Predicting asthma-related hospitalizations and deaths using routine electronic healthcare data: a quantitative database analysis study

Michael J Noble, Annie Burden, Susan Stirling, Allan B Clark, Stanley D. Musgrave, Mohammad A Alsallakh, David Price, Gwyneth A Davies, Hilary Pinnock, Martin Pond, Aziz Sheikh, Erika J Sims, Samantha Walker, Andrew M Wilson

Research output: Contribution to journalArticlepeer-review

8 Citations (Scopus)
9 Downloads (Pure)

Abstract

Background: There is no published algorithm predicting asthma crisis events (Accident and Emergency (A&E) attendance, hospitalisation or death) using routinely available electronic health record (EHR) data. Aim: To develop an algorithm to identify individuals at high risk of an asthma crisis event.Design and Setting: Database analysis from primary care EHRs.Method: Multivariable logistic regression was applied to a dataset of 61,861 peoplewith asthma from England and Scotland using the Clinical Practice Research Datalink. External validation was performed using the Secure Anonymised Information Linkage databank of 174,240 patients from Wales. Outcomes were one or more hospitalisation (development dataset) and asthma-related hospitalisation, A&E attendance or death (validation dataset) within a 12-month period.Results: Risk factors for asthma-related crisis events included previous hospitalisation, older age, underweight, smoking and blood eosinophilia. The prediction algorithm had acceptable predictive ability with a Receiver Operating Characteristic (ROC) of 0.71 (0.70, 0.72) in the validation dataset. Using a cut-point based on the 7% of the population at greatest risk results in a positive predictivevalue of 5.7% (95% CI 5.3 – 6.1) and a negative predictive value of 98.9% (98.9 –99.0), with sensitivity of 28.5% (26.7 – 30.3) and specificity of 93.3% (93.2 – 93.4); they had an event risk of 6.0% compared 1.1% for the remaining population. Eighteen people would be “needed to follow” to identify one admission.Conclusions: This externally validated algorithm has acceptable predictive ability foridentifying patients at high risk of asthma-related crisis events and excluding individuals not at high risk.
Original languageEnglish
Pages (from-to)e948-e957
Number of pages10
JournalBritish Journal of General Practice
Volume71
Issue number713
Early online date25 Nov 2021
DOIs
Publication statusPublished - Dec 2021

Bibliographical note

Acknowledgements
The authors would like to thank Derek Skinner, of the Observational & Pragmatic Research Institute, for his support in analytical dataset generation and statistical analyses. We would like to acknowledge the support of the Asthma UK Centre for Applied Research for its help with this study.
Funding
The Dataset and Statistical Analyses for the derivation of the algorithm was funded and delivered by the Observational & Pragmatic Research Institute (OPRI). This paper presents independent research funded by the National Institute for Health Research (NIHR) under its Health Technology Assessment (HTA) programme (Grant reference number 13/34/70). The views expressed are those of the author(s) and not necessarily those of the NHS, the NIHR or the Department of Health.

Keywords

  • Asthma
  • asthma attack
  • risk
  • prediction
  • Algorithm

Fingerprint

Dive into the research topics of 'Predicting asthma-related hospitalizations and deaths using routine electronic healthcare data: a quantitative database analysis study'. Together they form a unique fingerprint.

Cite this