Subscribe to RSS
DOI: 10.1055/a-1484-9678
Evaluation der Implementierung eines zugelassenen Künstliche-Intelligenz-Systems zur Erkennung der diabetischen Retinopathie
Evaluation of the implementation of an approved artificial intelligence system for the detection of diabetic retinopathy
Zusammenfassung
Einleitung Ziel der Studie war die Evaluation der Genauigkeit einer auf einem Künstliche-Intelligenz-System (KI) basierenden Bewertung von Fundusfotografien im Vergleich zum Augenarzt in Bezug auf das diabetische Retinopathie-Screening in einer internistisch geführten Klinik. Zudem erfolgte die Erhebung der Gesamtuntersuchungsdauer wie auch der Patienten- und Untersucherzufriedenheit.
Methoden Im Rahmen der Studie erhielten 112 ambulante Patienten eine Fundusfotografie mit automatisierter Diagnose der diabetischen Retinopathie (DR) über das IDx-DR-System (Digital Diagnostics). Die Aufnahmen erfolgten mit der Kamera Topcon TRC-NW400 (Topcon Corp. Japan). Einschlusskriterium war die Diagnose eines Diabetes mellitus Typ 1, 2 oder 3. Bei Patienten, bei denen keine Aufnahme mit ausreichender Qualität in Miosis durchgeführt werden konnte, erfolgte die Aufnahme in Mydriasis.
Ergebnisse Von 112 Patienten konnte bei 107 Patienten (95,5 %) durch das Grading mittels IDx-DR, anhand der Fundusaufnahmen, eine Analyse durchgeführt werden – vs. bei 103 Patienten (91,9 %) durch das Grading derselben, hochauflösenden Fundusaufnahmen durch Augenärzte. Bei den verbleibenden Patienten war eine Beurteilung allein durch die Funduskopie in Mydriasis möglich. Es zeigte sich eine hochsignifikante Korrelation bezüglich der Einschätzung der Schwere der diabetischen Retinopathie zwischen Untersucher und dem IDx-DR-System (Correlation coefficient (r) = 0,8738; p < 0,0001). Die Patientenzufriedenheit lag bei 4,5 ± 0,6 [1–5], die Gesamtdauer der Untersuchung in Miosis lag im Mittel bei 3:04 ± 0:28 [min:sek].
Schlussfolgerung Das Retinopathiescreening mittels IDx-DR ermöglicht die automatisierte, zeitnahe und zuverlässige Beurteilung bzgl. des Vorliegens einer diabetischen Retinopathie mit einem robusten technischen und klinischen Arbeitsfluss, der mit einer hohen Patientenzufriedenheit einhergeht.
Abstract
Introduction The aim of this study was to evaluate the accuracy of an artificial intelligence (AI)-based analysis of fundus photographs compared to ophthalmologists in diabetic retinopathy screening in an internal medicine clinic. In addition, the total examination time as well as the patient and examiner satisfaction were surveyed.
Methods In the study, 112 outpatients received fundus photography with automated diagnosis of diabetic retinopathy (DR) via the IDx-DR system (Digital Diagnostics). The images were taken with the Topcon TRC-NW400 camera (Topcon Corp. Japan). Inclusion criterion was a diagnosis of diabetes mellitus type 1, 2, or 3. Patients who could not be imaged with sufficient quality in miosis were imaged in mydriasis.
Results Of 112 patients, analysis was possible in 107 patients (95.5 %) by grading by IDx-DR, based on fundus images – vs. 103 patients (91.9 %) by grading by ophthalmologists, based on the same, high-resolution fundus images. In the remaining patients, grading was possible by funduscopy alone. There was a highly significant correlation regarding the assessment of the severity of diabetic retinopathy between the examiner and the IDx-DR system (Correlation coefficient (r) = 0.8738; p < 0.0001). Patient satisfaction was 4.5 ± 0.6 [1–5], and total examination time in miosis averaged 3:04 ± 0:28 [min:sec].
Conclusion Retinopathy screening using IDx-DR enables automated diagnosis based on fundus photographs with a robust, technical and clinical workflow that allows timely and reliable assessment of diabetic retinopathy and is associated with high patient satisfaction.
Publication History
Received: 09 December 2020
Accepted: 16 April 2021
Article published online:
28 May 2021
© 2021. Thieme. All rights reserved.
