Development of risk models for the prediction of new or worsening acute kidney injury on or during hospital admission: a cohort and nested study

Journal article


Bedford, M., Stevens, P., Coulton, S., Billings, J., Farr, M., Wheeler, T., Kalli, M., Mottishaw, T. and Farmer, C. 2016. Development of risk models for the prediction of new or worsening acute kidney injury on or during hospital admission: a cohort and nested study. Health Service Delivery Research. 4 (6). https://doi.org/10.3310/hsdr04060
AuthorsBedford, M., Stevens, P., Coulton, S., Billings, J., Farr, M., Wheeler, T., Kalli, M., Mottishaw, T. and Farmer, C.
Abstract

Background: Acute kidney injury (AKI) is a common clinical problem with significant morbidity and mortality. All hospitalised patients are at risk. AKI is often preventable and reversible; however, the 2009 National Confidential Enquiry into Patient Outcome and Death highlighted systematic failings of identification and management, and recommended risk assessment of all emergency admissions.

Objectives: To develop three predictive models to stratify the risk of (1) AKI on arrival in hospital;
(2) developing AKI during admission; and (3) worsening AKI if already present; and also to (4) develop a clinical algorithm for patients admitted to hospital and explore effective methods of delivery of this information at the point of care.

Study design: Quantitative methodology (1) to formulate predictive risk models and (2) to validate the models in both our population and a second population. Qualitative methodology to plan clinical decision support system (CDSS) development and effective integration into clinical care.

Data analysis: Quantitative – both traditional and Bayesian regression methods were used. Traditional methods were performed using ordinal logistic regression with univariable analyses to inform the development of multivariable analyses. Backwards selection was used to retain only statistically significant variables in the final models. The models were validated using actual and predicted probabilities, an area under the receiver operating characteristic (AUROC) curve analysis and the Hosmer–Lemeshow test. Qualitative – content analysis was employed.

Year2016
JournalHealth Service Delivery Research
Journal citation4 (6)
PublisherNational Institute of Health Research
ISSN2050-4349
Digital Object Identifier (DOI)https://doi.org/10.3310/hsdr04060
Official URLhttps://www.ncbi.nlm.nih.gov/books/NBK344211/pdf/Bookshelf_NBK344211.pdf
FunderNIHR
Publication dates
Print23 Feb 2016
Publication process dates
Deposited26 Jan 2017
Accepted author manuscript
Output statusPublished
Permalink -

https://repository.canterbury.ac.uk/item/880qw/development-of-risk-models-for-the-prediction-of-new-or-worsening-acute-kidney-injury-on-or-during-hospital-admission-a-cohort-and-nested-study

Download files


Accepted author manuscript
  • 24
    total views
  • 32
    total downloads
  • 2
    views this month
  • 0
    downloads this month

Export as

Related outputs

Flexible modeling of dependence in volatility processes
Kalli, M. and Griffin, J. 2015. Flexible modeling of dependence in volatility processes. Journal of Business and Economic Statistics. 33 (1), pp. 102-113. https://doi.org/10.1080/07350015.2014.925457
Time-varying sparsity in dynamic regression models
Kalli, M. and Griffin, J. 2014. Time-varying sparsity in dynamic regression models. Journal of Econometrics. 178 (2), pp. 779-793. https://doi.org/10.1016/j.jeconom.2013.10.012
Modelling the conditional distribution of daily stock index returns: an alternative Bayesian semiparametric model
Kalli, M., Damien, P. and Walker, S. 2013. Modelling the conditional distribution of daily stock index returns: an alternative Bayesian semiparametric model. Journal of Business and Economic Statistics. 31 (4). https://doi.org/10.1080/07350015.2013.794142
Provision of specialist education for haemophilia nurses
Bedford, M. and Vidler, V. 2000. Provision of specialist education for haemophilia nurses.
Examination of an appropriate model to guide haemophilia nursing care
Bedford, M., Wakelen, D. and Winter, M. 2000. Examination of an appropriate model to guide haemophilia nursing care.
Narrating Glanzmann’s
Bedford, M. 2000. Narrating Glanzmann’s.
Going electronic - updating the competency framework for nurses caring for patients with haemophilia and related disorders
Bedford, M., Khair, K. and Lawrence, K. 2010. Going electronic - updating the competency framework for nurses caring for patients with haemophilia and related disorders. Haemophilia. 16 (s4), pp. 1-158. https://doi.org/10.1111/j.1365-2516.2010.02283.x
Slice sampling mixture models
Kalli, M., Griffin, J. and Walker, S. 2011. Slice sampling mixture models. Statistics and Computing. 21 (1), pp. 93-105. https://doi.org/10.1007/s11222-009-9150-y