A frozen LLM prompted with a text description and one average patient example generates synthetic Parkinson's and Alzheimer's cohorts with preserved correlations, but with lower fidelity than models trained on original data.
Generation and evaluation of privacy preserving synthetic health data,
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
2024 1verdicts
CONDITIONAL 1roles
background 1polarities
support 1representative citing papers
citing papers explorer
-
A text-to-tabular approach to generate synthetic patient data using LLMs
A frozen LLM prompted with a text description and one average patient example generates synthetic Parkinson's and Alzheimer's cohorts with preserved correlations, but with lower fidelity than models trained on original data.