Search Articles

View query in Help articles search

Search Results (1 to 10 of 1798 Results)

Download search results: CSV END BibTex RIS


Unsupervised Deep Learning of Electronic Health Records to Characterize Heterogeneity Across Alzheimer Disease and Related Dementias: Cross-Sectional Study

Unsupervised Deep Learning of Electronic Health Records to Characterize Heterogeneity Across Alzheimer Disease and Related Dementias: Cross-Sectional Study

Alternative methods, such as K-means, Gaussian mixture models [40], and density-based spatial clustering of applications with noise (DBSCAN) [41], face theoretical limitations: K-means assumes spherical clusters that is difficult to satisfy in high-dimensional embeddings; DBSCAN relies on density thresholds that break down in such spaces; and Gaussian mixture models can be unstable with overlapping subtypes.

Matthew West, You Cheng, Yingnan He, Yu Leng, Colin Magdamo, Bradley T Hyman, John R Dickson, Alberto Serrano-Pozo, Deborah Blacker, Sudeshna Das

JMIR Aging 2025;8:e65178