{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,5,3]],"date-time":"2026-05-03T23:45:51Z","timestamp":1777851951557,"version":"3.51.4"},"reference-count":35,"publisher":"SAGE Publications","issue":"3","license":[{"start":{"date-parts":[[2023,7,1]],"date-time":"2023-07-01T00:00:00Z","timestamp":1688169600000},"content-version":"unspecified","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by-nc\/4.0\/"}],"funder":[{"name":"VA Cooperative Studies Program"},{"name":"VA Boston Medical Informatics Fellowship"},{"DOI":"10.13039\/100000968","name":"American Heart Association","doi-asserted-by":"publisher","award":["870726"],"award-info":[{"award-number":["870726"]}],"id":[{"id":"10.13039\/100000968","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":["journals.sagepub.com"],"crossmark-restriction":true},"short-container-title":["Health Informatics J"],"published-print":{"date-parts":[[2023,7]]},"abstract":"<jats:p>Introduction: PD-L1 expression is used to determine oncology patients\u2019 response to and eligibility for immunologic treatments; however, PD-L1 expression status often only exists in unstructured clinical notes, limiting ability to use it in population-level studies. Methods: We developed and evaluated a machine learning based natural language processing (NLP) tool to extract PD-L1 expression values from the nationwide Veterans Affairs electronic health record system. Results: The model demonstrated strong evaluation performance across multiple levels of label granularity. Mean precision of the overall PD-L1 positive label was 0.859 (sd, 0.039), recall 0.994 (sd, 0.013), and F1 0.921 (0.024). When a numeric PD-L1 value was identified, the mean absolute error of the value was 0.537 on a scale of 0 to 100. Conclusion: We presented an accurate NLP method for deriving PD-L1 status from clinical notes. By reducing the time and manual effort needed to review medical records, our work will enable future population-level studies in cancer immunotherapy.<\/jats:p>","DOI":"10.1177\/14604582231198021","type":"journal-article","created":{"date-parts":[[2023,8,27]],"date-time":"2023-08-27T23:58:21Z","timestamp":1693180701000},"update-policy":"https:\/\/doi.org\/10.1177\/sage-journals-update-policy","source":"Crossref","is-referenced-by-count":4,"title":["Machine learning-based natural language processing to extract PD-L1 expression levels from clinical notes"],"prefix":"10.1177","volume":"29","author":[{"ORCID":"https:\/\/orcid.org\/0000-0002-1061-7704","authenticated-orcid":false,"given":"Eric","family":"Lin","sequence":"first","affiliation":[{"name":"VA Boston Healthcare System, Boston, MA, USA"},{"name":"McLean Hospital, Institute for Technology in Psychiatry, Belmont, MA, USA"}]},{"given":"Robert","family":"Zwolinski","sequence":"additional","affiliation":[{"name":"VA Boston Healthcare System, Boston, MA, USA"}]},{"given":"Julie Tsu-Yu","family":"Wu","sequence":"additional","affiliation":[{"name":"VA Palo Alto Healthcare System, Palo Alto, CA, USA"},{"name":"Stanford University School of Medicine, Stanford, CA, USA"}]},{"given":"Jennifer","family":"La","sequence":"additional","affiliation":[{"name":"VA Boston Healthcare System, Boston, MA, USA"}]},{"given":"Sergey","family":"Goryachev","sequence":"additional","affiliation":[{"name":"VA Boston Healthcare System, Boston, MA, USA"}]},{"given":"Linden","family":"Huhmann","sequence":"additional","affiliation":[{"name":"VA Boston Healthcare System, Boston, MA, USA"}]},{"given":"Cenk","family":"Yildrim","sequence":"additional","affiliation":[{"name":"VA Boston Healthcare System, Boston, MA, USA"}]},{"given":"David P","family":"Tuck","sequence":"additional","affiliation":[{"name":"VA Boston Healthcare System, Boston, MA, USA"},{"name":"Boston University School of Medicine, Boston, MA, USA"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-0454-0173","authenticated-orcid":false,"given":"Danne C","family":"Elbers","sequence":"additional","affiliation":[{"name":"VA Boston Healthcare System, Boston, MA, USA"},{"name":"Harvard Medical School, Boston, MA, USA"}]},{"given":"Mary T","family":"Brophy","sequence":"additional","affiliation":[{"name":"VA Boston Healthcare System, Boston, MA, USA"},{"name":"Boston University School of Medicine, Boston, MA, USA"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-6868-7011","authenticated-orcid":false,"given":"Nhan V","family":"Do","sequence":"additional","affiliation":[{"name":"VA Boston Healthcare System, Boston, MA, USA"},{"name":"Boston University School of Medicine, Boston, MA, USA"}]},{"given":"Nathanael R","family":"Fillmore","sequence":"additional","affiliation":[{"name":"VA Boston Healthcare System, Boston, MA, USA"},{"name":"Harvard Medical School, Boston, MA, USA"},{"name":"Dana-Farber Cancer Institute, Boston, MA, USA"}]}],"member":"179","published-online":{"date-parts":[[2023,8,27]]},"reference":[{"key":"bibr1-14604582231198021","doi-asserted-by":"publisher","DOI":"10.3747\/co.27.5223"},{"key":"bibr2-14604582231198021","doi-asserted-by":"publisher","DOI":"10.1038\/nrclinonc.2013.208"},{"key":"bibr3-14604582231198021","first-page":"1281","volume":"15","author":"Uprety