{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,10,2]],"date-time":"2026-10-02T17:43:19Z","timestamp":1790962999933,"version":"4.1.0"},"reference-count":30,"publisher":"Springer Science and Business Media LLC","issue":"2","license":[{"start":{"date-parts":[[2025,8,21]],"date-time":"2025-08-21T00:00:00Z","timestamp":1755734400000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0"},{"start":{"date-parts":[[2025,8,21]],"date-time":"2025-08-21T00:00:00Z","timestamp":1755734400000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0"}],"funder":[{"DOI":"10.13039\/100000054","name":"U.S. Department of Health & Human Services | NIH | National Cancer Institute","doi-asserted-by":"publisher","award":["K08 CA230155"],"award-info":[{"award-number":["K08 CA230155"]}],"id":[{"id":"10.13039\/100000054","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/100000050","name":"U.S. Department of Health & Human Services | NIH | National Heart, Lung, and Blood Institute","doi-asserted-by":"publisher","award":["nadine.friedrich@cshs.org"],"award-info":[{"award-number":["nadine.friedrich@cshs.org"]}],"id":[{"id":"10.13039\/100000050","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":["link.springer.com"],"crossmark-restriction":false},"short-container-title":["Prostate Cancer Prostatic Dis"],"published-print":{"date-parts":[[2026,6]]},"abstract":"<jats:title>Abstract<\/jats:title>\n                  <jats:sec>\n                    <jats:title>Background<\/jats:title>\n                    <jats:p>AUA guidelines for shared decision making (SDM) in prostate cancer recommend discussion of five content areas in consultations: (1) cancer severity (tumor risk (TR), pathology results (PR)); (2) life expectancy (LE); (3) cancer prognosis (CP); (4) baseline urinary and erectile function (UF and EF); and (5) treatment side effects (erectile dysfunction (ED), urinary incontinence (UI), and irritative urinary symptoms (LUTS)). However, patient retention of information after the visit and inconsistent risk communication by physicians are barriers to informed SDM. We sought to develop natural language processing (NLP) models based on recorded consultations to provide key information to patients and audit quality of physician communication.<\/jats:p>\n                  <\/jats:sec>\n                  <jats:sec>\n                    <jats:title>Methods<\/jats:title>\n                    <jats:p>We used 50 consultation transcripts to train and validate NLP models to identify sentences related to key concepts. We then tested whether communication quality across entire consultations could be determined by sentences with the highest model-predicted topic concordance in 20 separate consultation transcripts.<\/jats:p>\n                  <\/jats:sec>\n                  <jats:sec>\n                    <jats:title>Results<\/jats:title>\n                    <jats:p>Our development dataset included 28,927 total sentences, with 75% reserved for training and 25% for internal validation. The Random Forest model had the highest accuracy for identifying topic-concordant sentences, with area under the curve 0.98, 0.94, 0.89, 0.92, 0.84, 0.96, 0.98, 0.97, and 0.99 for TR, PR, LE, CP, UF, EF, ED, UI, and LUTS compared with manual coding across all concepts in the internal validation dataset. In 20 separate consultations, the top 10 model-identified sentences correctly graded communication quality across entire consultations with accuracies of 100%, 90%, 95%, 95%, 80%, 95%, 85%, 100%, and 95% for TR, PR, LE, CP, UF, EF, ED, UI, and LUTS compared with manual coding, respectively.