{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,6,4]],"date-time":"2026-06-04T23:30:22Z","timestamp":1780615822621,"version":"3.54.1"},"reference-count":44,"publisher":"Public Library of Science (PLoS)","issue":"9","license":[{"start":{"date-parts":[[2024,9,6]],"date-time":"2024-09-06T00:00:00Z","timestamp":1725580800000},"content-version":"vor","delay-in-days":0,"URL":"http:\/\/creativecommons.org\/licenses\/by\/4.0\/"}],"funder":[{"name":"JSPS KAKENHI","award":["21H03170"],"award-info":[{"award-number":["21H03170"]}]},{"name":"JST CREST","award":["JPMJCR22N1"],"award-info":[{"award-number":["JPMJCR22N1"]}]}],"content-domain":{"domain":["www.plosone.org"],"crossmark-restriction":false},"short-container-title":["PLoS ONE"],"abstract":"<jats:p>Narratives posted on the internet by patients contain a vast amount of information about various concerns. This study aimed to extract multiple concerns from interviews with breast cancer patients using the natural language processing (NLP) model bidirectional encoder representations from transformers (BERT). A total of 508 interview transcriptions of breast cancer patients written in Japanese were labeled with five types of concern labels: \"treatment,\" \"physical,\" \"psychological,\" \"work\/financial,\" and \"family\/friends.\" The labeled texts were used to create a multi-label classifier by fine-tuning a pre-trained BERT model. Prior to fine-tuning, we also created several classifiers with domain adaptation using (1) breast cancer patients\u2019 blog articles and (2) breast cancer patients\u2019 interview transcriptions. The performance of the classifiers was evaluated in terms of precision through 5-fold cross-validation. The multi-label classifiers with only fine-tuning had precision values of over 0.80 for \"physical\" and \"work\/financial\" out of the five concerns. On the other hand, precision for \"treatment\" was low at approximately 0.25. However, for the classifiers using domain adaptation, the precision of this label took a range of 0.40\u20130.51, with some cases improving by more than 0.2. This study showed combining domain adaptation with a multi-label classifier on target data made it possible to efficiently extract multiple concerns from interviews.<\/jats:p>","DOI":"10.1371\/journal.pone.0305496","type":"journal-article","created":{"date-parts":[[2024,9,6]],"date-time":"2024-09-06T18:14:08Z","timestamp":1725646448000},"page":"e0305496","update-policy":"https:\/\/doi.org\/10.1371\/journal.pone.corrections_policy","source":"Crossref","is-referenced-by-count":5,"title":["Exploring a method for extracting concerns of multiple breast cancer patients in the domain of patient narratives using BERT and its optimization by domain adaptation using masked language modeling"],"prefix":"10.1371","volume":"19","author":[{"given":"Satoshi","family":"Watabe","sequence":"first","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Tomomi","family":"Watanabe","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-6209-1054","authenticated-orcid":true,"given":"Shuntaro","family":"Yada","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Eiji","family":"Aramaki","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Hiroshi","family":"Yajima","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Hayato","family":"Kizaki","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-4596-5418","authenticated-orcid":true,"given":"Satoko","family":"Hori","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"340","published-online":{"date-parts":[[2024,9,6]]},"reference":[{"issue":"3","key":"pone.0305496.ref001","doi-asserted-by":"crossref","first-page":"209","DOI":"10.3322\/caac.21660","article-title":"Global cancer statistics 2020: GLOBOCAN estimates of incidence and mortality worldwide for 36 cancers in 185 countries.","volume":"71","author":"H Sung","year":"2021","journal-title":"CA Cancer J Clin"},{"key":"pone.0305496.ref002","unstructured":"Cancer Statistics in Japan-2019. Tokyo, Japan: Foundation for Promotion of Cancer Research; Mar 2020."