most citedAn Unsupervised Homogenization Pipeline for Clustering Similar Patients using Electronic Health Record Data

5 citations · 5 across the 2 of their papers we have counts for

collaborators
Showing cs.LGShow all

1 paper · 1 filter

cs.LG2026

Representation Before Training: A Practical Benchmark for Generative Medical Event Model Tokenization

Inhyeok Lee, Luke Solo, Michael C. Burkhart +5

Generative medical event models use tokenized sequences of patient timelines as input, but practical guidance on the many decisions around tokenization is limited. We benchmark qua…