{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,9,3]],"date-time":"2026-09-03T20:20:14Z","timestamp":1788466814918,"version":"build-2803163510"},"reference-count":25,"publisher":"American Society of Clinical Oncology (ASCO)","issue":"3","content-domain":{"domain":["ascopubs.org"],"crossmark-restriction":true},"short-container-title":["JCO Clin Cancer Inform"],"published-print":{"date-parts":[[2026,7]]},"abstract":"<jats:sec>\n                    <jats:title>PURPOSE<\/jats:title>\n                    <jats:p>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)\u2013generated structured preconsult summaries compared with clinical staff\u2013authored summaries.<\/jats:p>\n                  <\/jats:sec>\n                  <jats:sec>\n                    <jats:title>METHODS<\/jats:title>\n                    <jats:p>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.<\/jats:p>\n                  <\/jats:sec>\n                  <jats:sec>\n                    <jats:title>RESULTS<\/jats:title>\n                    <jats:p>\n                      Artificial intelligence (AI)\u2013generated summaries demonstrated high field-level accuracy, with fabrication rates \u22642%. Accuracy rates were significantly higher than those observed in staff-authored notes across multiple domains, including nodal status (95%\n                      <jats:italic toggle=\"yes\">v<\/jats:italic>\n                      72%,\n                      <jats:italic toggle=\"yes\">P<\/jats:italic>\n                      &lt; .001) and documentation of invasive tumor component on biopsy (94%\n                      <jats:italic toggle=\"yes\">v<\/jats:italic>\n                      30%,\n                      <jats:italic toggle=\"yes\">P<\/jats:italic>\n                      &lt; .001). In contrast, staff-authored summaries were more accurate for receptor status (96%\n                      <jats:italic toggle=\"yes\">v<\/jats:italic>\n                      86%,\n                      <jats:italic toggle=\"yes\">P<\/jats:italic>\n                      = .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%).\n                    <\/jats:p>\n                  <\/jats:sec>\n                  <jats:sec>\n                    <jats:title>CONCLUSION<\/jats:title>\n                    <jats:p>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.<\/jats:p>\n                  <\/jats:sec>","DOI":"10.1200\/cci-26-00160","type":"journal-article","created":{"date-parts":[[2026,9,3]],"date-time":"2026-09-03T20:00:11Z","timestamp":1788465611000},"update-policy":"https:\/\/doi.org\/10.1200\/crossmark","source":"Crossref","is-referenced-by-count":0,"title":["Accuracy of Retrieval-Augmented Large Language Model\u2013Generated Preconsult Summaries in Breast Surgical Oncology"],"prefix":"10.1200","volume":"10","author":[{"ORCID":"https:\/\/orcid.org\/0000-0002-1117-401X","authenticated-orcid":true,"given":"Tracy-Ann","family":"Moo","sequence":"first","affiliation":[{"name":"Department of Surgery, Breast Service, Memorial Sloan Kettering Cancer Center, New York, NY"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0009-0004-9557-9330","authenticated-orcid":true,"given":"Robert","family":"James","sequence":"additional","affiliation":[{"name":"Department of Surgery, Breast Service, Memorial Sloan Kettering Cancer Center, New York, NY"},{"name":"Department of Epidemiology and Biostatistics, Biostatistics Service, Memorial Sloan Kettering Cancer Center, New York, NY"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-8765-2690","authenticated-orcid":true,"given":"Solange","family":"Bayard","sequence":"additional","affiliation":[{"name":"Department of Surgery, Breast Service, Memorial Sloan Kettering Cancer Center, New York, NY"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Andreas","family":"Giannakou","sequence":"additional","affiliation":[{"name":"Department of Surgery, Breast Service, Memorial Sloan Kettering Cancer Center, New York, NY"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Lisa R.","family":"Allen","sequence":"additional","affiliation":[{"name":"Department of Surgery, Breast Service, Memorial Sloan Kettering Cancer Center, New York, NY"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-3511-369X","authenticated-orcid":true,"given":"Giacomo","family":"Montagna","sequence":"additional","affiliation":[{"name":"Department of Surgery, Breast Service, Memorial Sloan Kettering Cancer Center, New York, NY"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0009-0004-4545-1005","authenticated-orcid":true,"given":"Ivan","family":"Pan","sequence":"additional","affiliation":[{"name":"Department of Data and Analytics, Artificial Intelligence &amp; Machine Learning (AIML), Memorial Sloan Kettering Cancer Center, New