<\/jats:p>\n                  <\/jats:sec>\n                  <jats:sec>\n                    <jats:title>Conclusions<\/jats:title>\n                    <jats:p>NLP models accurately capture key information and grade quality of physician communication in prostate cancer consultations, providing the foundation for scalable quality assessment of risk communication.<\/jats:p>\n                  <\/jats:sec>","DOI":"10.1038\/s41391-025-01011-5","type":"journal-article","created":{"date-parts":[[2025,8,21]],"date-time":"2025-08-21T12:26:26Z","timestamp":1755779186000},"page":"338-345","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":7,"title":["Development and validation of a natural language processing system to assess quality of physician communication in prostate cancer consultations"],"prefix":"10.1038","volume":"29","author":[{"ORCID":"https:\/\/orcid.org\/0009-0001-4286-2544","authenticated-orcid":false,"given":"Renning","family":"Zheng","sequence":"first","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-6713-0614","authenticated-orcid":false,"given":"Nadine A.","family":"Friedrich","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Michael","family":"Luu","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Rebecca","family":"Gale","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Dmitry","family":"Khodyakov","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-8104-6419","authenticated-orcid":false,"given":"Stephen J.","family":"Freedland","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Brennan","family":"Spiegel","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-7540-3272","authenticated-orcid":false,"given":"Timothy J.","family":"Daskivich","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"297","published-online":{"date-parts":[[2025,8,21]]},"reference":[{"key":"1011_CR1","doi-asserted-by":"publisher","first-page":"2532","DOI":"10.1001\/jama.2017.7248","volume":"317","author":"MS Litwin","year":"2017","unstructured":"Litwin MS, Tan H-J. The diagnosis and treatment of prostate cancer: a review. JAMA. 2017;317:2532\u201342.","journal-title":"JAMA"},{"key":"1011_CR2","doi-asserted-by":"publisher","first-page":"355","DOI":"10.1016\/j.urpr.2015.10.006","volume":"3","author":"DV Makarov","year":"2016","unstructured":"Makarov DV, Chrouser K, Gore JL, Maranchie J, Nielsen ME, Saigal C, et al. AUA White paper on implementation of shared decision making into urological practice. Urol Pract. 2016;3:355\u201363.","journal-title":"Urol Pract"},{"key":"1011_CR3","doi-asserted-by":"publisher","first-page":"733","DOI":"10.1002\/cncr.29101","volume":"121","author":"DS Wang","year":"2015","unstructured":"Wang DS, Jani AB, Sesay M, Tai CG, Lee DK, Echt KV, et al. Video-based educational tool improves patient comprehension of common prostate health terminology. Cancer. 2015;121:733\u201340.","journal-title":"Cancer"},{"key":"1011_CR4","doi-asserted-by":"publisher","unstructured":"Daskivich TJ, Gale R, Luu M, Naser-Tavakolian A, Venkataramana A, Khodyakov D, et al. Variation in Communication of competing risks of mortality in prostate cancer treatment consultations. J Urol. 2022. https:\/\/doi.org\/10.1097\/JU.0000000000002675.","DOI":"10.1097\/JU.0000000000002675"},{"key":"1011_CR5","doi-asserted-by":"crossref","unstructured":"Daskivich TJ, Naser-Tavakolian A, Gale R, Luu M, Friedrich N, Venkataramana A, et al. Variation in communication of side effects in prostate cancer treatment consultations. Prostate Cancer Prostatic Dis. 2025;28:145\u201352.","DOI":"10.1038\/s41391-024-00806-2"},{"key":"1011_CR6","doi-asserted-by":"publisher","first-page":"70","DOI":"10.1001\/jamasurg.2021.5803","volume":"157","author":"TJ Daskivich","year":"2022","unstructured":"Daskivich TJ, Gale R, Luu M, Khodyakov D, Anger JT, Freedland SJ, et al. Patient Preferences for Communication of Life Expectancy in Prostate Cancer Treatment Consultations. JAMA Surg. 2022;157:70\u201372.","journal-title":"JAMA Surg"},{"key":"1011_CR7","doi-asserted-by":"publisher","first-page":"1121","DOI":"10.1002\/pon.4592","volume":"27","author":"KL Rieger","year":"2018","unstructured":"Rieger KL, Hack TF, Beaver K, Schofield P. Should consultation recording use be a practice standard? A systematic review of the effectiveness and implementation of consultation recordings. Psychooncology. 