{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,9,17]],"date-time":"2026-09-17T18:11:52Z","timestamp":1789668712490,"version":"4.0.1"},"reference-count":29,"publisher":"Springer Science and Business Media LLC","issue":"10","license":[{"start":{"date-parts":[[2026,7,15]],"date-time":"2026-07-15T00:00:00Z","timestamp":1784073600000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0"},{"start":{"date-parts":[[2026,7,15]],"date-time":"2026-07-15T00:00:00Z","timestamp":1784073600000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0"}],"content-domain":{"domain":["link.springer.com"],"crossmark-restriction":false},"short-container-title":["Ann Surg Oncol"],"published-print":{"date-parts":[[2026,10]]},"abstract":"<jats:title>Abstract<\/jats:title>\n                  <jats:sec>\n                    <jats:title>Background<\/jats:title>\n                    <jats:p>Reviewing pathology, imaging, and consultation documents in oncology can be time-consuming, particularly when records originate from external facilities in different file formats. This study aimed to evaluate the impact of a Retrieval-Augmented Generation (RAG)-enabled GPT-4o summarization agent on clinical workflows and quality of outside-record summaries in breast surgical oncology.<\/jats:p>\n                  <\/jats:sec>\n                  <jats:sec>\n                    <jats:title>Methods<\/jats:title>\n                    <jats:p>Initial performance evaluation of a GPT-4o\/RAG agent to generate summaries of oncologic reports in 50 charts followed by a prospective pilot test of sequential cases, with each AI summary evaluated using a modified Provider Documentation Summarization Quality Instrument (PDSQI-9; 1\u20135 Likert scale), including dichotomized ratings (low [1\u20133], high [4, 5]), binomial testing, frequency and type of user-reported errors, clinician-coded error criticality (treatment-impacting vs noncritical). Pre- and post-use survey of documentation burden (NASA TLX) and user experience was performed.<\/jats:p>\n                  <\/jats:sec>\n                  <jats:sec>\n                    <jats:title>Results<\/jats:title>\n                    <jats:p>Among 62 cases, AI-generated summaries were rated high for accuracy, usefulness, succinctness, and source citation. Thoroughness without omission was rated low in 28 (45%) summaries. Errors were noted in 25 (40%) surveys, with 13 (52%) classified as critical (treatment-impacting). The most common error type involved imaging, reported in 17 (68%) cases. For perceived time savings, the median response was neutral, but qualitative feedback described the tool as helpful for straightforward cases and as reducing typing burden but requiring workflow adjustment and improvements for complex cases.<\/jats:p>\n                  <\/jats:sec>\n                  <jats:sec>\n                    <jats:title>Conclusions<\/jats:title>\n                    <jats:p>Although users rated RAG-enabled GPT-4o agent-generated documentation summaries favorably on several quality domains, they frequently lacked thoroughness and occasionally contained treatment-relevant errors. Human review and further iteration of the technology remain necessary before implementation.