{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,9,4]],"date-time":"2026-09-04T03:55:09Z","timestamp":1788494109577,"version":"build-2803163510"},"reference-count":29,"publisher":"Ovid Technologies (Wolters Kluwer Health)","issue":"3","license":[{"start":{"date-parts":[[2026,2,2]],"date-time":"2026-02-02T00:00:00Z","timestamp":1769990400000},"content-version":"unspecified","delay-in-days":0,"URL":"http:\/\/creativecommons.org\/licenses\/by-nc-nd\/4.0\/"}],"content-domain":{"domain":["lww.com","ovid.com"],"crossmark-restriction":true},"short-container-title":[],"published-print":{"date-parts":[[2026,3]]},"abstract":"<jats:sec>\n                    <jats:title>Objectives:<\/jats:title>\n                    <jats:p>To evaluate the application value of three ChatGPT versions and Gemini in pathology report simplification tasks for prostate cancer.<\/jats:p>\n                  <\/jats:sec>\n                  <jats:sec>\n                    <jats:title>Methods:<\/jats:title>\n                    <jats:p>\n                      This retrospective study assessed GPT-3.5, GPT-4.0, GPT-4o, and Gemini on pathology reports from 228 prostate cancer patients across two institutions. Data were split into internal (center 1,\n                      <jats:italic toggle=\"yes\">n<\/jats:italic>\n                      =\u00a0171) and external (center 2,\n                      <jats:italic toggle=\"yes\">n<\/jats:italic>\n                      =\u00a057) cohorts. Using specific prompts, models generated simplified texts. The evaluation of outputs included three main dimensions: (1) human scoring by patients, clinicians, and pathologists; (2) readability scores; and (3) BERT-based semantic similarity scores. Statistical comparisons employed paired\n                      <jats:italic toggle=\"yes\">t<\/jats:italic>\n                      -tests or Wilcoxon signed-rank tests. Statistical consistency between raters was assessed using squared weighted kappa, intraclass correlation coefficient(3,1), and percent agreement, with 95% confidence intervals calculated for all metrics.\n                    <\/jats:p>\n                  <\/jats:sec>\n                  <jats:sec>\n                    <jats:title>Results:<\/jats:title>\n                    <jats:p>GPT-4o (Few-Shot) achieved the highest accuracy and comprehensiveness scores from pathologists, while Gemini demonstrated the best understandability. Patient and clinician understandability ratings were consistently high across models. Mean Reading Grade Level scores varied between internal and external datasets, with GPT-4o Few-Shot performing best overall. BERT-based semantic similarity scores demonstrated distinct trends across models, reflecting differences in text simplification strategies.<\/jats:p>\n                  <\/jats:sec>\n                  <jats:sec>\n                    <jats:title>Conclusion:<\/jats:title>\n                    <jats:p>LLMs adopt distinct trade-off strategies between simplifying pathology reports and preserving their structure and logic, influenced by prompt design and textual style. Their application shows potential to enhance patient comprehension and clinical communication. Future work should focus on domain-specific fine-tuning to ensure safe and reliable clinical integration.<\/jats:p>\n                  <\/jats:sec>","DOI":"10.1097\/js9.0000000000004454","type":"journal-article","created":{"date-parts":[[2026,2,3]],"date-time":"2026-02-03T15:00:44Z","timestamp":1770130844000},"page":"5733-5741","update-policy":"https:\/\/doi.org\/10.1097\/lww.0000000000001000","source":"Crossref","is-referenced-by-count":2,"title":["A comparative evaluation of large language models for simplifying prostate cancer pathology reports: ChatGPT and Gemini"],"prefix":"10.1097","volume":"112","author":[{"ORCID":"https:\/\/orcid.org\/0000-0002-0771-2700","authenticated-orcid":false,"given":"Haoyang","family":"Zeng","sequence":"first","affiliation":[{"name":"Department of Radiology, The Third Affiliated Hospital of