2018;27:1121\u20138.","journal-title":"Psychooncology"},{"key":"1011_CR8","doi-asserted-by":"publisher","unstructured":"Pitkethly M, MacGillivray S, Ryan R Recordings or summaries of consultations for people with cancer. Cochrane Database Systematic Rev. 2008. https:\/\/doi.org\/10.1002\/14651858.CD001539.pub2.","DOI":"10.1002\/14651858.CD001539.pub2"},{"key":"1011_CR9","doi-asserted-by":"publisher","first-page":"297","DOI":"10.1016\/j.pec.2014.02.007","volume":"95","author":"M Tsulukidze","year":"2014","unstructured":"Tsulukidze M, Durand M-A, Barr PJ, Mead T, Elwyn G. Providing recording of clinical consultation to patients \u2013 A highly valued but underutilized intervention: A scoping review. Patient Educ Counsel. 2014;95:297\u2013304.","journal-title":"Patient Educ Counsel"},{"key":"1011_CR10","doi-asserted-by":"publisher","first-page":"e008566","DOI":"10.1136\/bmjopen-2015-008566","volume":"5","author":"G Elwyn","year":"2015","unstructured":"Elwyn G, Barr PJ, Grande SW. Patients recording clinical encounters: a path to empowerment? Assessment by mixed methods. BMJ Open. 2015;5:e008566.","journal-title":"BMJ Open"},{"key":"1011_CR11","doi-asserted-by":"publisher","first-page":"275","DOI":"10.1002\/cncr.33910","volume":"128","author":"RB Jimenez","year":"2022","unstructured":"Jimenez RB, Johnson AE, Horick NK, Hlubocky FJ, Lei Y, Matsen CB, et al. Do you mind if I record?: Perceptions and practice regarding patient requests to record clinic visits in oncology. Cancer. 2022;128:275\u201383.","journal-title":"Cancer"},{"key":"1011_CR12","doi-asserted-by":"publisher","first-page":"1538","DOI":"10.1016\/j.pec.2018.03.016","volume":"101","author":"H Al-Jabr","year":"2018","unstructured":"Al-Jabr H, Twigg MJ, Scott S, Desborough JA. Patient feedback questionnaires to enhance consultation skills of healthcare professionals: A systematic review. Patient Educ Counsel. 2018;101:1538\u201348.","journal-title":"Patient Educ Counsel"},{"key":"1011_CR13","doi-asserted-by":"publisher","first-page":"1426","DOI":"10.1097\/ACM.0b013e3182312162","volume":"86","author":"ME Reinders","year":"2011","unstructured":"Reinders ME, Ryan BL, Blankenstein AH, Van Der Horst HE, Stewart MA, Van Marwijk HWJ. The Effect of Patient Feedback on Physicians\u02bc Consultation Skills: A Systematic Review. Acad Med. 2011;86:1426\u201336.","journal-title":"Acad Med"},{"key":"1011_CR14","doi-asserted-by":"publisher","first-page":"1","DOI":"10.18637\/jss.v077.i01","volume":"77","author":"MN Wright","year":"2017","unstructured":"Wright MN, Ziegler A. ranger: A Fast Implementation of Random Forests for High Dimensional Data in C++ and R. J Stat Softw. 2017;77:1\u201317.","journal-title":"J Stat Softw"},{"key":"1011_CR15","first-page":"3905","volume":"16","author":"T Hothorn","year":"2015","unstructured":"Hothorn T, Zeileis A. partykit: A Modular toolkit for recursive partytioning in R. J Mach Learn Res. 2015;16:3905\u20139.","journal-title":"J Mach Learn Res"},{"key":"1011_CR16","doi-asserted-by":"publisher","first-page":"1","DOI":"10.18637\/jss.v033.i01","volume":"33","author":"JH Friedman","year":"2010","unstructured":"Friedman JH, Hastie T, Tibshirani R. Regularization paths for generalized linear models via coordinate descent. J Stat Softw. 