EUVIMEDEUVIMED entdecken
Crossref

Accuracy of Retrieval-Augmented Large Language Model–Generated Preconsult Summaries in Breast Surgical Oncology

Tracy-Ann Moo iD, Robert James iD, Solange Bayard iD, Andreas Giannakou, Lisa R Allen, Giacomo Montagna iD, Ivan Pan iD, Varadan Sevilimedu, Sarah Eskreis-Winkler iD, Monica Morrow iD

JCO Clinical Cancer Informatics · 2026

DOI: 10.1200/cci-26-00160 ↗

Kurz gefasst

Fachartikel in der Zeitschrift JCO Clinical Cancer Informatics, 2026. Verfasst von Tracy-Ann Moo und 9 weiteren Autor:innen. Beteiligte Einrichtung: Department of Surgery, Breast Service, Memorial Sloan Kettering Cancer Center, New York, NY. Hauptthemen laut MEDLINE: Breast Neoplasms, Surgical Oncology, Information Storage and Retrieval. Die Arbeit nennt 25 Literaturangaben.

AbstractSchlagwörterBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

PURPOSE Radiology and pathology reports are important in breast surgical oncology planning, but are often unstructured and variable, requiring time-intensive previsit review and preparation. Here we evaluate the accuracy, completeness, and safety of retrieval-augmented large language model (LLM)–generated structured preconsult summaries compared with clinical staff–authored summaries. METHODS In this single-institution retrospective validation study, 200 randomly sampled new breast surgical oncology consultations were included. LLM summaries were generated and compared with human summaries documented in consultation notes. Field-level accuracy, omission rate, and fabrication rate among extracted radiology and pathology variables were measured. Error analysis included patient level and clinically significant fabrication rates. RESULTS Artificial intelligence (AI)–generated summaries demonstrated high field-level accuracy, with fabrication rates ≤2%. Accuracy rates were significantly higher than those observed in staff-authored notes across multiple domains, including nodal status (95% v 72%, P < .001) and documentation of invasive tumor component on biopsy (94% v 30%, P < .001). In contrast, staff-authored summaries were more accurate for receptor status (96% v 86%, P = .002). At the patient level, fabrication occurred in 16 AI-generated summaries (8%), including six clinically significant cases (3%). Staff-authored summaries demonstrated fabrication in six cases (3.0%), with one clinically significant instance (0.5%). CONCLUSION In this retrospective validation study, structured retrieval-augmented LLM-generated preconsult summaries demonstrated field-level accuracy comparable with or exceeding staff-authored documentation across most radiologic and pathologic variables, with low per-field fabrication rates. Clinically significant errors occurred in a small proportion of summaries and were largely confined to identifiable high-risk variables that are amenable to targeted verification. With appropriate human oversight and safeguards, LLM-based structured information extraction may support documentation standardization and improved workflow efficiency in breast surgical oncology.

Schlagwörter

MeSH-Schlagwörter (MEDLINE)

Breast NeoplasmsSurgical OncologyInformation Storage and RetrievalHumansLarge Language ModelsFemaleRetrospective StudiesArtificial IntelligenceElectronic Health Records

Autor:innen und Institutionen

  • Department of Surgery, Breast Service, Memorial Sloan Kettering Cancer Center, New York, NY.
  • Department of Epidemiology and Biostatistics, Biostatistics Service, Memorial Sloan Kettering Cancer Center, New York, NY.
  • Department of Data and Analytics, Artificial Intelligence & Machine Learning (AIML), Memorial Sloan Kettering Cancer Center, New York, NY.
  • Department of Radiology, Memorial Sloan Kettering Cancer Center, New York, NY.

ORCID-Profile: Tracy-Ann Moo, Robert James, Solange Bayard, Giacomo Montagna, Ivan Pan, Sarah Eskreis-Winkler, Monica Morrow

Zitieren

APA

Moo, T. A., James, R., Bayard, S., Giannakou, A., Allen, L. R., Montagna, G., Pan, I., Sevilimedu, V., Eskreis-Winkler, S., & Morrow, M. (2026). Accuracy of Retrieval-Augmented Large Language Model–Generated Preconsult Summaries in Breast Surgical Oncology. JCO Clinical Cancer Informatics. https://doi.org/10.1200/cci-26-00160

Vancouver

Moo TA, James R, Bayard S, Giannakou A, Allen LR, Montagna G, et al. Accuracy of Retrieval-Augmented Large Language Model–Generated Preconsult Summaries in Breast Surgical Oncology. JCO Clinical Cancer Informatics. 2026. doi:10.1200/cci-26-00160

BibTeX
@article{Moo2026,
  author = {Moo, Tracy-Ann and James, Robert and Bayard, Solange and Giannakou, Andreas and Allen, Lisa R and Montagna, Giacomo and Pan, Ivan and Sevilimedu, Varadan and Eskreis-Winkler, Sarah and Morrow, Monica},
  title = {Accuracy of Retrieval-Augmented Large Language Model–Generated Preconsult Summaries in Breast Surgical Oncology},
  journal = {JCO Clinical Cancer Informatics},
  year = {2026},
  doi = {10.1200/cci-26-00160}
}
Kostenlos starten →