NORMA, a conditional transformer framework, generates blood biomarker reference intervals by conditioning on patient history and population priors, outperforming pure personalization in predicting clinical outcomes such as mortality and kidney injury.
Health system-scale language models are all-purpose prediction engines.Nature, 619(7969):357–362, July 2023
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
fields
cs.LG 1years
2026 1verdicts
UNVERDICTED 1representative citing papers
citing papers explorer
-
Learning Normal Representations for Blood Biomarkers
NORMA, a conditional transformer framework, generates blood biomarker reference intervals by conditioning on patient history and population priors, outperforming pure personalization in predicting clinical outcomes such as mortality and kidney injury.