CoChat

CORAL: Expert-Curated Oncology Reports to Advance Language Model Inference

Sushil, Madhumita, Kennedy, Vanessa E., Mandair, Divneet, Miao, Brenda Y., Zack, Travis, Butte, Atul J. · 2024 · NEJM AI
Cited by 64

The DOI matches its Crossref record; 15 of the 15 references it cites were found in a registry or an index.

Abstract

BACKGROUND: Both medical care and observational studies in oncology require a thorough understanding of a patient's disease progression and treatment history, often elaborately documented within clinical notes. As large language models (LLMs) are being considered for use within medical workflows, it becomes important to evaluate their potential in oncology. However, no current information representation schema fully encapsulates the diversity of oncology information within clinical notes, and no comprehensively annotated oncology notes exist publicly, thereby limiting a thorough evaluation. METHODS: extraction of detailed oncological information from two narrative sections of clinical progress notes. Model performance was quantified with BLEU-4, ROUGE-1, and exact-match (EM) F1 score metrics. RESULTS: Our team annotated 9028 entities, 9986 modifiers, and 5312 relationships. The GPT-4 model exhibited overall best performance, with an average BLEU score of 0.73, an average ROUGE score of 0.72, an average EM F1 score of 0.51, and an average accuracy of 68% (expert manual evaluation on subset). Notably, GPT-4 was proficient in tumor characteristic and medication extraction and demonstrated superior performance in advanced reasoning tasks of inferring symptoms due to cancer and considerations of future medications. Common errors included partial responses with missing information and hallucinations with note-specific information. CONCLUSIONS: By developing a comprehensive schema and benchmark of oncology-specific information in oncology notes, we uncovered both the strengths and the limitations of LLMs. Our evaluation showed variable zero-shot extraction capability among the GPT-3.5-turbo, GPT-4, and FLAN-UL2 models and highlighted a need for further improvements, particularly in complex medical reasoning, before performing reliable information extraction for clinical research and complex population management and documenting quality patient care. (Funded by the National Institute of Health, Food and Drug Administration and others.).

Overview

The claims and statistics of this paper haven’t been checked yet.

Free: it reads the open-access text and checks the first 5 claims that cite a source we can check. Create a free account to check every claim.

A few free checks a day · papers already verified open instantly · results are public

Integrity signals

Registry

Crossref · 10.1056/aidbp2300110

Cites

15 of 15 references verified0 citation errors · 0 not checkable

Statistics

Verification

Claims the paper makes

The claims and statistics of this paper haven’t been checked yet.

Free: it reads the open-access text and checks the first 5 claims that cite a source we can check. Create a free account to check every claim.

A few free checks a day · papers already verified open instantly · results are public

Claims other papers make about this one

Each is checked against this paper’s own text: does it say what the citing paper says it does?

Self-check

Percentages, sums and reported differences re-computed from the paper’s own numbers.

The self-check needs the paper’s full text.