<\/jats:p>\n                  <\/jats:sec>","DOI":"10.1245\/s10434-026-20170-w","type":"journal-article","created":{"date-parts":[[2026,7,15]],"date-time":"2026-07-15T12:49:29Z","timestamp":1784119769000},"page":"9102-9109","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":1,"title":["Artificial Intelligence-Generated Electronic Medical Record Summarization in Breast Surgical Oncology"],"prefix":"10.1245","volume":"33","author":[{"given":"Ko Un","family":"Park","sequence":"first","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Bergen K.","family":"Sather","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Anika","family":"Shah","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Christina A.","family":"Minami","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Matthew","family":"Butler","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Lara","family":"Butler","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Jordan A.","family":"Love","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Kathleen","family":"McLean","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Adam","family":"Dunn","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Elizabeth A.","family":"Mittendorf","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Tari A.","family":"King","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"297","published-online":{"date-parts":[[2026,7,15]]},"reference":[{"key":"20170_CR1","doi-asserted-by":"publisher","first-page":"1134","DOI":"10.1038\/s41591-024-02855-5","volume":"30","author":"D Van Veen","year":"2024","unstructured":"Van Veen D, Van Uden C, Blankemeier L, et al. Adapted large language models can outperform medical experts in clinical text summarization. Nat Med. 2024;30:1134\u201342. https:\/\/doi.org\/10.1038\/s41591-024-02855-5.","journal-title":"Nat Med."},{"key":"20170_CR2","doi-asserted-by":"publisher","first-page":"9871","DOI":"10.18653\/v1\/2023.acl-long.549","volume":"2023","author":"LL Wang","year":"2023","unstructured":"Wang LL, Otmakhova Y, DeYoung J, et al. Automated metrics for medical multi-document summarization disagree with human evaluations. Proc Conf Assoc Comput Linguist Meet. 2023;2023:9871\u201389. https:\/\/doi.org\/10.18653\/v1\/2023.acl-long.549.","journal-title":"Proc Conf Assoc Comput Linguist Meet."},{"key":"20170_CR3","doi-asserted-by":"publisher","first-page":"158","DOI":"10.1038\/s41746-023-00896-7","volume":"6","author":"L Tang","year":"2023","unstructured":"Tang L, Sun Z, Idnay B, et al. Evaluating large language models on medical evidence summarization. Npj Digit Med. 2023;6:158. https:\/\/doi.org\/10.1038\/s41746-023-00896-7.","journal-title":"Npj Digit Med."},{"key":"20170_CR4","doi-asserted-by":"publisher","DOI":"10.1371\/journal.pdig.0000877","volume":"4","author":"LM Amugongo","year":"2025","unstructured":"Amugongo LM, Mascheroni P, Brooks S, Doering S, Seidel J. Retrieval augmented generation for large language models in healthcare: a systematic review. PLOS Digit Health. 2025;4:e0000877. https:\/\/doi.org\/10.1371\/journal.pdig.0000877.","journal-title":"PLOS Digit Health."},{"key":"20170_CR5","doi-asserted-by":"publisher","first-page":"60","DOI":"10.1038\/s41591-024-03425-5","volume":"31","author":"J Gallifant","year":"2025","unstructured":"Gallifant J, Afshar M, Ameen S, et al. The TRIPOD-LLM reporting guideline for studies using large language models. Nat Med. 2025;31:60\u20139. https:\/\/doi.org\/10.1038\/s41591-024-03425-5.","journal-title":"Nat Med."},{"key":"20170_CR6","doi-asserted-by":"publisher","unstructured":"Boone H, Boone D. Analyzing Likert data. J Ext. 2012;50. https:\/\/doi.org\/10.34068\/joe.50.02.48.","DOI":"10.34068\/joe.50.02.48"},{"key":"20170_CR7","doi-asserted-by":"publisher","first-page":"131","DOI":"10.1080\/19488300.2011.609524","volume":"1","author":"P Hoonakker","year":"2011","unstructured":"Hoonakker P, Carayon P, Gurses A, et al. Measuring workload of ICU nurses with a questionnaire survey: the NASA Task Load Index (TLX). IIE Trans Healthc Syst Eng. 2011;1:131\u201343. https:\/\/doi.org\/10.1080\/19488300.2011.609524.","journal-title":"IIE Trans Healthc Syst Eng."