Use this skill whenever the user wants unsupervised disease subtyping, patient stratification, latent phenotype discovery, cluster stability analysis, or low-dimensional embeddings from neuroimaging features. It supports K-means, Gaussian mixture models, spectral clustering, NMF, consensus clustering, PCA embeddings, and autoencoder embeddings. Triggers include 'subtype', 'patient stratification', 'clustering', 'latent phenotype', 'consensus clustering', 'GMM', 'NMF', 'PCA embedding', and 'autoencoder clustering'.
