You are here

Article Text

Article menu

Download PDFPDF

XML
Health services research
Original research
Can clinical audits be enhanced by pathway simulation and machine learning? An example from the acute stroke pathway
  1. Michael Allen1,
  2. Kerry Pearn1,
  3. Thomas Monks2,
  4. Benjamin D Bray3,
  5. Richard Everson4,
  6. Andrew Salmon1,
  7. Martin James5,
  8. Ken Stein1
  1. 1 Medical School, University of Exeter, Exeter, UK
  2. 2 University of Southampton, Southampton, UK
  3. 3 Public Health, Royal College Physicians, London, UK
  4. 4 Computer Sciences, University of Exeter, Exeter, UK
  5. 5 Stroke Consultant, Royal Devon & Exeter NHS Trust, Exeter, UK
  1. Correspondence to Dr Michael Allen; M.Allen{at}exeter.ac.uk

Abstract

Objective To evaluate the application of clinical pathway simulation in machine learning, using clinical audit data, in order to identify key drivers for improving use and speed of thrombolysis at individual hospitals.

Design Computer simulation modelling and machine learning.

Setting Seven acute stroke units.

Participants Anonymised clinical audit data for 7864 patients.

Results Three factors were pivotal in governing thrombolysis use: (1) the proportion of patients with a known stroke onset time (range 44%–73%), (2) pathway speed (for patients arriving within 4 hours of onset: per-hospital median arrival-to-scan ranged from 11 to 56 min; median scan-to-thrombolysis ranged from 21 to 44 min) and (3) predisposition to use thrombolysis (thrombolysis use ranged from 31% to 52% for patients with stroke scanned with 30 min left to administer thrombolysis). A pathway simulation model could predict the potential benefit of improving individual stages of the clinical pathway speed, whereas a machine learning model could predict the benefit of ‘exporting’ clinical decision making from one hospital to another, while allowing for differences in patient population between hospitals. By applying pathway simulation and machine learning together, we found a realistic ceiling of 15%–25% use of thrombolysis across different hospitals and, in the seven hospitals studied, a realistic opportunity to double the number of patients with no significant disability that may be attributed to thrombolysis.

Conclusions National clinical audit may be enhanced by a combination of pathway simulation and machine learning, which best allows for an understanding of key levers for improvement in hyperacute stroke pathways, allowing for differences between local patient populations. These models, based on standard clinical audit data, may be applied at scale while providing results at individual hospital level. The models facilitate understanding of variation and levers for improvement in stroke pathways, and help set realistic targets tailored to local populations.

  • Stroke
  • thrombolysis
  • alteplase
  • simulation
  • machine learning
  • health services research

This is an open access article distributed in accordance with the Creative Commons Attribution 4.0 Unported (CC BY 4.0) license, which permits others to copy, redistribute, remix, transform and build upon this work for any purpose, provided the original work is properly cited, a link to the licence is given, and indication of whether changes were made. See: https://creativecommons.org/licenses/by/4.0/.

https://doi.org/10.1136/bmjopen-2018-028296

Statistics from Altmetric.com

    Request Permissions

    If you wish to reuse any or all of this article please use the link below which will take you to the Copyright Clearance Center’s RightsLink service. You will be able to get a quick price and instant permission to reuse the content in many different ways.

    View Full Text

    Footnotes

    • Contributors MA, KP, MJ and KS conceived the study. RE reviewed and provided guidance on the machine learning aspects. TM and KP reviewed and provided guidance on the simulation aspects. AS conducted literature reviews and provided guidance on methodologies. MA wrote the algorithm code used in this study and performed the primary analysis. MJ and BDB informed the base assumptions of the model, provided key literature and reviewed the output. MA produced the first draft of the paper, and all authors contributed significant editing to the paper. KS oversaw all stages of the project. KS is the guarantor.

    • Funding This study was jointly funded by the National Institute for Health Research (NIHR) Collaboration for Leadership in Applied Health Research and Care for the South West Peninsula, and the South West Academic Health Science Network.

    • Disclaimer The views and opinions expressed in this paper are those of the authors, and not necessarily those of the NHS, the National Institute for Health Research or the Department of Health.

    • Competing interests None declared.

    • Patient consent for publication Not required.

    • Ethics approval This study used anonymous secondary patient data only, collected as part of routine care audit. The study was conducted as part of a local service evaluation and improvement exercise sponsored by the South West Strategic Clinical Network. There was no access to patient identifiable information, no collecting of primary data, and no patient care was altered during the process of this study. There was no patient enrolment into the study. A decision that no formal ethical approval was needed was made by the project steering group with representation from the South West Strategic Clinical Network, the National Institute for Health Research (NIHR) Collaboration for Leadership in Applied Health Research and Care for the South West Peninsula, and the South West Academic Health Science Network.

    • Provenance and peer review Not commissioned; externally peer reviewed.

    • Data availability statement Data are available in a public, open access repository.