Purpose: To compare frequently used classification systems for age-related macular degeneration(AMD) in their abilty to predictlate AMD. Methods:Intotal,9066participantsfromthepopulation-basedRotterdamStudywere followedupforprogressionofAMDduringastudyperiodupto30years.AMDlesions weregradedoncolorfundusphotographsafterconfirmationonotherimagemodalities andgroupedatbaselineaccordingtosixclassificationsystems.LateAMDwasdefinedas geographicatrophyorchoroidalneovascularization.Incidencerate(IR)andcumulative incidence(CuI)oflateAMDwerecalculated,andKaplan-Meierplotsandareaunderthe operating characteristics curves(AUCs)wereconstructed. Results: A total of 186 persons developed incident late AMD during a mean follow-up timeof8.7years.TheAREDSsimplifiedscaleshowedthehighestIRforlateAMDat104 cases/1000 py for ages <75 years. The Rotterdam classification showed the highest IR at 89 cases/1000 py >75 years. The 3-Continent harmonization classification provided the most stable progression. Drusen area >10% ETDRS grid (hazard ratio 30.05, 95% confidence interval [CI] 19.25–46.91) was most prognostic of progression. The highest AUC of late AMD (0.8372, 95% CI: 0.8070-0.8673) was achieved when all AMD features present at base line were included. Conclusions: Highest turnover rates from intermediate to late AMD were provided by the AREDS simplified scale and the Rotterdam classification. The 3-Continent harmonization classification showed the most stable progression. All features, especially drusenarea,contribute to late AMD prediction. Translational Relevance: Findings will help stakeholders select appropriate classification systems for screening,deep learning algorithms, or trials.

AMD, Artificial intelligence, Classificatiosystems, Clinical trials, Screening
dx.doi.org/10.1167/TVST.9.2.26, hdl.handle.net/1765/130366
Translational Vision Science and Technology
Department of Ophthalmology

Thee, E.F. (Eric F.), Meester-Smoor, M.A, Luttikhuizen, D.T. (Daniel T.), Colijn, J.M, Enthoven, C.A. (Clair A.), Haarman, A.E.G. (Annechien E. G.), … Klaver, C.C.W. (2020). Performance of classification systems for age-related macular degeneration in the rotterdam study. Translational Vision Science and Technology, 9(2), 1–11. doi:10.1167/TVST.9.2.26