Shenzhen University (Luohu People\u2019s Hospital), Shenzhen, China"},{"name":"Laboratory of Interventional Radiology, Department of Minimally Invasive Interventional Radiology and Interventional Cancer Center, The Second Affiliated Hospital, Guangzhou Medical University, Guangzhou, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Yangguang","family":"Yuan","sequence":"additional","affiliation":[{"name":"Department of Radiology, The Third Affiliated Hospital of Shenzhen University (Luohu People\u2019s Hospital), Shenzhen, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Xiang","family":"Wu","sequence":"additional","affiliation":[{"name":"Department of Emergency, The Third Affiliated Hospital of Shenzhen University (Luohu People\u2019s Hospital), Shenzhen, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Zixi","family":"Ye","sequence":"additional","affiliation":[{"name":"Department of Medical College, Shantou University, Shantou, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Haoyuan","family":"Yuan","sequence":"additional","affiliation":[{"name":"Department of Medical College, Shantou University, Shantou, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Shimei","family":"Luo","sequence":"additional","affiliation":[{"name":"Department of Radiology, The Third Affiliated Hospital of Shenzhen University (Luohu People\u2019s Hospital), Shenzhen, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Kun","family":"Zhang","sequence":"additional","affiliation":[{"name":"Department of Radiology, The Third Affiliated Hospital of Shenzhen University (Luohu People\u2019s Hospital), Shenzhen, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Lei","family":"Wang","sequence":"additional","affiliation":[{"name":"Department of Radiology, The Third Affiliated Hospital of Shenzhen University (Luohu People\u2019s Hospital), Shenzhen, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Hanlin","family":"Liu","sequence":"additional","affiliation":[{"name":"Department of Radiology, The Third Affiliated Hospital of Shenzhen University (Luohu People\u2019s Hospital), Shenzhen, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0009-0004-5583-8203","authenticated-orcid":false,"given":"Huancheng","family":"Yang","sequence":"additional","affiliation":[{"name":"Department of Radiology, The Third Affiliated Hospital of Shenzhen University (Luohu People\u2019s Hospital), Shenzhen, China"}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"276","published-online":{"date-parts":[[2026,2,2]]},"reference":[{"key":"R1-20260417","doi-asserted-by":"crossref","first-page":"1166120","DOI":"10.3389\/fpubh.2023.1166120","article-title":"ChatGPT and the rise of large language models: the new AI-driven infodemic threat in public health","volume":"11","author":"De Angelis","year":"2023","journal-title":"Front Public Health"},{"key":"R2-20260417","doi-asserted-by":"crossref","first-page":"7532\u201341","DOI":"10.1007\/s00330-023-09812-9","article-title":"An automated surgical decision-making framework for partial or radical nephrectomy based on 3D-CT multi-level anatomical features in renal cell carcinoma","volume":"33","author":"Yang","year":"2023","journal-title":"Eur Radiol"},{"key":"R3-20260417","doi-asserted-by":"crossref","first-page":"7105\u201316","DOI":"10.21037\/qims-23-142","article-title":"A quantitative analysis framework of placenta accreta spectrum: placenta subtype, intraoperative bleeding, and hysterectomy risk evaluation based on magnetic resonance imaging-anatomical-clinical features","volume":"13","author":"Yang","year":"2023","journal-title":"Quant Imaging Med Surg"},{"key":"R4-20260417","doi-asserted-by":"crossref","first-page":"354","DOI":"10.1186\/s12909-024-05239-y","article-title":"Large language models for generating medical examinations: systematic review","volume":"24","author":"Artsi","year":"2024","journal-title":"BMC Med Educ"},{"key":"R5-20260417","doi-asserted-by":"crossref","first-page":"210\u201320","DOI":"10.7326\/M23-2772","article-title":"Large language