DataAtlas: automatic generation of data dictionaries using large language models
JAMIA Open · 05.05.2026 · 9 (3)
DOI: 10.1093/jamiaopen/ooag119 ↗Kurz gefasst
Fachartikel in der Zeitschrift JAMIA Open, online erschienen am 27.06.2026. Verfasst von Raffaele Giancotti und 4 weiteren Autor:innen. Beteiligte Einrichtung: Laboratory for Computational Physiology, MIT Institute for Medical Engineering and Science, Massachusetts Institute of Technology, Cambridge, MA 0213…. Die Arbeit nennt 19 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY 4.0). Gefördert von: PNRR, Advancing Lung Cancer Screening: Artificial Intelligence, Multimodal Imaging and Cutting-Edge Technologies for Early Detection and Characterization, NextGeneration EU.
Abstract (Originalsprache)
Objectives
Reuse of shared datasets is often limited by incomplete or inconsistent documentation, hindering interpretation and secondary analysis. We developed DataAtlas, an open-source system for automated generation of data dictionaries from tabular datasets. Materials and Methods DataAtlas combines deterministic structural profiling with large language model (LLM)-based semantic inference to generate human-readable descriptions of datasets, tables, and variables. The system integrates column metadata, statistical summaries, and representative sample values to produce concise, context-aware descriptions. We evaluated the approach on 3 heterogeneous clinical datasets using structural validation, blinded LLM-based comparison with official documentation, human expert review, and downstream task evaluation.
Results
Generated descriptions were frequently preferred over official documentation, particularly when existing descriptions were incomplete or ambiguous. Human expert review showed strong agreement with high-performing models, with most descriptions rated as correct and low rates of hallucination. The system accurately reconstructed schema elements and flagged inconsistencies in existing documentation. In a text-to-SQL benchmark, augmenting database schemas with generated data dictionaries improved execution accuracy from 0.52 to 0.88.
Discussion
Automated data dictionary generation improved both dataset interpretability and downstream analytical performances. Results highlight the importance of column-level metadata, particularly representative sample values, in grounding LLM-generated descriptions. Limitations include sensitivity to sample quality, potential domain-specific misinterpretation, and variability across model architectures, indicating that generated outputs should augment rather than replace expert curation.
Conclusion
DataAtlas provides a practical approach for generating structured data dictionaries, enhancing the accessibility, reproducibility, and reuse of clinical data.
Schlagwörter
Stichwörter der Autor:innen
Autor:innen und Institutionen
- Laboratory for Computational Physiology, MIT Institute for Medical Engineering and Science, Massachusetts Institute of Technology, Cambridge, MA 02139, United States.
- Department of Computer Engineering, Modeling, Electronics, and Systems Engineering, Università della Calabria, Arcavata di Rende (CS), 87036, Italy.
- TUM School of Computation, Information and Technology, Technical University of Munich, Munich, Bavaria 80333, Germany.
ORCID-Profile: Raffaele Giancotti, Tom Pollard
Förderung
- PNRR
- Advancing Lung Cancer Screening: Artificial Intelligence, Multimodal Imaging and Cutting-Edge Technologies for Early Detection and Characterization
- NextGeneration EU
- KILOWATT
- National Institutes for Health
- Boston-Korea Innovative Research Project through the Korea Health Industry Development Institute
- Ministry of Health & Welfare, Republic of Korea
- NTIS
Zitieren
APA
Giancotti, R., Fani, R., Al Attrach, R., Veltri, P., & Pollard, T. (2026). DataAtlas: automatic generation of data dictionaries using large language models. JAMIA Open, 9(3). https://doi.org/10.1093/jamiaopen/ooag119
Vancouver
Giancotti R, Fani R, Al Attrach R, Veltri P, Pollard T. DataAtlas: automatic generation of data dictionaries using large language models. JAMIA Open. 2026;9(3). doi:10.1093/jamiaopen/ooag119
BibTeX
@article{Giancotti2026,
author = {Giancotti, Raffaele and Fani, Rajna and Al Attrach, Rafi and Veltri, Pierangelo and Pollard, Tom},
title = {DataAtlas: automatic generation of data dictionaries using large language models},
journal = {JAMIA Open},
year = {2026},
volume = {9},
number = {3},
doi = {10.1093/jamiaopen/ooag119}
}
EUVIMED