Article Text

PDF
Costs and consequences of automated algorithms versus manual grading for the detection of referable diabetic retinopathy
  1. G S Scotland1,
  2. P McNamee1,
  3. A D Fleming2,
  4. K A Goatman2,
  5. S Philip3,
  6. G J Prescott4,
  7. P F Sharp2,
  8. G J Williams5,
  9. W Wykes6,
  10. G P Leese7,
  11. J A Olson3
  12. on behalf of the Scottish Diabetic Retinopathy Clinical Research Network
  1. 1Health Economics Research Unit, University of Aberdeen, Foresterhill, Aberdeen, UK
  2. 2Biomedical Physics, University of Aberdeen, Foresterhill, Aberdeen, UK
  3. 3Diabetes Retinal Screening Service, David Anderson Building, Foresterhill, Aberdeen, UK
  4. 4Section of Population Health, University of Aberdeen, Foresterhill, Aberdeen, UK
  5. 5Department of Ophthalmology, MacQuaker Building, Glasgow, Lanarkshire, UK
  6. 6Department of Ophthalmology, Southern General Hospital, Glasgow, UK
  7. 7Department of Diabetes, Ninewells Hospital, Dundee, UK
  1. Correspondence to Mr G S Scotland, Health Economics Research Unit, University of Aberdeen, Polwarth Building, Foresterhill, Aberdeen AB25 2ZD, UK; g.scotland{at}abdn.ac.uk

Abstract

Aims To assess the cost-effectiveness of an improved automated grading algorithm for diabetic retinopathy against a previously described algorithm, and in comparison with manual grading.

Methods Efficacy of the alternative algorithms was assessed using a reference graded set of images from three screening centres in Scotland (1253 cases with observable/referable retinopathy and 6333 individuals with mild or no retinopathy). Screening outcomes and grading and diagnosis costs were modelled for a cohort of 180 000 people, with prevalence of referable retinopathy at 4%. Algorithm (b), which combines image quality assessment with detection algorithms for microaneurysms (MA), blot haemorrhages and exudates, was compared with a simpler algorithm (a) (using image quality assessment and MA/dot haemorrhage (DH) detection), and the current practice of manual grading.

Results Compared with algorithm (a), algorithm (b) would identify an additional 113 cases of referable retinopathy for an incremental cost of £68 per additional case. Compared with manual grading, automated grading would be expected to identify between 54 and 123 fewer referable cases, for a grading cost saving between £3834 and £1727 per case missed. Extrapolation modelling over a 20-year time horizon suggests manual grading would cost between £25 676 and £267 115 per additional quality adjusted life year gained.

Conclusions Algorithm (b) is more cost-effective than the algorithm based on quality assessment and MA/DH detection. With respect to the value of introducing automated detection systems into screening programmes, automated grading operates within the recommended national standards in Scotland and is likely to be considered a cost-effective alternative to manual disease/no disease grading.

  • Diabetic retinopathy
  • automated grading
  • cost-effectiveness
  • retina
  • public health
  • imaging
  • patient preferences

Statistics from Altmetric.com

Footnotes

  • Linked articles 149807.

  • Scottish Diabetic Retinopathy Clinical Research Network: NHS Grampian/University of Aberdeen (Alan D Fleming, Keith A Goatman, John A Olson, Sam Philip, Gordon Prescott, Paul McNamee, Graham S Scotland, Peter F Sharp, Graeme J Williams); NHS Greater Glasgow (William Wykes); NHS Lanarkshire (Meena Virdi); NHS Lothian (Ken Swa); NHS Tayside (Graeme Leese).

  • Guarantor: Graham Scotland.

  • Funding This study was funded by the Chief Scientist Office of the Scottish Governments Health Directorates (SGHD). The views expressed here are those of the authors and not necessarily those of the SGHD.

  • Competing interests Implementation in Scotland is being considered. If this occurs it is likely that there will be some remuneration for the University of Aberdeen, NHS Grampian and the Scottish Executive.

  • Ethics approval The North of Scotland Research Ethics Committee confirmed that a formal ethics application was not required for this study based on anonymised routine data.

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

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.

Linked Articles