EUVIMEDEUVIMED entdecken
Open Access · CC BY 4.0

DataAtlas: automatic generation of data dictionaries using large language models

Raffaele Giancotti iD, Rajna Fani, Rafi Al Attrach, Pierangelo Veltri, Tom Pollard iD

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.

AbstractSchlagwörterBibliografische AngabenZitierenVerwandte Studien

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

clinical datadata dictionarygenerative AIlarge language models

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}
}
Kostenlos starten →