Missing data imputation for remote CHF patient monitoring systems

Myung Kyung Suh, Jonathan Woodbridge, Mars Lan, Alex Bui, Lorraine Evangelista, Majid Sarrafzadeh

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

4 Citations (Scopus)

Abstract

Congestive heart failure (CHF) is a leading cause of death in the United States. WANDA is a wireless health project that leverages sensor technology and wireless communication to monitor the health status of patients with CHF. The first pilot study of WANDA showed the system's effectiveness for patients with CHF. However, WANDA experienced a considerable amount of missing data due to system misuse, nonuse, and failure. Missing data is highly undesirable as automated alarms may fail to notify healthcare professionals of potentially dangerous patient conditions. In this study, we exploit machine learning techniques including projection adjustment by contribution estimation regression (PACE), Bayesian methods, and voting feature interval (VFI) algorithms to predict both non-binomial and binomial data. The experimental results show that the aforementioned algorithms are superior to other methods with high accuracy and recall. This approach also shows an improved ability to predict missing data when training on entire populations, as opposed to training unique classifiers for each individual.

Original languageEnglish (US)
Title of host publication33rd Annual International Conference of the IEEE Engineering in Medicine and Biology Society, EMBS 2011
Pages3184-3187
Number of pages4
DOIs
StatePublished - Dec 26 2011
Externally publishedYes
Event33rd Annual International Conference of the IEEE Engineering in Medicine and Biology Society, EMBS 2011 - Boston, MA, United States
Duration: Aug 30 2011Sep 3 2011

Publication series

NameProceedings of the Annual International Conference of the IEEE Engineering in Medicine and Biology Society, EMBS
ISSN (Print)1557-170X

Other

Other33rd Annual International Conference of the IEEE Engineering in Medicine and Biology Society, EMBS 2011
CountryUnited States
CityBoston, MA
Period8/30/119/3/11

Fingerprint

Patient monitoring
Physiologic Monitoring
Heart Failure
Wireless Technology
Health
Social Adjustment
Aptitude
Bayes Theorem
Politics
Health Status
Learning systems
Cause of Death
Classifiers
Communication
Delivery of Health Care
Sensors
Population

ASJC Scopus subject areas

  • Signal Processing
  • Biomedical Engineering
  • Computer Vision and Pattern Recognition
  • Health Informatics

Cite this

Suh, M. K., Woodbridge, J., Lan, M., Bui, A., Evangelista, L., & Sarrafzadeh, M. (2011). Missing data imputation for remote CHF patient monitoring systems. In 33rd Annual International Conference of the IEEE Engineering in Medicine and Biology Society, EMBS 2011 (pp. 3184-3187). [6090867] (Proceedings of the Annual International Conference of the IEEE Engineering in Medicine and Biology Society, EMBS). https://doi.org/10.1109/IEMBS.2011.6090867

Missing data imputation for remote CHF patient monitoring systems. / Suh, Myung Kyung; Woodbridge, Jonathan; Lan, Mars; Bui, Alex; Evangelista, Lorraine; Sarrafzadeh, Majid.

33rd Annual International Conference of the IEEE Engineering in Medicine and Biology Society, EMBS 2011. 2011. p. 3184-3187 6090867 (Proceedings of the Annual International Conference of the IEEE Engineering in Medicine and Biology Society, EMBS).