York, NY"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Varadan","family":"Sevilimedu","sequence":"additional","affiliation":[{"name":"Department of Epidemiology and Biostatistics, Biostatistics Service, Memorial Sloan Kettering Cancer Center, New York, NY"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-2427-3532","authenticated-orcid":true,"given":"Sarah","family":"Eskreis-Winkler","sequence":"additional","affiliation":[{"name":"Department of Radiology, Memorial Sloan Kettering Cancer Center, New York, NY"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-4636-8313","authenticated-orcid":true,"given":"Monica","family":"Morrow","sequence":"additional","affiliation":[{"name":"Department of Surgery, Breast Service, Memorial Sloan Kettering Cancer Center, New York, NY"}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"233","reference":[{"key":"e_1_3_5_2_2","doi-asserted-by":"publisher","DOI":"10.3414\/ME0569"},{"key":"e_1_3_5_3_2","doi-asserted-by":"publisher","DOI":"10.1016\/j.ijmedinf.2014.12.001"},{"key":"e_1_3_5_4_2","doi-asserted-by":"publisher","DOI":"10.2196\/24014"},{"key":"e_1_3_5_5_2","doi-asserted-by":"publisher","DOI":"10.1093\/jamia\/ocab009"},{"key":"e_1_3_5_6_2","doi-asserted-by":"publisher","DOI":"10.1002\/cncr.70050"},{"key":"e_1_3_5_7_2","doi-asserted-by":"publisher","DOI":"10.1016\/j.annemergmed.2024.01.039"},{"key":"e_1_3_5_8_2","doi-asserted-by":"publisher","DOI":"10.1038\/s41746-023-00896-7"},{"key":"e_1_3_5_9_2","doi-asserted-by":"publisher","DOI":"10.1038\/s41598-025-28767-z"},{"key":"e_1_3_5_10_2","doi-asserted-by":"publisher","DOI":"10.1016\/j.ijmedinf.2025.106022"},{"key":"e_1_3_5_11_2","doi-asserted-by":"publisher","DOI":"10.2196\/65984"},{"key":"e_1_3_5_12_2","doi-asserted-by":"publisher","DOI":"10.1038\/s41591-024-02855-5"},{"key":"e_1_3_5_13_2","doi-asserted-by":"publisher","DOI":"10.1038\/s41591-024-02970-3"},{"key":"e_1_3_5_14_2","doi-asserted-by":"publisher","DOI":"10.1001\/jamanetworkopen.2024.0357"},{"key":"e_1_3_5_15_2","doi-asserted-by":"publisher","DOI":"10.1001\/jama.2023.9630"},{"key":"e_1_3_5_16_2","doi-asserted-by":"publisher","unstructured":"Joseph E Vallee P Perennec T et al: Development and assessment of a pipeline for extracting structured data from free-text medical reports using a large language model. JCO Clin Cancer Inform 10.1200\/CCI-25-00133","DOI":"10.1200\/CCI-25-00133"},{"key":"e_1_3_5_17_2","doi-asserted-by":"publisher","DOI":"10.1200\/JCO.2025.43.16_suppl.e13593"},{"key":"e_1_3_5_18_2","doi-asserted-by":"publisher","DOI":"10.1001\/jamainternmed.2025.0821"},{"key":"e_1_3_5_19_2","doi-asserted-by":"publisher","DOI":"10.1001\/jamanetworkopen.2025.26339"},{"key":"e_1_3_5_20_2","doi-asserted-by":"publisher","DOI":"10.1038\/s41598-025-24659-4"},{"key":"e_1_3_5_21_2","volume-title":"Guidance on the Responsible Use of Artificial Intelligence in Healthcare","author":"The Joint Commission; Coalition for Health AI (CHAI)","year":"2025","unstructured":"The Joint Commission; Coalition for Health AI (CHAI): Guidance on the Responsible Use of Artificial Intelligence in Healthcare, 2025"},{"key":"e_1_3_5_22_2","doi-asserted-by":"publisher","DOI":"10.2196\/81604"},{"key":"e_1_3_5_23_2","doi-asserted-by":"publisher","DOI":"10.1001\/jamanetworkopen.2025.37000"},{"key":"e_1_3_5_24_2","doi-asserted-by":"publisher","DOI":"10.1136\/bmjopen-2025-099301"},{"key":"e_1_3_5_25_2","doi-asserted-by":"publisher","DOI":"10.1093\/jamia\/ocae209"},{"key":"e_1_3_5_26_2","doi-asserted-by":"publisher","DOI":"10.1001\/jama.2025.23059"}],"container-title":["JCO Clinical Cancer Informatics"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/ascopubs.org\/doi\/pdfdirect\/10.1200\/CCI-26-00160","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,9,3]],"date-time":"2026-09-03T20:00:12Z","timestamp":1788465612000},"score":1,"resource":{"primary":{"URL":"https:\/\/ascopubs.org\/doi\/10.1200\/CCI-26-00160"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026,7]]},"references-count":25,"journal-issue":{"issue":"3","published-print":{"date-parts":[[2026,7]]}},"alternative-id":["10.1200\/CCI-26-00160"],"URL":"https:\/\/doi.org\/10.1200\/cci-26-00160","relation":{},"ISSN":["2473-4276"],"issn-type":[{"value":"2473-4276","type":"electronic"}],"subject":[],"published":{"date-parts":[[2026,7]]},"assertion":[{"value":"2026-05-15","order":0,"name":"received","label":"Received","group":{"name":"publication_history","label":"Publication History"}},{"value":"2026-06-24","order":1,"name":"revised","label":"Revised","group":{"name":"publication_history","label":"Publication History"}},{"value":"2026-07-28","order":2,"name":"accepted","label":"Accepted","group":{"name":"publication_history","label":"Publication History"}},{"value":"2026-09-03","order":3,"name":"published","label":"Published","group":{"name":"publication_history","label":"Publication History"}}],"article-number":"e2600160"}}