Georg Thieme Verlag KG
Rüdigerstraße 14, 70469 Stuttgart, Germany
-
Literatur
- 1 Cheung N, Mitchell P, Wong TY. Diabetic retinopathy. Lancet 2010; 376: 124-136
- 2 Yau JW, Rogers SL, Kawasaki R. et al. Global prevalence and major risk factors of diabetic retinopathy. Diabetes Care 2012; 35: 556-564
- 3 Flaxman SR, Bourne RRA, Resnikoff S. et al. Global causes of blindness and distance vision impairment 1990-2020: a systematic review and meta-analysis. Lancet Glob Health 2017; 5: e1221-e1234
- 4 Li JQ, Welchowski T, Schmid M. et al. Prevalence, incidence and future projection of diabetic eye disease in Europe: a systematic review and meta-analysis. Eur J Epidemiol 2020; 35: 11-23
- 5 Vujosevic S, Aldington SJ, Silva P. et al. Screening for diabetic retinopathy: new perspectives and challenges. The Lancet Diabetes & Endocrinology 2020; 8: 337-347
- 6 Bundesärztekammer (BÄK) ÄZfQidM. Arbeitsgemeinschaft der Wissenschaftlichen Medizinischen Fachgesellschaften (AWMF). Nationale VersorgungsLeitlinie Prävention und Therapie von Netzhautkomplikationen bei Diabetes – Langfassung. 2015 2. Auflage. Version 2.
- 7 Ferris 3rd FL. How effective are treatments for diabetic retinopathy?. Jama 1993; 269: 1290-1291
- 8 Rohan TE, Frost CD, Wald NJ. Prevention of blindness by screening for diabetic retinopathy: a quantitative assessment. Bmj 1989; 299: 1198-1201
- 9 Kreft D, McGuinness MB, Doblhammer G. et al. Diabetic retinopathy screening in incident diabetes mellitus type 2 in Germany between 2004 and 2013 – A prospective cohort study based on health claims data. PloS one 2018; 13: e0195426-e0195426
- 10 Forster AS, Forbes A, Dodhia H. et al. Non-attendance at diabetic eye screening and risk of sight-threatening diabetic retinopathy: a population-based cohort study. Diabetologia 2013; 56: 2187-2193
- 11 Jones S, Edwards RT. Diabetic retinopathy screening: a systematic review of the economic evidence. Diabet Med 2010; 27: 249-256
- 12 Heintz E, Wiréhn AB, Peebo BB. et al. Prevalence and healthcare costs of diabetic retinopathy: a population-based register study in Sweden. Diabetologia 2010; 53: 2147-2154
- 13 Schmidt-Erfurth U, Sadeghipour A, Gerendas BS. et al. Artificial intelligence in retina. Prog Retin Eye Res 2018; 67: 1-29
- 14 Abràmoff MD, Folk JC, Han DP. et al. Automated analysis of retinal images for detection of referable diabetic retinopathy. JAMA Ophthalmol 2013; 131: 351-357
- 15 Hansen MB, Abràmoff MD, Folk JC. et al. Results of Automated Retinal Image Analysis for Detection of Diabetic Retinopathy from the Nakuru Study, Kenya. PLoS One 2015; 10: e0139148
- 16 Ting DSW, Cheung CY-L, Lim G. et al. Development and Validation of a Deep Learning System for Diabetic Retinopathy and Related Eye Diseases Using Retinal Images From Multiethnic Populations With Diabetes. JAMA 2017; 318: 2211-2223
- 17 Heydon P, Egan C, Bolter L. et al. Prospective evaluation of an artificial intelligence-enabled algorithm for automated diabetic retinopathy screening of 30 000 patients. Br J Ophthalmol 2020;
- 18 Santos T, Warren LH, Santos AR. et al. Swept-source OCTA quantification of capillary closure predicts ETDRS severity staging of NPDR. British Journal of Ophthalmology 2020;
- 19 Padhy SK, Takkar B, Chawla R. et al. Artificial intelligence in diabetic retinopathy: A natural step to the future. Indian J Ophthalmol 2019; 67: 1004-1009
- 20 Landis JR, Koch GG. The measurement of observer agreement for 10categorical data. Biometrics 1977; 33: 159-174
- 21 Castillo-Reinado K, Maier W, Holle R. et al. Associations of area deprivation and urban/rural traits with the incidence of type 1 diabetes: analysis at the municipality level in North Rhine-Westphalia, Germany. Diabetic Medicine
- 22 Tufail A, Kapetanakis VV, Salas-Vega S. et al. An observational study to assess if automated diabetic retinopathy image assessment software can replace one or more steps of manual imaging grading and to determine their cost-effectiveness. Health Technol Assess 2016; 20: 1-72
- 23 Tufail A, Rudisill C, Egan C. et al. Automated Diabetic Retinopathy Image Assessment Software: Diagnostic Accuracy and Cost-Effectiveness Compared with Human Graders. Ophthalmology 2017; 124: 343-351