Novel prediction model detects progression to advanced AMD

A comprehensive prediction model that applies a machine learning algorithm allowing selection of the most predictive risk factors automatically achieves high discrimination abilities in calculating progression to advanced age-related macular degeneration (AMD), as shown in two cohort studies.

This paves the way toward making precision medicine for AMD patients a reality in the near future, according to the investigators.

The Rotterdam Study I (RS-I; training set) included 3,838 participants aged ≥55 years, with a median follow-up of 10.8 years, and 108 incident cases of advanced AMD. In addition, the Antioxydants, Lipids Essentiels, Nutrition et Maladies Oculaires (ALIENOR) study (test set) included 362 individuals aged ≥73 years, with a median follow-up of 6.5 years, and 33 incident cases of advanced AMD.

The prediction model utilized the bootstrap least absolute shrinkage and selection operator (LASSO) method for survival analysis to select the best predictors of incident advanced AMD in the training set. The area under the receiver operating characteristic curve (AUC) was used to assess the predictive performance of the model.

The following factors were retained in the prediction model: age, a combination of phenotypic predictors (based on the presence of intermediate drusen, hyperpigmentation in one or both eyes, and Age-Related Eye Disease Study simplified score), a summary genetic risk score based on 49 single nucleotide polymorphisms, smoking, diet quality, education, and pulse pressure.

In RS-I, the cross-validated AUC estimation was 0.92 (95 percent confidence interval [CI], 0.88–0.97) at 5 years, 0.92 (95 percent CI, 0.90–0.95) at 10 years, and 0.91 (95 percent CI, 0.88–0.94) at 15 years. In ALIENOR, the AUC was 0.92 (95 percent CI, 0.87–0.98) at 5 years.

When it came to calibration, the model seemed to underestimate the cumulative incidence of advanced AMD for the high-risk groups, especially in ALIENOR.

“Current prediction models for advanced AMD are based on a restrictive set of risk factors,” the investigators noted.