},{"issue":"9972","key":"pone.0305496.ref003","doi-asserted-by":"crossref","first-page":"977","DOI":"10.1016\/S0140-6736(14)62038-9","article-title":"Global surveillance of cancer survival 1995\u20132009: analysis of individual data for 25,676,887 patients from 279 population-based registries in 67 countries (CONCORD-2).","volume":"385","author":"C Allemani","year":"2015","journal-title":"Lancet"},{"issue":"2","key":"pone.0305496.ref004","doi-asserted-by":"crossref","first-page":"229","DOI":"10.1007\/s10549-017-4290-9","article-title":"Predictors of distress in female breast cancer survivors: a systematic review","volume":"165","author":"A Syrowatka","journal-title":"Breast Cancer Res Treat"},{"key":"pone.0305496.ref005","doi-asserted-by":"crossref","first-page":"35","DOI":"10.3389\/fpubh.2018.00035","article-title":"Developing a Return to Work Intervention for Breast Cancer Survivors with the Intervention Mapping Protocol: Challenges and Opportunities of the Needs Assessment.","volume":"6","author":"JB Fassier","year":"2018","journal-title":"Front Public Health"},{"issue":"1","key":"pone.0305496.ref006","doi-asserted-by":"crossref","first-page":"7485","DOI":"10.1038\/s41598-022-11478-0","article-title":"The role of psychosocial factors in patients\u2019 recollections of breast reconstruction options discussed with their surgeons.","volume":"12","author":"H Wang","year":"2022","journal-title":"Sci Rep."},{"issue":"19","key":"pone.0305496.ref007","doi-asserted-by":"crossref","first-page":"1994","DOI":"10.1200\/JCO.2018.78.1914","article-title":"Fertility Preservation in Patients With Cancer: ASCO Clinical Practice Guideline Update.","volume":"36","author":"K Oktay","year":"2018","journal-title":"J Clin Oncol"},{"issue":"5","key":"pone.0305496.ref008","doi-asserted-by":"crossref","first-page":"e1011","DOI":"10.1016\/j.clbc.2018.04.012","article-title":"Breast Reconstruction After Mastectomy: A Survey of Surgeons\u2019 and Patients\u2019 Perceptions.","volume":"18","author":"A Ishak","year":"2018","journal-title":"Clin Breast Cancer"},{"issue":"6","key":"pone.0305496.ref009","doi-asserted-by":"crossref","first-page":"808","DOI":"10.1007\/s11764-017-0620-5","article-title":"Social media for breast cancer survivors: a literature review.","volume":"11","author":"AL Falisi","year":"2017","journal-title":"J Cancer Surviv"},{"issue":"2","key":"pone.0305496.ref010","doi-asserted-by":"crossref","first-page":"253","DOI":"10.1007\/s00268-010-0830-8","article-title":"A quantitative assessment of changing trends in internet usage for cancer information","volume":"35","author":"SM McHugh","year":"2011","journal-title":"World J Surg"},{"key":"pone.0305496.ref011","article-title":"A Blog Text Analysis to Explore Psychosocial Support in Adolescents and Young Adults With Cancer.","author":"E Choi","year":"2022","journal-title":"Cancer Nurs"},{"issue":"6","key":"pone.0305496.ref012","doi-asserted-by":"crossref","first-page":"2183","DOI":"10.1007\/s40123-022-00571-2","article-title":"A Social Media Listening Study to Understand the Unmet Needs and Quality of Life in Adult and Pediatric Amblyopia Patients.","volume":"11","author":"A Syntosi","year":"2022","journal-title":"Ophthalmol Ther."},{"issue":"1","key":"pone.0305496.ref013","doi-asserted-by":"crossref","first-page":"103","DOI":"10.1177\/1359105307071744","article-title":"Breast and prostate cancer online discussion boards: a thematic analysis of gender differences and similarities.","volume":"12","author":"R Gooden","year":"2007","journal-title":"J Health Psychol"},{"key":"pone.0305496.ref014","doi-asserted-by":"crossref","first-page":"37","DOI":"10.1016\/j.ijmedinf.2019.02.008","article-title":"A systematic review of natural language processing and text mining of symptoms from electronic patient-authored text data","volume":"125","author":"C. Dreisbach","year":"2019","journal-title":"International journal of medical informatics"},{"issue":"3","key":"pone.0305496.ref015","doi-asserted-by":"crossref","first-page":"e23","DOI":"10.2196\/medinform.7779","article-title":"What patients can tell us: topic analysis for social media on breast cancer.","volume":"5","author":"MD Tapi Nzali","year":"2017","journal-title":"JMIR Med Inform"},{"key":"pone.0305496.ref016","first-page":"1735","volume":"1780","author":"S. Hochreiter","year":"1997","journal-title":"Long Short-Term Memory"},{"key":"pone.0305496.ref017","unstructured":"Devlin J, Chang MW, Lee K, Toutanova K. BERT: pre-training of deep bidirectional transformers for language understanding. 