{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,5,15]],"date-time":"2026-05-15T06:29:14Z","timestamp":1778826554652,"version":"3.51.4"},"reference-count":44,"publisher":"American Society of Clinical Oncology (ASCO)","issue":"7","content-domain":{"domain":["ascopubs.org"],"crossmark-restriction":true},"short-container-title":["JCO Clinical Cancer Informatics"],"published-print":{"date-parts":[[2023,7]]},"abstract":"<jats:sec><jats:title>PURPOSE<\/jats:title><jats:p> Radiotherapy (RT) toxicities can impair survival and quality of life, yet remain understudied. Real-world evidence holds potential to improve our understanding of toxicities, but toxicity information is often only in clinical notes. We developed natural language processing (NLP) models to identify the presence and severity of esophagitis from notes of patients treated with thoracic RT. <\/jats:p><\/jats:sec><jats:sec><jats:title>METHODS<\/jats:title><jats:p> Our corpus consisted of a gold-labeled data set of 1,524 clinical notes from 124 patients with lung cancer treated with RT, manually annotated for Common Terminology Criteria for Adverse Events (CTCAE) v5.0 esophagitis grade, and a silver-labeled data set of 2,420 notes from 1,832 patients from whom toxicity grades had been collected as structured data during clinical care. We fine-tuned statistical and pretrained Bidirectional Encoder Representations from Transformers\u2013based models for three esophagitis classification tasks: task 1, no esophagitis versus grade 1-3; task 2, grade \u22641 versus &gt;1; and task 3, no esophagitis versus grade 1 versus grade 2-3. Transferability was tested on 345 notes from patients with esophageal cancer undergoing RT. <\/jats:p><\/jats:sec><jats:sec><jats:title>RESULTS<\/jats:title><jats:p> Fine-tuning of PubMedBERT yielded the best performance. The best macro-F1 was 0.92, 0.82, and 0.74 for tasks 1, 2, and 3, respectively. Selecting the most informative note sections during fine-tuning improved macro-F1 by \u22652% for all tasks. Silver-labeled data improved the macro-F1 by \u22653% across all tasks. For the esophageal cancer notes, the best macro-F1 was 0.73, 0.74, and 0.65 for tasks 1, 2, and 3, respectively, without additional fine-tuning. <\/jats:p><\/jats:sec><jats:sec><jats:title>CONCLUSION<\/jats:title><jats:p> To our knowledge, this is the first effort to automatically extract esophagitis toxicity severity according to CTCAE guidelines from clinical notes. This provides proof of concept for NLP-based automated detailed toxicity monitoring in expanded domains. <\/jats:p><\/jats:sec>","DOI":"10.1200\/cci.23.00048","type":"journal-article","created":{"date-parts":[[2023,7,28]],"date-time":"2023-07-28T19:59:52Z","timestamp":1690574392000},"update-policy":"https:\/\/doi.org\/10.1200\/crossmark","source":"Crossref","is-referenced-by-count":12,"title":["Natural Language Processing to Automatically Extract the Presence and Severity of Esophagitis in Notes of Patients Undergoing Radiotherapy"],"prefix":"10.1200","author":[{"ORCID":"https:\/\/orcid.org\/0000-0001-7999-7410","authenticated-orcid":false,"given":"Shan","family":"Chen","sequence":"first","affiliation":[{"name":"Artificial Intelligence in Medicine (AIM) Program, Mass General Brigham, Harvard Medical School, Boston, MA"},{"name":"Department of Radiation Oncology, Brigham and Women's Hospital\/Dana-Farber Cancer Institute, Boston, MA"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Marco","family":"Guevara","sequence":"additional","affiliation":[{"name":"Artificial Intelligence in Medicine (AIM) Program, Mass General Brigham, Harvard Medical School, Boston, MA"},{"name":"Department of Radiation Oncology, Brigham and Women's Hospital\/Dana-Farber Cancer Institute, Boston, MA"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Nicolas","family":"Ramirez","sequence":"additional","affiliation":[{"name":"Artificial