Best model reduction approach for Fine-Gray prediction model

Yes if there are many candidate predictors then unsupervised learning is a great first step.

Regarding the big picture, I don’t find prediction of AD that precedes death to be that meaningful. That’s what competing risk analysis does. I find it much more natural to use multi-state models. See this amazing document by Therneau, Crowson, Atkinson.

Discrete time multistate models are even simpler.

This survey revealed that most researchers find it impossible to really separate death from nonfatal outcomes anyway.