2010;33:1\u201322.","journal-title":"J Stat Softw"},{"key":"1011_CR17","doi-asserted-by":"publisher","first-page":"1","DOI":"10.18637\/jss.v011.i09","volume":"11","author":"A Karatzoglou","year":"2004","unstructured":"Karatzoglou A, Smola A, Hornik K, Zeileis A. kernlab - An S4 Package for Kernel Methods in R. Journal Stat Softw. 2004;11:1\u201320.","journal-title":"Journal Stat Softw"},{"key":"1011_CR18","unstructured":"Chen T, He T, Benesty M, Khotilovich V, Tang Y, Cho H, et al. Xgboost: Extreme Gradient Boosting. R Package Version 0.4-2, 1\u20134 (2015)."},{"key":"1011_CR19","doi-asserted-by":"publisher","first-page":"618","DOI":"10.1016\/j.eururo.2016.08.003","volume":"71","author":"N Mottet","year":"2017","unstructured":"Mottet N, Bellmunt J, Bolla M, Briers E, Cumberbatch MG, De Santis M, et al. EAU-ESTRO-SIOG Guidelines on Prostate Cancer. Part 1: Screening, Diagnosis, and Local Treatment with Curative Intent. Eur Urol. 2017;71:618\u201329.","journal-title":"Eur Urol"},{"key":"1011_CR20","doi-asserted-by":"publisher","unstructured":"Eastham JA, Auffenberg GB, Barocas DA, Chou R, Crispino T, Davis JW, et al. Clinically Localized Prostate Cancer: AUA\/ASTRO Guideline, Part I: Introduction, risk assessment, staging, and risk-based management. J Urol 2022. https:\/\/doi.org\/10.1097\/JU.0000000000002757.","DOI":"10.1097\/JU.0000000000002757"},{"key":"1011_CR21","first-page":"1288","volume":"20","author":"EM Schaeffer","year":"2022","unstructured":"Schaeffer EM, Srinivas S, Adra N, An Y, Barocas D, Bitting R, et al. NCCN Guidelines\u00ae Insights: Prostate Cancer, Version 1.2023: Featured Updates to the NCCN Guidelines. Journal Natl Compr Cancer Netw. 2022;20:1288\u201398.","journal-title":"Journal Natl Compr Cancer Netw"},{"key":"1011_CR22","doi-asserted-by":"publisher","DOI":"10.1186\/s12911-021-01533-7","volume":"21","author":"A Casey","year":"2021","unstructured":"Casey A, Davidson E, Poon M, Dong H, Duma D, Grivas A, et al. A systematic review of natural language processing applied to radiology reports. BMC Med Inf Decis Mak. 2021;21:179.","journal-title":"BMC Med Inf Decis Mak"},{"key":"1011_CR23","doi-asserted-by":"publisher","DOI":"10.1016\/j.artmed.2023.102701","volume":"146","author":"J Sim","year":"2023","unstructured":"Sim J, Huang X, Horan MR, Stewart CM, Robison LL, Hudson MM, et al. Natural language processing with machine learning methods to analyze unstructured patient-reported outcomes derived from electronic health records: A systematic review. Artif Intell Med. 2023;146:102701.","journal-title":"Artif Intell Med"},{"key":"1011_CR24","doi-asserted-by":"publisher","first-page":"7878","DOI":"10.1007\/s00330-024-10812-6","volume":"34","author":"H Nakai","year":"2024","unstructured":"Nakai H, Suman G, Adamo DA, Navin PJ, Bookwalter CA, LeGout JD, et al. Natural language processing pipeline to extract prostate cancer-related information from clinical notes. Eur Radio. 2024;34:7878\u201391.","journal-title":"Eur Radio"},{"key":"1011_CR25","doi-asserted-by":"publisher","first-page":"1057","DOI":"10.1093\/jamia\/ocaa238","volume":"28","author":"C Dymek","year":"2021","unstructured":"Dymek C, Kim B, Melton GB, Payne TH, Singh H, Hsiao C-J. Building the evidence-base to reduce electronic health record\u2013related clinician burden. J Am Med Inform Assoc. 