A standardized MIMIC-IV benchmark comparing eight unimodal and multimodal foundation models shows multimodal inputs improve predictive performance without adding bias, while medical LVLMs underperform on length-of-stay prediction.
Harnessing ehr data for health research,
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
citation-role summary
background 1
citation-polarity summary
fields
cs.LG 1years
2025 1verdicts
CONDITIONAL 1roles
background 1polarities
unclear 1representative citing papers
citing papers explorer
-
Benchmarking Foundation Models with Multimodal Public Electronic Health Records
A standardized MIMIC-IV benchmark comparing eight unimodal and multimodal foundation models shows multimodal inputs improve predictive performance without adding bias, while medical LVLMs underperform on length-of-stay prediction.