Article Text

other Versions

Costs and consequences of automated algorithms versus manual grading for the detection of referable diabetic retinopathy
  1. Graham S Scotland1,*,
  2. Paul McNamee1,
  3. Alan D Fleming2,
  4. Keith A Goatman2,
  5. Sam Philip3,
  6. Gordon J Prescott4,
  7. Peter F Sharp3,
  8. Graeme J Williams5,
  9. William Wykes6,
  10. Graham P Leese7,
  11. John Alexander Olson8
  1. 1 Health Economics Research Unit, University of Aberdeen, United Kingdom;
  2. 2 Department of Biomedical Physics, University of Aberdeen, United Kingdom;
  3. 3 University of Aberdeen, United Kingdom;
  4. 4 Section of Population Health, University of Aberdeen, United Kingdom;
  5. 5 Aberdeen Royal Infirmary, United Kingdom;
  6. 6 Chairman DRS clinical and grading group, United Kingdom;
  7. 7 Tayside Health Board, United Kingdom;
  8. 8 Grampian University Hospitals NHS Trust, United Kingdom
  1. Correspondence to: Graham S Scotland, Health Economics Research Unit, University of Aberdeen, Polwarth Building, Foresterhill, Aberdeen, AB25 2ZD, United Kingdom; g.scotland{at}


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 6,333 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) (utilising 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 £3,834 and £1,727 per case missed. Extrapolation modelling over a 20 year time horizon suggests manual grading would cost between £29,111 and £289,917 per additional quality adjusted life year (QALY) 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.

Statistics from


    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