Developing and Validating a Multivariable Prediction Model Which Predicts Progression of Intermediate to Late Age-Related Macular Degeneration—the PINNACLE Trial Protocol

AI Generated Summary*

PINNACLE is a protocol combining retrospective machine learning with a prospective cohort to identify OCT markers predicting which intermediate age-related macular degeneration eyes convert to late disease. Retrospectively, over 400,000 OCT images from nearly 100,000 people at four university sites and UK Biobank are pooled for supervised and unsupervised analysis. Prospectively, 400 patients aged 55 to 90 (a planned 600 eyes) at 12 sites in the UK, Austria and Switzerland undergo four-monthly imaging, with focal changes triggering adaptive optics, OCT angiography, autofluorescence and microperimetry. A Cox model developed on 360 eyes and validated on 240 should identify the most important predictors, assuming roughly 170 events. Pandemic disruption cut minimum follow-up to one year; no outcomes are reported.

*This summary was generated by AI and is published unedited. Oku does not alter these summaries. It may contain errors or omissions and is provided for general informational purposes only. Oku does not guarantee its accuracy, completeness, or reliability. For authoritative information, please refer to the original, peer-reviewed article.