},{"key":"20170_CR8","doi-asserted-by":"publisher","first-page":"61","DOI":"10.1111\/j.1464-0597.2004.00161.x","volume":"53","author":"S Rubio","year":"2004","unstructured":"Rubio S, D\u00edaz E, Mart\u00edn J, Puente JM. Evaluation of subjective mental workload: a comparison of SWAT, NASA-TLX, and workload profile methods. Appl Psychol Int Rev. 2004;53:61\u201386. https:\/\/doi.org\/10.1111\/j.1464-0597.2004.00161.x.","journal-title":"Appl Psychol Int Rev."},{"key":"20170_CR9","doi-asserted-by":"publisher","unstructured":"Hart SG. NASA-Task Load Index (NASA-TLX): 20 years later. Published online 2006. https:\/\/doi.org\/10.1037\/e577632012-009.","DOI":"10.1037\/e577632012-009"},{"key":"20170_CR10","doi-asserted-by":"publisher","first-page":"1050","DOI":"10.1093\/jamia\/ocaf068","volume":"32","author":"E Croxford","year":"2025","unstructured":"Croxford E, Gao Y, Pellegrino N, et al. Development and validation of the provider documentation summarization quality instrument for large language models. JAMIA J Am Med Inform Assoc. 2025;32:1050\u201360. https:\/\/doi.org\/10.1093\/jamia\/ocaf068.","journal-title":"JAMIA J Am Med Inform Assoc."},{"key":"20170_CR11","doi-asserted-by":"publisher","first-page":"175","DOI":"10.1509\/jmkr.44.2.175","volume":"44","author":"L Bergkvist","year":"2007","unstructured":"Bergkvist L, Rossiter JR. The predictive validity of multiple-item versus single-item measures of the same constructs. J Mark Res. 2007;44:175\u201384. https:\/\/doi.org\/10.1509\/jmkr.44.2.175.","journal-title":"J Mark Res."},{"key":"20170_CR12","doi-asserted-by":"publisher","DOI":"10.1093\/jamiaopen\/ooaf082","author":"L Shemtob","year":"2025","unstructured":"Shemtob L, Nouri A, Harvey-Sullivan A, et al. Comparing artificial intelligence- vs clinician-authored summaries of simulated primary care electronic health records. JAMIA Open. 2025. https:\/\/doi.org\/10.1093\/jamiaopen\/ooaf082.","journal-title":"JAMIA Open."},{"key":"20170_CR13","doi-asserted-by":"publisher","DOI":"10.1001\/jamanetworkopen.2025.26339","volume":"8","author":"WR Small","year":"2025","unstructured":"Small WR, Austrian J, O\u2019Donnell L, et al. Evaluating hospital course summarization by an electronic health record-based large language model. JAMA Netw Open. 2025;8:e2526339. https:\/\/doi.org\/10.1001\/jamanetworkopen.2025.26339.","journal-title":"JAMA Netw Open."},{"key":"20170_CR14","doi-asserted-by":"publisher","DOI":"10.1001\/jamanetworkopen.2024.48723","volume":"7","author":"V Hartman","year":"2024","unstructured":"Hartman V, Zhang X, Poddar R, et al. Developing and evaluating large language model-generated emergency medicine handoff notes. JAMA Netw Open. 2024;7:e2448723. https:\/\/doi.org\/10.1001\/jamanetworkopen.2024.48723.","journal-title":"JAMA Netw Open."},{"key":"20170_CR15","first-page":"312","volume":"2025","author":"AS Liang","year":"2025","unstructured":"Liang AS, Banda JM, Savage T, et al. Feasibility of automated precharting using GPT-4 in new specialty referrals. AMIA Summits Transl Sci Proc. 2025;2025:312\u201321.","journal-title":"AMIA Summits Transl Sci Proc."},{"key":"20170_CR16","doi-asserted-by":"publisher","DOI":"10.1101\/2025.06.02.25328807","author":"R Verma","year":"2025","unstructured":"Verma R, Alsentzer E, Strasser Z, et al. Verifiable summarization of electronic health records using large language models to support chart review. MedRxiv Prepr Serv Health Sci. 2025. https:\/\/doi.org\/10.1101\/2025.06.02.25328807.","journal-title":"MedRxiv Prepr Serv Health Sci."},{"key":"20170_CR17","doi-asserted-by":"publisher","DOI":"10.1001\/jamanetworkopen.2025.38427","volume":"8","author":"JW Song","year":"2025","unstructured":"Song JW, Park J, Kim JH, You SC. Large language model assistant for emergency department discharge documentation. JAMA Netw Open. 2025;8:e2538427. https:\/\/doi.org\/10.1001\/jamanetworkopen.2025.38427.","journal-title":"JAMA Netw Open."