Comparison of 21 artificial intelligence algorithms in automated diabetic retinopathy screening using handheld fundus camera.

BACKGROUND: Diabetic retinopathy (DR) is a common complication of diabetes and may lead to irreversible visual loss. Efficient screening and improved treatment of both diabetes and DR have amended visual prognosis for DR. The number of patients with diabetes is increasing and telemedicine, mobile handheld devices and automated solutions may alleviate the burden for healthcare. We compared the performance of 21 artificial intelligence (AI) algorithms for referable DR screening in datasets taken by handheld Optomed Aurora fundus camera in a real-world setting. PATIENTS AND METHODS: Prospective study of 156 patients (312 eyes) attending DR screening and follow-up. Both papilla- and macula-centred 50° fundus images were taken from each eye. DR was graded by experienced ophthalmologists and 21 AI algorithms. RESULTS: Most eyes, 183 out of 312 (58.7%), had no DR and mild NPDR was noted in 21 (6.7%) of the eyes. Moderate NPDR was detected in 66 (21.2%) of the eyes, severe NPDR in 1 (0.3%), and PDR in 41 (13.1%) composing a group of 34.6% of eyes with referable DR. The AI algorithms achieved a mean agreement of 79.4% for referable DR, but the results varied from 49.4% to 92.3%. The mean sensitivity for referable DR was 77.5% (95% CI 69.1-85.8) and specificity 80.6% (95% CI 72.1-89.2). The rate for images ungradable by AI varied from 0% to 28.2% (mean 1.9%). Nineteen out of 21 (90.5%) AI algorithms resulted in grading for DR at least in 98% of the images. CONCLUSIONS: Fundus images captured with Optomed Aurora were suitable for DR screening. The performance of the AI algorithms varied considerably emphasizing the need for external validation of screening algorithms in real-world settings before their clinical application.

What is already known on this topic? Diabetic retinopathy (DR) is a common complication of diabetes. Efficient screening and timely treatment are important to avoid the development of sight-threatening DR. The increasing number of patients with diabetes and DR poses a challenge for healthcare.What this study adds? Telemedicine, mobile handheld devices and artificial intelligence (AI)-based automated algorithms are likely to alleviate the burden by improving efficacy of DR screening programs. Reliable algorithms of high quality exist despite the variability between the solutions.How this study might affect research, practice or policy? AI algorithms improve the efficacy of screening and might be implemented to clinical use after thorough validation in a real-life setting.

Handheld fundus camera performance, image quality and outcomes of diabetic retinopathy grading in a pilot screening study.

PURPOSE: To compare the performance and image quality of the handheld fundus camera to standard table-top fundus cameras in diabetic retinopathy (DR) screening. The reliability and diagnostic accuracy of DR grading performed by an ophthalmologist and a photographer reader were evaluated. MATERIALS AND METHODS: 157 patients with diabetes, attending screening or follow-up of DR, were evaluated by fundus photographs taken in mydriasis by Optomed Aurora and Canon or Zeiss Visucam fundus cameras. The image quality and the severity of DR were evaluated independently by an ophthalmologist and experienced photographer. The sensitivity, specificity and reliability of the assessments were determined. RESULTS: 1884 fundus images from 314 eyes were analysed. In 53% of all eyes, DR was not present. 10% had mild non-proliferative diabetic retinopathy (NPDR), 16% moderate NPDR, 6% severe NPDR and 16% proliferative diabetic retinopathy (PDR). The DR grading outcomes by Aurora highly equalled to those of Canon or Zeiss (κ = 0.93, 95% CI 0.91 to 0.94), and there was almost perfect agreement in grading between the ophthalmologist and photographer (κ = 0.96, 95% CI 0.95 to 0.97). The image quality of Aurora was sufficient for reliable assessment according to both graders in 84-88% of the cases. CONCLUSION: The Optomed Aurora fundus camera seems appropriate for DR screening. The sufficient image quality and high diagnostic accuracy for DR grading are supportive for a less expensive and easily transportable screening system for DR. Immediate image grading carried out by a photographer would further improve and speed up the screening process in all settings.

Health-related quality of life of Finnish patients with diabetes.

AIMS: This study evaluated the influence of diabetes on the health-related quality of life (HRQoL) scores of adult patients with diabetes in northern Finland. METHODS: A total of 3771 patients of the population of 10,264 patients aged ⩾15 years with the right for reimbursement of the cost of diabetes medication attended fundus photography screening for retinopathy in 2012. The 15D HRQoL scores and data on age, sex, type and duration of diabetes were gathered concurrently. The results were compared with the 15D scores reported in Finnish population studies. RESULTS: The 15D score was obtained from 2461 patients aged 60±14 years; 20% had type 1 diabetes (T1D). The mean±SD 15D index was 0.930±0.079 in patients with T1D and their mean±SD age was 46±15 years. The mean±SD 15D index of the patients with type 2 diabetes (T2D) was 0.890±0.100 and their mean±SD age was 63±11 years. The 15D index was no lower than in the Finnish general population in either patient group or in any age group. However, the 15D score was negatively influenced by an increasing duration of diabetes in both patients with T1D and patients with T2D. No sex difference was found. CONCLUSIONS: The mean HRQoL score of patients with diabetes in this study is comparable with that of the general population of equal age. Neither the type of diabetes nor sex independently affected the HRQoL score, but a longer duration of diabetes seemed to impair the HRQoL score. Current diabetes care appears to maintain a normal HRQoL score in this diabetic population in Finland.

Marked reductions in visual impairment due to diabetic retinopathy achieved by efficient screening and timely treatment.

PURPOSE: Diabetic retinopathy (DR) is the most common complication of diabetes and needs to be diagnosed early to prevent severe sight-threatening retinopathy. Digital photography with telemedicine connections is a novel way to deliver cost-effective, accessible screening to remote areas. Screening for DR in a mobile eye examination unit (EyeMo) is compared to traditional service models (i.e. local municipal services or a commercial service provider). The quality of images, delays from screening to treatment, the stage of DR, coverage of screening and the rate of visual impairment due to DR are evaluated. METHODS: EyeMo utilizes telemedicine technology. The electronic databases of the hospital and information from the Finnish Register of Visual Impairment were used to determine delays and the rate of visual impairment. RESULTS: Fourteen thousand eight hundred and sixty-six fundus photographs were taken in EyeMo in 2007-2011. Coverage reached 78% of potential clients. No DR was detected in 43%, mild background retinopathy in 23%, moderate or severe background retinopathy in 31% and proliferative retinopathy in 3% of the evaluations. The quality of images was higher (p < 0.01) and delays shorter (p < 0.01) in EyeMo as compared to traditional service models. The rate of visual impairment due to DR decreased by 86% in the area covered by EyeMo, and the change compared favourably to the situation in the entire Finland (p < 0.0005). CONCLUSION: EyeMo is a feasible model of telemedicine application for screening of DR. Effective screening and timely access to care may indeed have influenced the reduced rate of visual damage.