models in medicine: the potentials and pitfalls: a narrative review","volume":"177","author":"Omiye","year":"2024","journal-title":"Ann Intern Med"},{"key":"R6-20260417","doi-asserted-by":"crossref","first-page":"22","DOI":"10.1007\/s10916-024-02045-3","article-title":"The breakthrough of large language models release for medical applications: 1-year timeline and perspectives","volume":"48","author":"Cascella","year":"2024","journal-title":"J Med Syst"},{"key":"R7-20260417","doi-asserted-by":"crossref","first-page":"100101","DOI":"10.1016\/j.acpath.2023.100101","article-title":"Establishing priorities for implementation of large language models in pathology and laboratory medicine","volume":"11","author":"Arvisais-Anhalt","year":"2024","journal-title":"Acad Pathol"},{"key":"R8-20260417","first-page":"220\u201324","article-title":"ChatGPT: chances and challenges for dentistry","volume":"44","author":"Eggmann","year":"2023","journal-title":"Compend Contin Educ Dent"},{"key":"R9-20260417","doi-asserted-by":"crossref","first-page":"379\u201394","DOI":"10.1097\/ALN.0000000000002960","article-title":"Artificial Intelligence in anesthesiology: current techniques, clinical applications, and limitations","volume":"132","author":"Hashimoto","year":"2020","journal-title":"Anesthesiology"},{"key":"R10-20260417","doi-asserted-by":"crossref","first-page":"831\u201337","DOI":"10.1016\/j.surg.2022.05.007","article-title":"Patient comprehension of breast pathology report terminology: the need for patient-centered resources","volume":"172","author":"Verosky","year":"2022","journal-title":"Surgery"},{"key":"R11-20260417","doi-asserted-by":"crossref","first-page":"9","DOI":"10.1038\/s41572-020-00243-0","article-title":"Prostate cancer","volume":"7","author":"Rebello","year":"2021","journal-title":"Nat Rev Dis Primers"},{"key":"R12-20260417","first-page":"231\u201338","article-title":"Locally advanced prostate cancer. Definition, diagnosis and treatment","volume":"71","author":"Mayor de Castro","year":"2018","journal-title":"Arch Esp Urol"},{"key":"R13-20260417","doi-asserted-by":"crossref","first-page":"5730","DOI":"10.3390\/molecules27175730","article-title":"Prostate cancer review: genetics, diagnosis, treatment options, and alternative approaches","volume":"27","author":"Sekhoacha","year":"2022","journal-title":"Molecules"},{"key":"R14-20260417","doi-asserted-by":"crossref","first-page":"1091\u201394","DOI":"10.1016\/j.urolonc.2014.04.011","article-title":"Readability of urologic pathology reports: the need for patient-centered approaches","volume":"32","author":"Mossanen","year":"2014","journal-title":"Urol Oncol"},{"key":"R15-20260417","doi-asserted-by":"crossref","first-page":"521\u201328","DOI":"10.1093\/ajcp\/aqab014","article-title":"Addressing the diagnostic miscommunication in pathology","volume":"156","author":"Mirham","year":"2021","journal-title":"Am J Clin Pathol"},{"key":"R16-20260417","doi-asserted-by":"crossref","first-page":"e231593","DOI":"10.1148\/radiol.231593","article-title":"Quantitative evaluation of large language models to streamline radiology report impressions: a multimodal retrospective analysis","volume":"310","author":"Doshi","year":"2024","journal-title":"Radiology"},{"key":"R17-20260417","first-page":"100081","article-title":"Revised strengthening the reporting of cohort, cross-sectional and case-control studies in surgery (STROCSS) guideline: an update for the age of Artificial Intelligence","volume":"10","author":"Mathew","year":"2025","journal-title":"Prem J Sci"},{"key":"R18-20260417","doi-asserted-by":"crossref","first-page":"e2532956","DOI":"10.2214\/AJR.25.32956","article-title":"Prompt engineering for large language models in interventional radiology","volume":"225","author":"Dietrich","year":"2025","journal-title":"AJR Am J Roentgenol"},{"key":"R19-20260417","doi-asserted-by":"crossref","first-page":"100731","DOI":"10.1016\/j.hjdsi.2023.100731","article-title":"Large language models as a source of health information: are they