},{"issue":"16 Suppl","key":"20170_CR18","doi-asserted-by":"publisher","first-page":"1523","DOI":"10.1200\/JCO.2024.42.16","volume":"42","author":"PHCC Chen","year":"2024","unstructured":"Chen PHCC, Jung JJ, Kim Y, et al. AI-assisted clinical summary and treatment planning for cancer care: a comparative study of human vs AI-based approaches. J Clin Oncol. 2024;42(16 Suppl):1523. https:\/\/doi.org\/10.1200\/JCO.2024.42.16.","journal-title":"J Clin Oncol."},{"key":"20170_CR19","doi-asserted-by":"publisher","first-page":"11654","DOI":"10.1038\/s41598-022-15245-z","volume":"12","author":"D Vela","year":"2022","unstructured":"Vela D, Sharp A, Zhang R, Nguyen T, Hoang A, Pianykh OS. Temporal quality degradation in AI models. Sci Rep. 2022;12:11654. https:\/\/doi.org\/10.1038\/s41598-022-15245-z.","journal-title":"Sci Rep."},{"key":"20170_CR20","doi-asserted-by":"publisher","DOI":"10.1056\/AIdbp2500418","author":"P Chung","year":"2025","unstructured":"Chung P, Swaminathan A, Goodell AJ, et al. Verifying facts in patient care documents generated by large language models using electronic health records. NEJM AI. 2025. https:\/\/doi.org\/10.1056\/AIdbp2500418.","journal-title":"NEJM AI."},{"key":"20170_CR21","doi-asserted-by":"publisher","first-page":"1253","DOI":"10.1093\/jnci\/djaf052","volume":"117","author":"AJ Holmgren","year":"2025","unstructured":"Holmgren AJ, Apathy NC, Crews J, Shanafelt T. National trends in oncology specialists\u2019 EHR inbox work, 2019\u20132022. JNCI J Natl Cancer Inst. 2025;117:1253\u20139. https:\/\/doi.org\/10.1093\/jnci\/djaf052.","journal-title":"JNCI J Natl Cancer Inst."},{"key":"20170_CR22","doi-asserted-by":"publisher","first-page":"857","DOI":"10.1055\/s-0042-1756422","volume":"13","author":"T Ebbers","year":"2022","unstructured":"Ebbers T, Kool RB, Smeele LE, Takes RP, van den Broek GB, Dirven R. Quantifying the electronic health record burden in head and neck cancer care. Appl Clin Inform. 2022;13:857\u201364. https:\/\/doi.org\/10.1055\/s-0042-1756422.","journal-title":"Appl Clin Inform."},{"key":"20170_CR23","doi-asserted-by":"publisher","DOI":"10.1001\/jamanetworkopen.2025.28056","volume":"8","author":"JG You","year":"2025","unstructured":"You JG, Dbouk RH, Landman A, et al. Ambient documentation technology in clinician experience of documentation burden and burnout. JAMA Netw Open. 2025;8:e2528056. https:\/\/doi.org\/10.1001\/jamanetworkopen.2025.28056.","journal-title":"JAMA Netw Open."},{"key":"20170_CR24","doi-asserted-by":"publisher","DOI":"10.1056\/CAT.25.0040","author":"AA Tierney","year":"2025","unstructured":"Tierney AA, Gayre G, Hoberman B, et al. Ambient artificial intelligence scribes: learnings after 1 year and over 25 million uses. NEJM Catal. 2025. https:\/\/doi.org\/10.1056\/CAT.25.0040.","journal-title":"NEJM Catal."},{"key":"20170_CR25","doi-asserted-by":"publisher","first-page":"106","DOI":"10.1038\/s41746-024-01079-8","volume":"7","author":"J Huang","year":"2024","unstructured":"Huang J, Yang DM, Rong R, et al. A critical assessment of using ChatGPT for extracting structured data from clinical notes. NPJ Digit Med. 2024;7:106. https:\/\/doi.org\/10.1038\/s41746-024-01079-8.","journal-title":"NPJ Digit Med."},{"key":"20170_CR26","doi-asserted-by":"publisher","first-page":"401","DOI":"10.1016\/j.jacr.2015.09.036","volume":"13","author":"HY Pan","year":"2016","unstructured":"Pan HY, Shaitelman SF, Perkins GH, Schlembach PJ, Woodward WA, Smith BD. Implementing a real-time electronic data capture system to improve clinical documentation in radiation oncology. JACR J Am Coll Radiol. 