2019 Presented at: NAACL-HLT 2019; June 2019; Minneapolis, MN"},{"issue":"2016","key":"pone.0305496.ref018","first-page":"604","article-title":"Development and testing of a text-mining approach to analyse patients\u2019 comments on their experiences of colorectal cancer care","volume":"25.8","author":"Richard Wagland","journal-title":"BMJ Quality & Safety"},{"key":"pone.0305496.ref019","first-page":"524","article-title":"Understanding patient satisfaction with received healthcare services: A natural language processing approach.","volume":"2016","author":"K Doing-Harris","year":"2017","journal-title":"AMIA Annu Symp Proc"},{"issue":"5","key":"pone.0305496.ref020","doi-asserted-by":"crossref","first-page":"e0267901","DOI":"10.1371\/journal.pone.0267901","article-title":"Identification of hand-foot syndrome from cancer patients\u2019 blog posts: BERT-based deep-learning approach to detect potential adverse drug reaction symptoms.","volume":"17","author":"S Nishioka","year":"2022","journal-title":"PLoS One"},{"key":"pone.0305496.ref021","first-page":"37","article-title":"Development of Internet suicide message identification and the Monitoring-Tracking-Rescuing model in Taiwan","volume":"320","author":"EL Wu","journal-title":"J Affect Disord"},{"key":"pone.0305496.ref022","doi-asserted-by":"crossref","first-page":"104228","DOI":"10.1016\/j.jbi.2022.104228","article-title":"How do others cope? Extracting coping strategies for adverse drug events from social media","volume":"139","author":"A. Dirkson","year":"2023","journal-title":"Journal of Biomedical Informatics"},{"issue":"1","key":"pone.0305496.ref023","first-page":"e9887","article-title":"Analyzing empowerment processes among cancer patients in an online community: a text mining approach","volume":"5","author":"S. Verberne","year":"2019","journal-title":"JMIR"},{"issue":"2","key":"pone.0305496.ref024","doi-asserted-by":"crossref","first-page":"e37840","DOI":"10.2196\/37840","article-title":"Extracting Multiple Worries From Breast Cancer Patient Blogs Using Multilabel Classification With the Natural Language Processing Model Bidirectional Encoder Representations From Transformers: Infodemiology Study of Blogs.","volume":"8","author":"T Watanabe","year":"2022","journal-title":"JMIR Cancer"},{"key":"pone.0305496.ref025","unstructured":"Petek, Elyse. Pilot Study: Exploration of How Women Use Social Media After a Breast Cancer Diagnosis. 2021. Ohio State University, Master\u2019s thesis. OhioLINK Electronic Theses and Dissertations Center, http:\/\/rave.ohiolink.edu\/etdc\/view?acc_num=osu1617891913525326."},{"issue":"6","key":"pone.0305496.ref026","doi-asserted-by":"crossref","first-page":"e13685","DOI":"10.1111\/ecc.13685","article-title":"YouTube English videos as a source of information on arm and shoulder exercise after breast cancer surgery","volume":"31","author":"S G\u00fclo\u011flu","year":"2022","journal-title":"Eur J Cancer Care (Engl)."},{"key":"pone.0305496.ref027","article-title":"Narratives of Breast Cancer Patients","author":"DIPEx-Japan"},{"issue":"2000","key":"pone.0305496.ref028","first-page":"1540","article-title":"Database of patients\u2019 experiences (DIPEx): a multi-media approach to sharing experiences and information.\"","author":"Andrew Herxheimer","journal-title":"The Lancet"},{"key":"pone.0305496.ref029","article-title":"Life Palette","author":"Mediaid Corporation"},{"key":"pone.0305496.ref030","volume-title":"The voices of 1,275 people who have faced breast cancer","year":"2016"},{"key":"pone.0305496.ref031","volume-title":"cl-tohoku \/ bert-japanese","author":"Inui Laboratory Tohoku University"},{"key":"pone.0305496.ref032","doi-asserted-by":"crossref","unstructured":"Suchin Gururangan, Ana Marasovi\u0107, Swabha Swayamdipta, Kyle Lo, Iz Beltagy, Doug Downey, et al. 2020. Don\u2019t Stop Pretraining: Adapt Language Models to Domains and Tasks. In Proceedings of the 58th Annual Meeting of the Association for Computational Linguistics, pages 8342\u20138360, Online. Association for Computational Linguistics.","DOI":"10.18653\/v1\/2020.acl-main.740"},{"key":"pone.0305496.ref033","doi-asserted-by":"crossref","unstructured":"Roee Aharoni and Yoav Goldberg. 2020. Unsupervised domain clusters in pretrained language models. In ACL. To appear.","DOI":"10.18653\/v1\/2020.acl-main.692"},{"key":"pone.0305496.ref034","doi-asserted-by":"crossref","unstructured":"Whang, Taesun, et al. \"An effective domain adaptive post-training method for bert in response selection.