patient-centered? A longitudinal analysis","volume":"12","author":"Amin","year":"2024","journal-title":"Healthc (Amst)"},{"key":"R20-20260417","doi-asserted-by":"crossref","first-page":"e232561","DOI":"10.1148\/radiol.232561","article-title":"Accuracy of ChatGPT, google bard, and microsoft bing for simplifying radiology reports","volume":"309","author":"Amin","year":"2023","journal-title":"Radiology"},{"key":"R21-20260417","first-page":"e1575","article-title":"Patient education materials found via Google search for shoulder arthroscopy are written at too-high of a reading level","volume":"4","author":"Abdullah","year":"2022","journal-title":"Arthrosc Sports Med Rehabil"},{"key":"R22-20260417","article-title":"Accessibility to puberphonia online and its readability by patients","author":"Aljawi","journal-title":"J Voice"},{"key":"R23-20260417","doi-asserted-by":"crossref","first-page":"284\u201390","DOI":"10.1177\/18632521231156435","article-title":"Readability assessment of patient educational materials for pediatric spinal conditions from top academic orthopedic institutions","volume":"17","author":"Michel","year":"2023","journal-title":"J Child Orthop"},{"key":"R24-20260417","first-page":"868\u201376","article-title":"Prostate magnetic resonance imaging for local recurrence reporting (PI-RR): international consensus -based guidelines on multiparametric magnetic resonance imaging for prostate cancer recurrence after radiation therapy and radical prostatectomy","volume":"4","author":"Panebianco","year":"2021","journal-title":"Eur Urol Oncol"},{"key":"R25-20260417","doi-asserted-by":"crossref","first-page":"e48392","DOI":"10.2196\/48392","article-title":"The ChatGPT (Generative Artificial Intelligence) revolution has made artificial intelligence approachable for medical professionals","volume":"25","author":"Mesko","year":"2023","journal-title":"J Med Internet Res"},{"key":"R26-20260417","doi-asserted-by":"crossref","first-page":"141","DOI":"10.1038\/s43856-023-00370-1","article-title":"The future landscape of large language models in medicine","volume":"3","author":"Clusmann","year":"2023","journal-title":"Commun Med (Lond)"},{"key":"R27-20260417","doi-asserted-by":"crossref","first-page":"bbad226","DOI":"10.1093\/bib\/bbad226","article-title":"PharmBERT: a domain-specific BERT model for drug labels","volume":"24","author":"ValizadehAslani","year":"2023","journal-title":"Brief Bioinform"},{"key":"R28-20260417","doi-asserted-by":"crossref","first-page":"115667","DOI":"10.1016\/j.psychres.2023.115667","article-title":"Beyond rating scales: with targeted evaluation, large language models are poised for psychological assessment","volume":"333","author":"Kjell","year":"2024","journal-title":"Psychiatry Res"},{"key":"R29-20260417","doi-asserted-by":"crossref","first-page":"104106","DOI":"10.1016\/j.jbi.2022.104106","article-title":"A comparative evaluation of biomedical similar article recommendation","volume":"131","author":"Zhang","year":"2022","journal-title":"J Biomed Inform"}],"container-title":["International Journal of Surgery"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/journals.lww.com\/10.1097\/JS9.0000000000004454","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,4,17]],"date-time":"2026-04-17T11:06:54Z","timestamp":1776424014000},"score":1,"resource":{"primary":{"URL":"https:\/\/journals.lww.com\/10.1097\/JS9.0000000000004454"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026,2,2]]},"references-count":29,"journal-issue":{"issue":"3","published-print":{"date-parts":[[2026]]}},"URL":"https:\/\/doi.org\/10.1097\/js9.0000000000004454","relation":{},"ISSN":["1743-9159"],"issn-type":[{"value":"1743-9159","type":"electronic"}],"subject":[],"published":{"date-parts":[[2026,2,2]]},"assertion":[{"value":"2025-06-10","name":"received","label":"Received","group":{"name":"publication_history","label":"Publication History"}},{"value":"2025-11-25","name":"accepted","label":"Accepted","group":{"name":"publication_history","label":"Publication History"}}]}}