Intelligence in Medicine (AIM) Program, Mass General Brigham, Harvard Medical School, Boston, MA"},{"name":"Department of Radiation Oncology, Brigham and Women's Hospital\/Dana-Farber Cancer Institute, Boston, MA"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Arpi","family":"Murray","sequence":"additional","affiliation":[{"name":"Department of Radiation Oncology, Brigham and Women's Hospital\/Dana-Farber Cancer Institute, Boston, MA"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-2851-7242","authenticated-orcid":false,"given":"Jeremy L.","family":"Warner","sequence":"additional","affiliation":[{"name":"Population Sciences Program, Legorreta Cancer Center, Brown University, Providence, RI"},{"name":"Lifespan Cancer Institute, Providence, RI"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-2122-2003","authenticated-orcid":false,"given":"Hugo J. W. L.","family":"Aerts","sequence":"additional","affiliation":[{"name":"Artificial Intelligence in Medicine (AIM) Program, Mass General Brigham, Harvard Medical School, Boston, MA"},{"name":"Department of Radiation Oncology, Brigham and Women's Hospital\/Dana-Farber Cancer Institute, Boston, MA"},{"name":"Radiology and Nuclear Medicine, GROW & CARIM, Maastricht University, Maastricht, the Netherlands"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Timothy A.","family":"Miller","sequence":"additional","affiliation":[{"name":"Computational Health Informatics Program, Boston Children's Hospital, Boston, MA"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-5887-200X","authenticated-orcid":false,"given":"Guergana K.","family":"Savova","sequence":"additional","affiliation":[{"name":"Computational Health Informatics Program, Boston Children's Hospital, Boston, MA"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-8754-0565","authenticated-orcid":false,"given":"Raymond H.","family":"Mak","sequence":"additional","affiliation":[{"name":"Artificial Intelligence in Medicine (AIM) Program, Mass General Brigham, Harvard Medical School, Boston, MA"},{"name":"Department of Radiation Oncology, Brigham and Women's Hospital\/Dana-Farber Cancer Institute, Boston, MA"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-0345-2232","authenticated-orcid":false,"given":"Danielle S.","family":"Bitterman","sequence":"additional","affiliation":[{"name":"Artificial Intelligence in Medicine (AIM) Program, Mass General Brigham, Harvard Medical School, Boston, MA"},{"name":"Department of Radiation Oncology, Brigham and Women's Hospital\/Dana-Farber Cancer Institute, Boston, MA"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"233","reference":[{"key":"b1","doi-asserted-by":"publisher","DOI":"10.3322\/caac.21763"},{"key":"b2","volume-title":"National Cancer Institute: Cancer trends progress report: Life after diagnosis"},{"key":"b3","doi-asserted-by":"publisher","DOI":"10.1002\/(SICI)1099-1557(199901\/02)8:1<61::AID-PDS395>3.0.CO;2-A"},{"key":"b4","doi-asserted-by":"publisher","DOI":"10.1136\/bmjopen-2018-024537"},{"key":"b5","doi-asserted-by":"publisher","DOI":"10.1001\/archinternmed.2009.306"},{"key":"b6","doi-asserted-by":"publisher","DOI":"10.1001\/jama.285.4.437"},{"key":"b7","doi-asserted-by":"publisher","DOI":"10.2165\/00002018-200225020-00002"},{"key":"b8","doi-asserted-by":"publisher","DOI":"10.1016\/j.jtho.2018.08.2035"},{"key":"b9","doi-asserted-by":"publisher","DOI":"10.2217\/mmt-2017-0028"},{"key":"b10","doi-asserted-by":"publisher","DOI":"10.1016\/j.lungcan.2018.09.015"},{"key":"b11","doi-asserted-by":"publisher","DOI":"10.1038\/s41598-022-05861-0"},{"key":"b12","doi-asserted-by":"publisher","DOI":"10.1186\/s12885-020-07215-3"},{"key":"b13","doi-asserted-by":"publisher","DOI":"10.1186\/s12885-022-09843-3"},{"key":"b14","doi-asserted-by":"publisher","DOI":"10.1158\/0008-5472.CAN-19-0579"},{"key":"b15","doi-asserted-by":"publisher","DOI":"10.1371\/journal.pone.0279842"},{"key":"b16","doi-asserted-by":"publisher","DOI":"10.1007\/s40264-017-0558-6"},{"key":"b17","doi-asserted-by":"publisher","DOI":"10.1016\/j.ijrobp.2021.01.044"},{"key":"b18","doi-asserted-by":"publisher","DOI":"10.1093\/jamiaopen\/ooaa064"},{"key":"b19","doi-asserted-by":"publisher","DOI":"10.1200\/CCI.20.00109"},{"key":"b20","doi-asserted-by":"publisher","DOI":"10.1200\/CCI.21.00136"},{"key":"b21","doi-asserted-by":"publisher","DOI":"10.1093\/jamia\/ocz166"},{"key":"b22","doi-asserted-by":"publisher","DOI":"10.1007\/s40264-018-0762-z"},{"key":"b23","doi-asserted-by":"publisher","DOI":"10.1016\/j.ijrobp.2016.10.042"},{"key":"b24","doi-asserted-by":"publisher","DOI":"10.1093\/jnci\/djz167"},{"key":"b25","doi-asserted-by":"publisher","DOI":"10.3322\/caac.21660"},{"key":"b26","doi-asserted-by":"publisher","DOI":"10.1200\/jco.2006.24.18_suppl.7008"},{"key":"b27","doi-asserted-by":"publisher","DOI":"10.1016\/S1470-2045(15)70168-3"},{"key":"b28","doi-asserted-by":"publisher","DOI":"10.1016\/S0140-6736(09)60737-6"},{"key":"b29","doi-asserted-by":"publisher","DOI":"10.1200\/JCO.2004.06.123"},{"key":"b30","doi-asserted-by":"publisher","DOI":"10.1093\/jnci\/djr325"},{"key":"b31","doi-asserted-by":"publisher","DOI":"10.1056\/NEJMoa1809697"},{"key":"b32","doi-asserted-by":"publisher","DOI":"10.2147\/LCTT.S96443"},{"key":"b33","doi-asserted-by":"publisher","DOI":"10.1016\/j.radonc.2017.10.002"},{"key":"b34","volume-title":"National Cancer Institute: Common terminology criteria for adverse rvents (CTCAE) v5.0 quick reference"},{"key":"b35","doi-asserted-by":"publisher","DOI":"10.1017\/CBO9781139058452.002"},{"key":"b36","doi-asserted-by":"publisher","DOI":"10.3390\/info10040150"},{"key":"b38","doi-asserted-by":"publisher","DOI":"10.1093\/bioinformatics\/btz682"},{"key":"b40","first-page":"1","volume":"2","author":"Gu Y","year":"2021","journal-title":"ACM Trans Comput Healthcare"},{"key":"b42","doi-asserted-by":"publisher","DOI":"10.1186\/s12874-019-0792-y"},{"key":"b44","first-page":"438","volume":"2021","author":"Eyre H","year":"2021","journal-title":"AMIA Annu Symp Proc"},{"key":"b46","doi-asserted-by":"publisher","DOI":"10.1371\/journal.pone.0112774"},{"key":"b47","first-page":"185","volume":"192","author":"Kim Y","year":"2013","journal-title":"Stud Health Technol Inform"},{"key":"b49","doi-asserted-by":"publisher","DOI":"10.1055\/s-0041-1726522"},{"key":"b50","doi-asserted-by":"publisher","DOI":"10.1136\/jitc-2020-001935"}],"container-title":["JCO Clinical Cancer Informatics"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/ascopubs.org\/doi\/pdfdirect\/10.1200\/CCI.23.00048","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2023,7,28]],"date-time":"2023-07-28T19:59:59Z","timestamp":1690574399000},"score":1,"resource":{"primary":{"URL":"https:\/\/ascopubs.org\/doi\/10.1200\/CCI.23.00048"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2023,7]]},"references-count":44,"journal-issue":{"issue":"7","published-print":{"date-parts":[[2023,7]]}},"alternative-id":["10.1200\/CCI.23.00048"],"URL":"https:\/\/doi.org\/10.1200\/cci.23.00048","relation":{},"ISSN":["2473-4276"],"issn-type":[{"value":"2473-4276","type":"electronic"}],"subject":[],"published":{"date-parts":[[2023,7]]},"assertion":[{"value":"2023-03-28","order":0,"name":"received","label":"Received","group":{"name":"publication_history","label":"Publication History"}},{"value":"2023-05-05","order":1,"name":"revised","label":"Revised","group":{"name":"publication_history","label":"Publication History"}},{"value":"2023-05-26","order":2,"name":"accepted","label":"Accepted","group":{"name":"publication_history","label":"Publication History"}},{"value":"2023-07-28","order":3,"name":"published","label":"Published","group":{"name":"publication_history","label":"Publication History"}}],"article-number":"e2300048"}}