2021;28:1057\u201361.","journal-title":"J Am Med Inform Assoc"},{"key":"1011_CR26","doi-asserted-by":"publisher","DOI":"10.1093\/jamiaopen\/ooab071","volume":"4","author":"CH Ganoe","year":"2021","unstructured":"Ganoe CH, Wu W, Barr PJ, Haslett W, Dannenberg MD, Bonasia KL, et al. Natural language processing for automated annotation of medication mentions in primary care visit conversations. JAMIA Open. 2021;4:ooab071.","journal-title":"JAMIA Open"},{"key":"1011_CR27","doi-asserted-by":"publisher","first-page":"1153","DOI":"10.2147\/PPA.S202034","volume":"13","author":"NA Mart\u00ednez-Gonz\u00e1lez","year":"2019","unstructured":"Mart\u00ednez-Gonz\u00e1lez NA, Plate A, Markun S, Senn O, Rosemann T, Neuner-Jehle S. Shared decision making for men facing prostate cancer treatment: a systematic review of randomized controlled trials. PPA. 2019;13:1153\u201374.","journal-title":"PPA"},{"key":"1011_CR28","doi-asserted-by":"publisher","first-page":"582","DOI":"10.1016\/j.juro.2018.02.3091","volume":"200","author":"M-A Van Stam","year":"2018","unstructured":"Van Stam M-A, Pieterse AH, Van Der Poel HG, Bosch JLHR, Tillier C, Horenblas S, et al. Shared decision making in prostate cancer care\u2014encouraging every patient to be actively involved in decision making or ensuring the patient preferred level of involvement?. J Urol. 2018;200:582\u20139.","journal-title":"J Urol"},{"key":"1011_CR29","doi-asserted-by":"publisher","first-page":"582","DOI":"10.1016\/j.socscimed.2011.11.015","volume":"74","author":"SM Dy","year":"2012","unstructured":"Dy SM, Purnell TS. Key concepts relevant to quality of complex and shared decision-making in health care: A literature review. Social Sci Med. 2012;74:582\u20137.","journal-title":"Social Sci Med"},{"key":"1011_CR30","doi-asserted-by":"publisher","unstructured":"Luo X, Zhou L, Adelgais K, Zhang Z. Assessing the effectiveness of automatic speech recognition technology in emergency medicine settings: a comparative study of four Ai-powered engines. 2024. https:\/\/doi.org\/10.21203\/rs.3.rs-4727659\/v1.","DOI":"10.21203\/rs.3.rs-4727659\/v1"}],"container-title":["Prostate Cancer and Prostatic Diseases"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/www.nature.com\/articles\/s41391-025-01011-5.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/www.nature.com\/articles\/s41391-025-01011-5","content-type":"text\/html","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/www.nature.com\/articles\/s41391-025-01011-5.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,5,21]],"date-time":"2026-05-21T02:42:01Z","timestamp":1779331321000},"score":1,"resource":{"primary":{"URL":"https:\/\/www.nature.com\/articles\/s41391-025-01011-5"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,8,21]]},"references-count":30,"journal-issue":{"issue":"2","published-print":{"date-parts":[[2026,6]]}},"alternative-id":["1011"],"URL":"https:\/\/doi.org\/10.1038\/s41391-025-01011-5","relation":{},"ISSN":["1365-7852","1476-5608"],"issn-type":[{"value":"1365-7852","type":"print"},{"value":"1476-5608","type":"electronic"}],"subject":[],"published":{"date-parts":[[2025,8,21]]},"assertion":[{"value":"21 May 2025","order":1,"name":"received","label":"Received","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"19 July 2025","order":2,"name":"revised","label":"Revised","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"13 August 2025","order":3,"name":"accepted","label":"Accepted","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"21 August 2025","order":4,"name":"first_online","label":"First Online","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"All methods were performed in accordance with the relevant guidelines and regulations. The study was approved by the Cedars-Sinai IRB (Pro#00053972). All participants provided written or verbal informed consent.","order":1,"name":"Ethics","group":{"name":"EthicsHeading","label":"Ethics approval and consent to participate"}},{"value":"The authors declare no competing interests.","order":2,"name":"Ethics","group":{"name":"EthicsHeading","label":"Competing interests"}}]}}