Evaluation of a System for Automatic Detection of Diabetic Retinopathy From Color Fundus Photographs in a Large Population of Patients With Diabetes
Response to Olson et al.
- Michael D. Abràmoff, MD, PHD1,2,3,
- Meindert Niemeijer, PHD3,
- Maria S.A. Suttorp-Schulten, MD, PHD4,
- Max A. Viergever, PHD5,
- Stephen R. Russell, MD1,2 and
- Bram van Ginneken, PHD5
- 1Retina Service, Department of Ophthalmology and Visual Sciences, University of Iowa Hospitals and Clinics, Iowa City, Iowa
- 2Department of Veterans Affairs, Iowa City VA Medical Center, Iowa City, Iowa
- 3Department of Electrical and Computer Engineering, University of Iowa, Iowa City, Iowa
- 4Ophthalmology Service, Onze Lieve Vrouwe Gasthuis (OLVG), Amsterdam, the Netherlands
- 5Image Sciences Institute, University Medical Center Utrecht, Utrecht, the Netherlands
- Corresponding author: Michael D. Abràmoff, michael-abramoff{at}uiowa.edu
We thank Olson et al. (1) for their close reading of our recent study (2), where we examined sensitivity and specificity of automated diabetic retinopathy detection and demonstrated an area under the receiver operating characteristic curve of 0.87. A limited, 500-patient sample of all 10,000 photographic exams was examined by multiple, masked experts. We felt uncomfortable recommending a system for clinical practice for which patient safety compared to an accepted (gold) standard could not be established, concluding that it should be tested against widely accepted clinical standards, if practical. We have recently presented studies of an improved algorithm on a new, larger dataset of 15,000 exams with an area under the curve of 0.90 …
