Journal article · 2026 · Open access

A multi-stage validation framework for trustworthy large-scale clinical information extraction using large language models

Maria Mahbub, Gregory M. Dams, Josh Arnold, Caitlin Rizy, Sudarshan Srinivasan, Elliot M. Fielstein, M. Aghevli, Kamonica Craig, Elizabeth M. Oliva, Joseph Erdos, Jodie A. Trafton, Ioana Danciu

npj Digital Medicine · Published 16 October 2026 · DOI 10.1038/s41746-026-03341-7

Open PDFView at the publisherCite this paper

In brief

“A multi-stage validation framework for trustworthy large-scale clinical information extraction using large language models” is a 2026 journal article by Maria Mahbub and 11 co-authors, published in npj Digital Medicine. OpenAlex counts 3 citations as of 17 November 2026, which puts it in the top 4% of works published in 2026 by citations. It is open access under a CC BY licence: the full text is free to read at npj Digital Medicine.

Citations
3
Most cited in
2026 (3)
Field-weighted impact
3.24
References
50
Authors
12

Abstract

Large language models (LLMs) show promise for extracting clinically meaningful information from unstructured health records, yet real-world deployment is constrained by limited scalable, trustworthy validation approaches. Conventional evaluation relies on annotation-intensive reference standards and incomplete structured data, limiting population-scale use. We propose a multi-stage validation framework for LLM-based clinical information extraction that enables rigorous assessment under weak supervision by integrating complementary validation strategies. The framework combines prompt calibration, rule-based filtering, semantic grounding, judge-LLM evaluation, expert review, and predictive validity analysis to quantify uncertainty without exhaustive manual annotation. We applied this framework to extract substance use disorder (SUD) diagnoses across 11 substance categories from 919,783 clinical notes. Rule-based filtering and semantic grounding removed 14.59% of LLM-positive extractions that were unsupported or structurally implausible. For high-uncertainty cases, the judge LLM showed substantial agreement with subject matter expert. Using judge evaluations as references, the primary LLM achieved an F1 score of 0.80. LLM-extracted SUD diagnoses predicted subsequent engagement in SUD specialty care more accurately than structured-data baselines. By unifying complementary validation strategies, this work presents a generalizable human-in-the-loop framework for establishing the trustworthiness of LLM-based clinical information extraction at scale while minimizing the need for exhaustive manual annotation.

Cite this paper

Formatted from the catalogue record. Check names, capitals and page numbers against the paper before you submit.

APA 7

Mahbub, M., Dams, G. M., Arnold, J., Rizy, C., Srinivasan, S., Fielstein, E. M., Aghevli, M., Craig, K., Oliva, E. M., Erdos, J., Trafton, J. A., & Danciu, I. (2026). A multi-stage validation framework for trustworthy large-scale clinical information extraction using large language models. npj Digital Medicine. https://doi.org/10.1038/s41746-026-03341-7

MLA 9

Mahbub, Maria, et al. “A multi-stage validation framework for trustworthy large-scale clinical information extraction using large language models.” npj Digital Medicine, 2026. https://doi.org/10.1038/s41746-026-03341-7.

Chicago

Mahbub, Maria, Gregory M. Dams, Josh Arnold, Caitlin Rizy, Sudarshan Srinivasan, Elliot M. Fielstein, M. Aghevli, et al. 2026. “A multi-stage validation framework for trustworthy large-scale clinical information extraction using large language models.” npj Digital Medicine. https://doi.org/10.1038/s41746-026-03341-7.

Harvard

Mahbub, M. et al. (2026) ‘A multi-stage validation framework for trustworthy large-scale clinical information extraction using large language models’, npj Digital Medicine. doi:10.1038/s41746-026-03341-7.

IEEE

M. Mahbub et al., “A multi-stage validation framework for trustworthy large-scale clinical information extraction using large language models,” npj Digital Medicine, 2026, doi: 10.1038/s41746-026-03341-7.

BibTeX

@article{mahbub2026multi,
  title     = {{A multi-stage validation framework for trustworthy large-scale clinical information extraction using large language models}},
  author    = {Mahbub, Maria and Dams, Gregory M. and Arnold, Josh and Rizy, Caitlin and Srinivasan, Sudarshan and Fielstein, Elliot M. and Aghevli, M. and Craig, Kamonica and Oliva, Elizabeth M. and Erdos, Joseph and Trafton, Jodie A. and Danciu, Ioana},
  journal   = {npj Digital Medicine},
  year      = {2026},
  doi       = {10.1038/s41746-026-03341-7},
  url       = {https://doi.org/10.1038/s41746-026-03341-7}
}

Download for a reference manager: BibTeX (.bib) · RIS for Zotero, Mendeley and EndNote (.ris)

Topic and keywords

Physical Sciences › Computer Science › Artificial Intelligence › Machine Learning in Healthcare

  • large language models
  • clinical information extraction
  • weakly supervised learning
  • human-in-the-loop evaluation
  • rule-based filtering
  • semantic grounding
  • uncertainty quantification
  • clinical notes

Work with this paper

Most-cited papers in Computer Science

All highly cited Computer Science papers

Questions about this paper

How do I cite this paper in APA style?

Mahbub, M., Dams, G. M., Arnold, J., Rizy, C., Srinivasan, S., Fielstein, E. M., Aghevli, M., Craig, K., Oliva, E. M., Erdos, J., Trafton, J. A., & Danciu, I. (2026). A multi-stage validation framework for trustworthy large-scale clinical information extraction using large language models. npj Digital Medicine. https://doi.org/10.1038/s41746-026-03341-7

How many times has this paper been cited?

3 times, according to OpenAlex on 17 November 2026. Google Scholar and Scopus count different sets of sources, so their numbers differ.

Is this paper free to read?

Yes. It is open access at npj Digital Medicine: sign in and open the PDF from this page.

Who wrote this paper?

Maria Mahbub, Gregory M. Dams, Josh Arnold, Caitlin Rizy, Sudarshan Srinivasan, Elliot M. Fielstein, M. Aghevli, Kamonica Craig, Elizabeth M. Oliva, Joseph Erdos, Jodie A. Trafton, Ioana Danciu.

What is the DOI of this paper?

10.1038/s41746-026-03341-7, permanently at https://doi.org/10.1038/s41746-026-03341-7. Sign in and open it from this page.

Bibliographic data from OpenAlex (CC0), last checked 17 November 2026. ResearchGuru does not host this paper; once you are signed in, the links open it at the publisher or the repository that does.