University of Hertfordshire

A Grid implementation for profiling hospitals based on patient readmissions

Research output: Chapter in Book/Report/Conference proceedingChapter (peer-reviewed)

Standard

A Grid implementation for profiling hospitals based on patient readmissions. / Demir, Eren; Chaussalet, Thierry J.; Weingarten, Noam; Kiss, Tamas.

Intelligent Patient Management. ed. / S. McClean; P. Millard; E. El-Darzi; C. D. Nugent. Springer, 2009. p. 127-146 (Studies in Computational Intelligence; Vol. 189).

Research output: Chapter in Book/Report/Conference proceedingChapter (peer-reviewed)

Harvard

Demir, E, Chaussalet, TJ, Weingarten, N & Kiss, T 2009, A Grid implementation for profiling hospitals based on patient readmissions. in S McClean, P Millard, E El-Darzi & CD Nugent (eds), Intelligent Patient Management. Studies in Computational Intelligence, vol. 189, Springer, pp. 127-146.

APA

Demir, E., Chaussalet, T. J., Weingarten, N., & Kiss, T. (2009). A Grid implementation for profiling hospitals based on patient readmissions. In S. McClean, P. Millard, E. El-Darzi, & C. D. Nugent (Eds.), Intelligent Patient Management (pp. 127-146). (Studies in Computational Intelligence; Vol. 189). Springer.

Vancouver

Demir E, Chaussalet TJ, Weingarten N, Kiss T. A Grid implementation for profiling hospitals based on patient readmissions. In McClean S, Millard P, El-Darzi E, Nugent CD, editors, Intelligent Patient Management. Springer. 2009. p. 127-146. (Studies in Computational Intelligence).

Author

Demir, Eren ; Chaussalet, Thierry J. ; Weingarten, Noam ; Kiss, Tamas. / A Grid implementation for profiling hospitals based on patient readmissions. Intelligent Patient Management. editor / S. McClean ; P. Millard ; E. El-Darzi ; C. D. Nugent. Springer, 2009. pp. 127-146 (Studies in Computational Intelligence).

Bibtex

@inbook{045baa235ec74d16841c45af3d60539b,
title = "A Grid implementation for profiling hospitals based on patient readmissions",
abstract = "Generally, high level of readmission is associated with poor patient care, hence, its relation to the quality of care is plausible. Frequent patient readmissions have personal, financial and organisational consequences. This has motivated healthcare commissioners in England to use emergency readmission as an indicator in the performance rating framework. A statistical model, known as the multilevel transition model was previously developed, where individual hospitals propensity for first readmission, second readmission, third (and so on) were con-sidered to be measures of performance. Using these measures, we defined a new performance index. During the period 1997 and 2004, the national (England) hos-pital episodes statistics dataset comprise more than 5 million patient readmissions. Implementing a statistical model using the complete population dataset could possibly take weeks to estimate the parameters. Moreover, it is not statistically sound to utilise the full population dataset. To resolve the problem, we extract 1000 random samples from the original data, where each random sample is likely to lead to differing hospital performance measures. For computational efficiency a Grid implementation of the model is developed. Using a stand-alone computer, it took approximately 500 hours to estimate 1000 samples, whereas in the Grid implementation, the full 1000 samples were analysed in less than 24 hours. From the 167 National Health Service Acute and Foundation Trusts in England, 4 out of the 5 worst performing hospitals treating cancer patients were in London.",
author = "Eren Demir and Chaussalet, {Thierry J.} and Noam Weingarten and Tamas Kiss",
year = "2009",
language = "English",
isbn = "978-3-642-00178-9",
series = "Studies in Computational Intelligence",
publisher = "Springer",
pages = "127--146",
editor = "S. McClean and P. Millard and E. El-Darzi and Nugent, {C. D.}",
booktitle = "Intelligent Patient Management",

}

RIS

TY - CHAP

T1 - A Grid implementation for profiling hospitals based on patient readmissions

AU - Demir, Eren

AU - Chaussalet, Thierry J.

AU - Weingarten, Noam

AU - Kiss, Tamas

PY - 2009

Y1 - 2009

N2 - Generally, high level of readmission is associated with poor patient care, hence, its relation to the quality of care is plausible. Frequent patient readmissions have personal, financial and organisational consequences. This has motivated healthcare commissioners in England to use emergency readmission as an indicator in the performance rating framework. A statistical model, known as the multilevel transition model was previously developed, where individual hospitals propensity for first readmission, second readmission, third (and so on) were con-sidered to be measures of performance. Using these measures, we defined a new performance index. During the period 1997 and 2004, the national (England) hos-pital episodes statistics dataset comprise more than 5 million patient readmissions. Implementing a statistical model using the complete population dataset could possibly take weeks to estimate the parameters. Moreover, it is not statistically sound to utilise the full population dataset. To resolve the problem, we extract 1000 random samples from the original data, where each random sample is likely to lead to differing hospital performance measures. For computational efficiency a Grid implementation of the model is developed. Using a stand-alone computer, it took approximately 500 hours to estimate 1000 samples, whereas in the Grid implementation, the full 1000 samples were analysed in less than 24 hours. From the 167 National Health Service Acute and Foundation Trusts in England, 4 out of the 5 worst performing hospitals treating cancer patients were in London.

AB - Generally, high level of readmission is associated with poor patient care, hence, its relation to the quality of care is plausible. Frequent patient readmissions have personal, financial and organisational consequences. This has motivated healthcare commissioners in England to use emergency readmission as an indicator in the performance rating framework. A statistical model, known as the multilevel transition model was previously developed, where individual hospitals propensity for first readmission, second readmission, third (and so on) were con-sidered to be measures of performance. Using these measures, we defined a new performance index. During the period 1997 and 2004, the national (England) hos-pital episodes statistics dataset comprise more than 5 million patient readmissions. Implementing a statistical model using the complete population dataset could possibly take weeks to estimate the parameters. Moreover, it is not statistically sound to utilise the full population dataset. To resolve the problem, we extract 1000 random samples from the original data, where each random sample is likely to lead to differing hospital performance measures. For computational efficiency a Grid implementation of the model is developed. Using a stand-alone computer, it took approximately 500 hours to estimate 1000 samples, whereas in the Grid implementation, the full 1000 samples were analysed in less than 24 hours. From the 167 National Health Service Acute and Foundation Trusts in England, 4 out of the 5 worst performing hospitals treating cancer patients were in London.

M3 - Chapter (peer-reviewed)

SN - 978-3-642-00178-9

T3 - Studies in Computational Intelligence

SP - 127

EP - 146

BT - Intelligent Patient Management

A2 - McClean, S.

A2 - Millard, P.

A2 - El-Darzi, E.

A2 - Nugent, C. D.

PB - Springer

ER -