Reproduce “Self-Supervised Transformer for Sparse and Irregularly Sampled Multivariate Clinical Time-Series” on OpenResearch
Turn your favorite coding agents into research agents that review literature, develop hypotheses, and run experiments.
Universal app for Apple silicon and Intel. Requires macOS 11 or later.
About this paper
Sindhu Tipirneni, Chandan K. Reddy
STraTS predicts in-hospital mortality from irregular clinical records by representing each observed measurement as a time, variable, and value, without first filling gaps or aggregating observations. It also uses forecasting as a self-supervised training task. On MIMIC-III and PhysioNet-2012, it achieved higher PR-AUC than the strongest baseline on that metric in the evaluated mortality tasks.
Summary by alphaXiv.
Tip: change arxiv.org to autoarxiv.org in any arXiv abstract link to open the paper here.