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

Suh, MK, Woodbridge, J, Lan, M, Bui, A, Evangelista, L & Sarrafzadeh, M 2011, Missing data imputation for remote CHF patient monitoring systems. in 33rd Annual International Conference of the IEEE Engineering in Medicine and Biology Society, EMBS 2011., 6090867, Proceedings of the Annual International Conference of the IEEE Engineering in Medicine and Biology Society, EMBS, pp. 3184-3187, 33rd Annual International Conference of the IEEE Engineering in Medicine and Biology Society, EMBS 2011, Boston, MA, United States, 8/30/11. https://doi.org/10.1109/IEMBS.2011.6090867
Suh MK, Woodbridge J, Lan M, Bui A, Evangelista L, Sarrafzadeh M. Missing data imputation for remote CHF patient monitoring systems. In 33rd Annual International Conference of the IEEE Engineering in Medicine and Biology Society, EMBS 2011. 2011. p. 3184-3187. 6090867. (Proceedings of the Annual International Conference of the IEEE Engineering in Medicine and Biology Society, EMBS). https://doi.org/10.1109/IEMBS.2011.6090867
Suh, Myung Kyung ; Woodbridge, Jonathan ; Lan, Mars ; Bui, Alex ; Evangelista, Lorraine ; Sarrafzadeh, Majid. / Missing data imputation for remote CHF patient monitoring systems. 33rd Annual International Conference of the IEEE Engineering in Medicine and Biology Society, EMBS 2011. 2011. pp. 3184-3187 (Proceedings of the Annual International Conference of the IEEE Engineering in Medicine and Biology Society, EMBS).
@inproceedings{d9650a4b69a24ce7b247516a93551107,
title = "Missing data imputation for remote CHF patient monitoring systems",
abstract = "Congestive heart failure (CHF) is a leading cause of death in the United States. WANDA is a wireless health project that leverages sensor technology and wireless communication to monitor the health status of patients with CHF. The first pilot study of WANDA showed the system's effectiveness for patients with CHF. However, WANDA experienced a considerable amount of missing data due to system misuse, nonuse, and failure. Missing data is highly undesirable as automated alarms may fail to notify healthcare professionals of potentially dangerous patient conditions. In this study, we exploit machine learning techniques including projection adjustment by contribution estimation regression (PACE), Bayesian methods, and voting feature interval (VFI) algorithms to predict both non-binomial and binomial data. The experimental results show that the aforementioned algorithms are superior to other methods with high accuracy and recall. This approach also shows an improved ability to predict missing data when training on entire populations, as opposed to training unique classifiers for each individual.",
author = "Suh, {Myung Kyung} and Jonathan Woodbridge and Mars Lan and Alex Bui and Lorraine Evangelista and Majid Sarrafzadeh",
year = "2011",
month = "12",
day = "26",
doi = "10.1109/IEMBS.2011.6090867",
language = "English (US)",
isbn = "9781424441211",
series = "Proceedings of the Annual International Conference of the IEEE Engineering in Medicine and Biology Society, EMBS",
pages = "3184--3187",
booktitle = "33rd Annual International Conference of the IEEE Engineering in Medicine and Biology Society, EMBS 2011",

}

TY - GEN

T1 - Missing data imputation for remote CHF patient monitoring systems

AU - Suh, Myung Kyung

AU - Woodbridge, Jonathan

AU - Lan, Mars

AU - Bui, Alex

AU - Evangelista, Lorraine

AU - Sarrafzadeh, Majid

PY - 2011/12/26

Y1 - 2011/12/26

N2 - Congestive heart failure (CHF) is a leading cause of death in the United States. WANDA is a wireless health project that leverages sensor technology and wireless communication to monitor the health status of patients with CHF. The first pilot study of WANDA showed the system's effectiveness for patients with CHF. However, WANDA experienced a considerable amount of missing data due to system misuse, nonuse, and failure. Missing data is highly undesirable as automated alarms may fail to notify healthcare professionals of potentially dangerous patient conditions. In this study, we exploit machine learning techniques including projection adjustment by contribution estimation regression (PACE), Bayesian methods, and voting feature interval (VFI) algorithms to predict both non-binomial and binomial data. The experimental results show that the aforementioned algorithms are superior to other methods with high accuracy and recall. This approach also shows an improved ability to predict missing data when training on entire populations, as opposed to training unique classifiers for each individual.

AB - Congestive heart failure (CHF) is a leading cause of death in the United States. WANDA is a wireless health project that leverages sensor technology and wireless communication to monitor the health status of patients with CHF. The first pilot study of WANDA showed the system's effectiveness for patients with CHF. However, WANDA experienced a considerable amount of missing data due to system misuse, nonuse, and failure. Missing data is highly undesirable as automated alarms may fail to notify healthcare professionals of potentially dangerous patient conditions. In this study, we exploit machine learning techniques including projection adjustment by contribution estimation regression (PACE), Bayesian methods, and voting feature interval (VFI) algorithms to predict both non-binomial and binomial data. The experimental results show that the aforementioned algorithms are superior to other methods with high accuracy and recall. This approach also shows an improved ability to predict missing data when training on entire populations, as opposed to training unique classifiers for each individual.

UR - http://www.scopus.com/inward/record.url?scp=84862606671&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=84862606671&partnerID=8YFLogxK

U2 - 10.1109/IEMBS.2011.6090867

DO - 10.1109/IEMBS.2011.6090867

M3 - Conference contribution

C2 - 22255016

AN - SCOPUS:84862606671

SN - 9781424441211

T3 - Proceedings of the Annual International Conference of the IEEE Engineering in Medicine and Biology Society, EMBS

SP - 3184

EP - 3187

BT - 33rd Annual International Conference of the IEEE Engineering in Medicine and Biology Society, EMBS 2011

ER -