Large language models for generating longitudinal synthetic data in low-risk pregnancy care
Gonçalo Pinto, Vítor Crista, Regina Silva, Bruno Costa, Filipe Andrade Bernardi, Rute Almeida, Julio Souza, Alberto Freitas, Goreti Marreiros, Luís Conceição · 2026
Read Large language models for generating longitudinal synthetic data in low-risk pregnancy care by Gonçalo Pinto, Vítor Crista, Regina Silva, Bruno Costa, Filipe Andrade Bernardi, Rute Almeida, Julio Souza, Alberto Freitas, Goreti Marreiros, Luís Conceição (2026) in the Tower of Babel, a free online library of public-domain works preserved in clean, searchable text. No sign-up. The full text is served as a plain-text file at a predictable URL, where text is present: https://antarctic-labs.com/tower-of-babel/pmc-13273859.txt.
Description
Gonçalo Pinto and co-authors used a large language model to generate a synthetic pregnancy dataset in a 2026 data article. Real obstetric records are hard to share because of privacy, which slows methods research. Synthetic patients can stand in for teaching and testing if they stay plausible.
Their dataset follows five thousand low risk pregnant women from before conception to after birth. It holds trimester measures such as weight, hemoglobin, glucose tests, and body mass, plus visit, delivery, and outcome variables. An expert panel in family medicine and data science reviewed early output, and repeated prompt revisions improved consistency. Rule checks then verified internal coherence. The authors stress the data suit simulation and machine learning practice, not clinical decisions.
Catalog record
| CREATOR | Gonçalo Pinto, Vítor Crista, Regina Silva, Bruno Costa, Filipe Andrade Bernardi, Rute Almeida, Julio Souza, Alberto Freitas, Goreti Marreiros, Luís Conceição |
|---|---|
| YEAR | 2026 |
| COLLECTION | PAPERS |
| FORMAT | TXT |
| FILE SIZE | 65 KB |
| VERSION | 1.0 |
| LICENSE | CC BY 4.0 |
| RIGHTS | CC BY |
| SOURCE | Europe PMC |