2016;13:401\u20137. https:\/\/doi.org\/10.1016\/j.jacr.2015.09.036.","journal-title":"JACR J Am Coll Radiol."},{"key":"20170_CR27","doi-asserted-by":"publisher","DOI":"10.1136\/bmjoq-2023-002732","author":"G Alonso-J\u00e1udenes Curbera","year":"2024","unstructured":"Alonso-J\u00e1udenes Curbera G, G\u00f3mez-Randulfe Rodr\u00edguez MI, Alonso de Castro B, et al. Improving quality of care by standardising patient data collection in electronic medical records in an oncology department in Spain. BMJ Open Qual. 2024. https:\/\/doi.org\/10.1136\/bmjoq-2023-002732.","journal-title":"BMJ Open Qual"},{"key":"20170_CR28","doi-asserted-by":"publisher","first-page":"174","DOI":"10.1148\/radiol.11101913","volume":"260","author":"LH Schwartz","year":"2011","unstructured":"Schwartz LH, Panicek DM, Berk AR, Li Y, Hricak H. Improving communication of diagnostic radiology findings through structured reporting. Radiology. 2011;260:174\u201381. https:\/\/doi.org\/10.1148\/radiol.11101913.","journal-title":"Radiology."},{"key":"20170_CR29","doi-asserted-by":"publisher","first-page":"20170670","DOI":"10.1259\/bjr.20170670","volume":"91","author":"BW Buckley","year":"2018","unstructured":"Buckley BW, Daly L, Allen GN, Ridge CA. Recall of structured radiology reports is significantly superior to that of unstructured reports. Br J Radiol. 2018;91:20170670. https:\/\/doi.org\/10.1259\/bjr.20170670.","journal-title":"Br J Radiol."}],"container-title":["Annals of Surgical Oncology"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1245\/s10434-026-20170-w.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/link.springer.com\/article\/10.1245\/s10434-026-20170-w","content-type":"text\/html","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1245\/s10434-026-20170-w.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,9,17]],"date-time":"2026-09-17T17:52:19Z","timestamp":1789667539000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1245\/s10434-026-20170-w"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026,7,15]]},"references-count":29,"journal-issue":{"issue":"10","published-print":{"date-parts":[[2026,10]]}},"alternative-id":["20170"],"URL":"https:\/\/doi.org\/10.1245\/s10434-026-20170-w","relation":{},"ISSN":["1068-9265","1534-4681"],"issn-type":[{"value":"1068-9265","type":"print"},{"value":"1534-4681","type":"electronic"}],"subject":[],"published":{"date-parts":[[2026,7,15]]},"assertion":[{"value":"24 March 2026","order":1,"name":"received","label":"Received","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"24 June 2026","order":2,"name":"accepted","label":"Accepted","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"15 July 2026","order":3,"name":"first_online","label":"First Online","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"Elizabeth A. Mittendorf reports compensated service on scientific advisory boards for Astra Zeneca and Merck, uncompensated service on steering committees for Bristol Myers Squibb and Roche\/Genentech, and institutional research support from Roche\/Genentech (via SU2C grant) and Gilead. She also reports research funding from Susan Komen for the Cure, for which she serves as a Scientific Advisor, and uncompensated participation as a member of the American Society of Clinical Oncology Board of Directors. Tari A. King reports speaker honoraria for Exact Sciences, compensated service on the FES Steering Committee for GE Healthcare, compensated service for a Prosigna advisory board role for Veracyte, compensated service on the advisory board for Ataraxia AI, and compensated service as faculty for PrecisCa cancer information service. The remaining authors have no conflicts of interest.","order":1,"name":"Ethics","label":"Disclosure","group":{"name":"EthicsHeading","label":"Ethics"}}]}}