\" arXiv preprint arXiv:1908.04812 (2019).","DOI":"10.21437\/Interspeech.2020-2153"},{"key":"pone.0305496.ref035","doi-asserted-by":"crossref","unstructured":"Shnarch, Eyal, et al. \"Cluster & tune: Boost cold start performance in text classification.\" arXiv preprint arXiv:2203.10581 (2022).","DOI":"10.18653\/v1\/2022.acl-long.526"},{"key":"pone.0305496.ref036","first-page":"03","article-title":"Resources Course MAIN NLP TASKS","author":"Hugging Face","year":"2023","journal-title":"Fine-tuning a masked language model"},{"key":"pone.0305496.ref037","first-page":"59","article-title":"Classifying patient portal messages using Convolutional Neural Networks.","volume":"74","author":"L Sulieman","journal-title":"J Biomed Inform. 2017 Oct"},{"key":"pone.0305496.ref038","unstructured":"Miyabe M, Shimamoto Y, Aramaki E. Extracting patients\u2019 distress of their medical care from web texts: the automatic classification of cancer patients\u2019 distress. 2014 Presented at: Forum on Information Technology; September 2014; Tsukuba, Japan."},{"issue":"1","key":"pone.0305496.ref039","doi-asserted-by":"crossref","first-page":"e100262","DOI":"10.1136\/bmjhci-2020-100262","article-title":"Applying natural language processing and machine learning techniques to patient experience feedback: a systematic review","volume":"28","author":"M Khanbhai","year":"2021","journal-title":"BMJ Health Care Inform"},{"key":"pone.0305496.ref040","doi-asserted-by":"crossref","unstructured":"Zhou, S.; Wang, L.; Wang, N.; Liu, H.; Zhang, R. CancerBERT: A BERT Model for Extracting Breast Cancer Phenotypes from Electronic Health Records. arXiv 2021, arXiv:2108.11303.","DOI":"10.1093\/jamia\/ocac040"},{"key":"pone.0305496.ref041","doi-asserted-by":"crossref","first-page":"103985","DOI":"10.1016\/j.ijmedinf.2019.103985","article-title":"Extracting comprehensive clinical information for breast cancer using deep learning methods","volume":"132","author":"X Zhang","year":"2019","journal-title":"Int J Med Inform"},{"key":"pone.0305496.ref042","doi-asserted-by":"crossref","unstructured":"O. Solarte-Pab\u00f3n, M. Torrente, A. Garcia-Barrag\u00e1n, M. Provencio, E. Menasalvas and V. Robles, \"Deep learning to extract Breast Cancer diagnosis concepts,\" 2022 IEEE 35th International Symposium on Computer-Based Medical Systems (CBMS), Shenzen, China, 2022, pp. 13\u201318, doi: 10.1109\/CBMS55023.2022.00010","DOI":"10.1109\/CBMS55023.2022.00010"},{"key":"pone.0305496.ref043","doi-asserted-by":"crossref","unstructured":"Arefyev, Nikolay, Dmitrii Kharchev, and Artem Shelmanov. \"Nb-mlm: Efficient domain adaptation of masked language models for sentiment analysis.\" Proceedings of the 2021 Conference on Empirical Methods in Natural Language Processing. 2021.","DOI":"10.18653\/v1\/2021.emnlp-main.717"},{"key":"pone.0305496.ref044","unstructured":"Katsumata S, Komachi M, Manabe A, Tanimoto H. Using Data Selection for Failure Report Classification Problems Improving the Performance of BERT Model. 2020 Presented at: 26th Annual Conference of The Association for Natural Language Processing; March 2020; Ibaraki, Japan."}],"updated-by":[{"DOI":"10.1371\/journal.pone.0329664","type":"correction","label":"Correction","source":"publisher","updated":{"date-parts":[[2025,8,1]],"date-time":"2025-08-01T00:00:00Z","timestamp":1754006400000}}],"container-title":["PLOS ONE"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/dx.plos.org\/10.1371\/journal.pone.0305496","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2024,9,6]],"date-time":"2024-09-06T18:14:36Z","timestamp":1725646476000},"score":1,"resource":{"primary":{"URL":"https:\/\/dx.plos.org\/10.1371\/journal.pone.0305496"}},"subtitle":[],"editor":[{"given":"Asif","family":"Ekbal","sequence":"first","affiliation":[],"role":[{"vocabulary":"crossref","role":"editor"}]}],"short-title":[],"issued":{"date-parts":[[2024,9,6]]},"references-count":44,"journal-issue":{"issue":"9","published-online":{"date-parts":[[2024,9,6]]}},"URL":"https:\/\/doi.org\/10.1371\/journal.pone.0305496","relation":{},"ISSN":["1932-6203"],"issn-type":[{"value":"1932-6203","type":"electronic"}],"subject":[],"published":{"date-parts":[[2024,9,6]]}}}