE Healthcare Innovation Conference, HIC 2014. Institute of Electrical and Electronics Engineers Inc., 2014. pp. 106-110 (2014 IEEE Healthcare Innovation Conference, HIC 2014).
@inproceedings{515a80252e1a46bdb4cd0b6a2735b449,
title = "Multiple model analytics for adverse event prediction in remote health monitoring systems",
abstract = "Remote health monitoring systems (RHMS) are gaining an important role in healthcare by collecting and transmitting patient vital information and providing data analysis and medical adverse event prediction (e.g. hospital readmission prediction). Reduction in the readmission rate is typically achieved by early prediction of the readmission based on the data collected from RHMS, and then applying early intervention to prevent the readmission. Given the diversity of patient populations and the continuous nature of patient monitoring, a single static predictive model is insufficient for accurately predicting adverse events. To address this issue, we propose a multiple prediction modeling technique that includes a set of accurate prediction models rather than one single universal predictor. In this paper, we propose a novel analytics framework based on the physiological data collected from RHMS, advanced clustering algorithms and multiple-model-classification. We tested our proposed method on a subset of data collected through a remote health monitoring system from 600 Heart Failure patients. Our proposed method provides significant improvements in prediction accuracy and performance over single predictive models.",
author = "Mohammad Pourhomayoun and Nabil Alshurafa and Bobak Mortazavi and Hassan Ghasemzadeh and Konstantinos Sideris and Bahman Sadeghi and Michael Ong and Lorraine Evangelista and Patrick Romano and Andrew Auerbach and Asher Kimchi and Majid Sarrafzadeh",
year = "2014",
month = "2",
day = "10",
doi = "10.1109/HIC.2014.7038886",
language = "English (US)",
series = "2014 IEEE Healthcare Innovation Conference, HIC 2014",
publisher = "Institute of Electrical and Electronics Engineers Inc.",
pages = "106--110",
booktitle = "2014 IEEE Healthcare Innovation Conference, HIC 2014",

}

TY - GEN

T1 - Multiple model analytics for adverse event prediction in remote health monitoring systems

AU - Pourhomayoun, Mohammad

AU - Alshurafa, Nabil

AU - Mortazavi, Bobak

AU - Ghasemzadeh, Hassan

AU - Sideris, Konstantinos

AU - Sadeghi, Bahman

AU - Ong, Michael

AU - Evangelista, Lorraine

AU - Romano, Patrick

AU - Auerbach, Andrew

AU - Kimchi, Asher

AU - Sarrafzadeh, Majid

PY - 2014/2/10

Y1 - 2014/2/10

N2 - Remote health monitoring systems (RHMS) are gaining an important role in healthcare by collecting and transmitting patient vital information and providing data analysis and medical adverse event prediction (e.g. hospital readmission prediction). Reduction in the readmission rate is typically achieved by early prediction of the readmission based on the data collected from RHMS, and then applying early intervention to prevent the readmission. Given the diversity of patient populations and the continuous nature of patient monitoring, a single static predictive model is insufficient for accurately predicting adverse events. To address this issue, we propose a multiple prediction modeling technique that includes a set of accurate prediction models rather than one single universal predictor. In this paper, we propose a novel analytics framework based on the physiological data collected from RHMS, advanced clustering algorithms and multiple-model-classification. We tested our proposed method on a subset of data collected through a remote health monitoring system from 600 Heart Failure patients. Our proposed method provides significant improvements in prediction accuracy and performance over single predictive models.

AB - Remote health monitoring systems (RHMS) are gaining an important role in healthcare by collecting and transmitting patient vital information and providing data analysis and medical adverse event prediction (e.g. hospital readmission prediction). Reduction in the readmission rate is typically achieved by early prediction of the readmission based on the data collected from RHMS, and then applying early intervention to prevent the readmission. Given the diversity of patient populations and the continuous nature of patient monitoring, a single static predictive model is insufficient for accurately predicting adverse events. To address this issue, we propose a multiple prediction modeling technique that includes a set of accurate prediction models rather than one single universal predictor. In this paper, we propose a novel analytics framework based on the physiological data collected from RHMS, advanced clustering algorithms and multiple-model-classification. We tested our proposed method on a subset of data collected through a remote health monitoring system from 600 Heart Failure patients. Our proposed method provides significant improvements in prediction accuracy and performance over single predictive models.

UR - http://www.scopus.com/inward/record.url?scp=84949922867&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=84949922867&partnerID=8YFLogxK

U2 - 10.1109/HIC.2014.7038886

DO - 10.1109/HIC.2014.7038886

M3 - Conference contribution

AN - SCOPUS:84949922867

T3 - 2014 IEEE Healthcare Innovation Conference, HIC 2014

SP - 106

EP - 110

BT - 2014 IEEE Healthcare Innovation Conference, HIC 2014

PB - Institute of Electrical and Electronics Engineers Inc.

ER -