Citations

Cites

Research works printed but not linked: 23

  1. 10.1158/0008-5472.CAN-19-0579 · DOI · Paper page
  2. 10.1148/radiol.230424 · DOI · Paper page
  3. Alawad M Yoon H-J Tourassi GD. Coarse-to-fine multi-task training of convolutional neural networks for automated information extraction from cancer pathology reports. In: 2018 IEEE EMBS International Conference on Biomedical & Health Informatics (BHI). Piscataway NJ: IEEE 2018:218-221. · DOI · Paper page
  4. 10.1111/cts.12514 · DOI · Paper page
  5. 10.1007/s10549-016-4035-1 · DOI · Paper page
  6. 10.1097/01.JU.0000557177.97226.63 · doi:10.1097/01.ju.0000557177.97226.63
  7. 10.1200/CCI.19.00147 · DOI
  8. 10.1016/j.jbi.2021.103872 · DOI
  9. 10.1200/CCI.20.00079 · DOI · Paper page
  10. Roberts K Si Y Gandhi A Bernstam E. A FrameNet for cancer information in clinical narratives: schema and annotation. In: Calzolari N Choukri K Cieri C et al. eds. Proceedings of the Eleventh International Conference on Language Resources and Evaluation (LREC 2018). Paris: European Language Resources Association 2018:272-279.
  11. 10.1016/j.jbi.2019.103301 · DOI
  12. 10.4103/jfmpc.jfmpc_931_19 · DOI
  13. Datta S Ulinski M Godfrey-Stovall J Khanpara S Riascos-Castaneda RF Roberts K. Rad-SpatialNet: a frame-based resource for fine-grained spatial relations in radiology reports. In: Calzolari N Béchet F Blache P et al. eds. Proceedings of the 12th Language Resources and Evaluation Conference. Marseille France: European Language Resources Association 2020: 2251-2260.
  14. 10.1158/0008-5472.CAN-17-0615 · DOI
  15. 10.1093/jamiaopen/ooad045 · DOI
  16. Open AI. GPT-4 technical report. March 15 2023 (http://arxiv.org/abs/2303.08774). Preprint. · arXiv
  17. Papineni K Roukos S Ward T Zhu W-J. Bleu: a method for automatic evaluation of machine translation. In: Isabelle P Charniak E Lin D eds. Proceedings of the 40th Annual Meeting of the Association for Computational Linguistics. Kerrville TX: Association for Computational Linguistics 2002:311-318. · DOI · Paper page
  18. Lin C-Y. ROUGE: a package for automatic evaluation of summaries. In: Moens M-F, Szpakowicz S, eds. Text summarization branches out. Kerrville, TX: Association for Computational Linguistics, 2004:74-81.
  19. 10.1197/jamia.M1733 · DOI · Paper page
  20. Lehman E Hernandez E Mahajan D et al. Do we still need clinical language models? In: Mortazavi BJ Sarker T Beam A Ho JC eds. Proceedings of Machine Learning Research. Vol. 209. Machine Learning Research Press 2023:578-597.
  21. Weller O Lourie N Gardner M Peters ME. Learning from task descriptions. In: Webber B Cohn T He Y Liu Y eds. Proceedings of the 2020 Conference on Empirical Methods in Natural Language Processing (EMNLP). Kerrville TX: Association for Computational Linguistics 2020:1361-1375. · DOI · Paper page
  22. 10.1111/cts.13463 · DOI
  23. Creswell A Shanahan M Higgins I. Selection-inference: exploiting large language models for interpretable logical reasoning. 2023 (https://openreview.net/forum?id=3Pf3Wg6o-A4).

Cited by

See all 64

Metadata

Authors
Sushil, M., Kennedy, V. E., Mandair, D., Miao, B. Y., Zack, T., & Butte, A. J.
Affiliations
  • Bakar Computational Health Sciences Institute, University of California, San Francisco, San Francisco
  • Helen Diller Family Comprehensive Cancer Center, University of California, San Francisco, San Francisco
Venue
NEJM AI
Published
2024-03-28
Volume
1
Issue
4
ISSN
2836-9386
Cited by
64
References
15
Language
en

About these checks

Registry, retraction, Cites and statistics results are computed, not judged, with one exception: a printed reference that no index lists is read once by a model before it counts as a citation error. Claims are extracted by a model and kept only when their quote appears verbatim in the text; each cited source is then checked, with a model’s help, for whether it says what the claim relies on. Those verdicts can be wrong — read the claim’s quote and the cited source before relying on one.

Statistics and arithmetic are recomputed, not judged.

Confidence bands are shown only for fields calibrated on our annotated test set. None is calibrated yet, so no band is shown.

What counts as a claim ›How we measure confidence ›How we check this ›

Are you an author, or do you see a problem with this page? Request a review

Data sources

Bibliographic data: Semantic Scholar, OpenAlex, Crossref.

Contains information from the Semantic Scholar Academic Graph Datasets, made available under the ODC Attribution License (ODC-BY 1.0).

Semantic Scholar’s data is described in: Kinney, R., et al. (2023). The Semantic Scholar Open Data Platform. arXiv:2301.10140.