The authors report an analysis that was developed as part of a pilot study examining the use of decision analysis and value-of-information methods to inform research prioritization decisions for the UK health care system. This analysis was conducted to inform decision makers whether additional research on screening for age-related macular degeneration (AMD) would be worthwhile and to demonstrate the benefits and feasibility of using such analytic methods to inform policy decision within the time-lines demanded by existing procedures. A probabilistic decision model was developed to establish the cost-effectiveness of a policy of repeat screening for AMD using the Amsler grid followed by treatment with photodynamic therapy (PDT) compared with 2 alternatives: PDT without screening (self-referral) and no screening or treatment. Screening for AMD appears to be cost-effective on the basis of existing evidence; however, the decision to implement a policy of screening is somewhat uncertain, with a probability that screening is cost-effective of 0.87 and 0.72 for the 20/40 and 20/80 models, respectively, at a threshold of 30,000 pounds per quality-adjusted life-year. The expected value of perfect information (EVPI) associated with this decision is substantial (6.9 million pounds for the 20/40 model and 14.5 million pounds for the 20/80 model), with a sizeable EVPI associated with the effect of PDT on quality of life. The analysis demonstrates that EVPI analysis can be implemented in a timely fashion to inform the type of research prioritization decisions faced by any health care system. This case study also illustrates the need to account for any structural uncertainties appropriately.