D","year":"2020","journal-title":"J Thorac Oncol Off Publ Int Assoc Study Lung Cancer"},{"key":"bibr4-14604582231198021","doi-asserted-by":"publisher","DOI":"10.1126\/science.aax0182"},{"key":"bibr5-14604582231198021","doi-asserted-by":"publisher","DOI":"10.1016\/j.thorsurg.2020.01.001"},{"key":"bibr6-14604582231198021","doi-asserted-by":"publisher","DOI":"10.2217\/imt-2017-0143"},{"key":"bibr7-14604582231198021","doi-asserted-by":"publisher","DOI":"10.1016\/S1470-2045(18)30700-9"},{"key":"bibr8-14604582231198021","doi-asserted-by":"publisher","DOI":"10.1016\/S1470-2045(15)70076-8"},{"key":"bibr9-14604582231198021","doi-asserted-by":"publisher","DOI":"10.1016\/S0140-6736(15)01281-7"},{"key":"bibr10-14604582231198021","doi-asserted-by":"publisher","DOI":"10.1200\/JCO.18.00149"},{"key":"bibr11-14604582231198021","doi-asserted-by":"publisher","DOI":"10.1016\/S0140-6736(18)32409-7"},{"key":"bibr12-14604582231198021","doi-asserted-by":"publisher","DOI":"10.1186\/s40425-017-0300-z"},{"key":"bibr13-14604582231198021","doi-asserted-by":"publisher","DOI":"10.3322\/caac.21596"},{"key":"bibr14-14604582231198021","doi-asserted-by":"publisher","DOI":"10.1016\/S1470-2045(16)30406-5"},{"key":"bibr15-14604582231198021","doi-asserted-by":"publisher","DOI":"10.1007\/s12325-019-01057-7"},{"key":"bibr16-14604582231198021","doi-asserted-by":"publisher","DOI":"10.1073\/pnas.192461099"},{"key":"bibr17-14604582231198021","doi-asserted-by":"publisher","DOI":"10.1001\/jamaoncol.2017.2411"},{"key":"bibr18-14604582231198021","doi-asserted-by":"publisher","DOI":"10.1200\/JCO.2016.67.9761"},{"key":"bibr19-14604582231198021","doi-asserted-by":"publisher","DOI":"10.1016\/S0140-6736(16)00561-4"},{"key":"bibr20-14604582231198021","doi-asserted-by":"publisher","DOI":"10.1056\/NEJMoa1507643"},{"key":"bibr21-14604582231198021","doi-asserted-by":"publisher","DOI":"10.1056\/NEJMoa1504627"},{"key":"bibr22-14604582231198021","doi-asserted-by":"publisher","DOI":"10.1056\/NEJMoa1504030"},{"key":"bibr23-14604582231198021","doi-asserted-by":"publisher","DOI":"10.1158\/1535-7163.MCT-14-0983"},{"key":"bibr24-14604582231198021","doi-asserted-by":"publisher","DOI":"10.1016\/j.brat.2009.06.019"},{"key":"bibr25-14604582231198021","doi-asserted-by":"publisher","DOI":"10.1016\/j.jbi.2017.07.012"},{"key":"bibr26-14604582231198021","doi-asserted-by":"publisher","DOI":"10.1038\/s41591-018-0316-z"},{"key":"bibr27-14604582231198021","doi-asserted-by":"publisher","DOI":"10.1200\/CCI.18.00098"},{"key":"bibr28-14604582231198021","doi-asserted-by":"publisher","DOI":"10.1016\/j.jbi.2019.103267"},{"key":"bibr29-14604582231198021","doi-asserted-by":"publisher","DOI":"10.1200\/CCI.21.00017"},{"key":"bibr30-14604582231198021","doi-asserted-by":"publisher","DOI":"10.1007\/s40487-021-00150-8"},{"key":"bibr31-14604582231198021","unstructured":"HumanSignal\/label-studio Human Signal: San Francisco, CA, USA, 2023. https:\/\/github.com\/HumanSignal\/label-studio (accessed 24 August 2023)."},{"key":"bibr32-14604582231198021","doi-asserted-by":"publisher","DOI":"10.5555\/1953048.2078195"},{"key":"bibr33-14604582231198021","unstructured":"spaCy Industrial-strength natural language processing in Python, Berlin, Germany: Explosion. https:\/\/spacy.io\/ (accessed 6 July 2022)."},{"key":"bibr34-14604582231198021","unstructured":"Neumann M, King D, Beltagy I, et al. ScispaCy: fast and robust models for biomedical natural language processing. In: Proceedings of the 18th BioNLP Workshop and Shared Task. Florence, Italy: Association for Computational Linguistics, pp. 319\u2013327."},{"key":"bibr35-14604582231198021","volume-title":"Training pipelines & models spaCy usage documentation"}],"container-title":["Health Informatics Journal"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/journals.sagepub.com\/doi\/pdf\/10.1177\/14604582231198021","content-type":"application\/pdf","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/journals.sagepub.com\/doi\/full-xml\/10.1177\/14604582231198021","content-type":"application\/xml","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/journals.sagepub.com\/doi\/pdf\/10.1177\/14604582231198021","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,4,29]],"date-time":"2026-04-29T22:28:16Z","timestamp":1777501696000},"score":1,"resource":{"primary":{"URL":"https:\/\/journals.sagepub.com\/doi\/10.1177\/14604582231198021"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2023,7]]},"references-count":35,"journal-issue":{"issue":"3","published-print":{"date-parts":[[2023,7]]}},"alternative-id":["10.1177\/14604582231198021"],"URL":"https:\/\/doi.org\/10.1177\/14604582231198021","relation":{},"ISSN":["1460-4582","1741-2811"],"issn-type":[{"value":"1460-4582","type":"print"},{"value":"1741-2811","type":"electronic"}],"subject":[],"published":{"date-parts":[[2023,7]]},"article-number":"14604582231198021"}}