{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,8,1]],"date-time":"2026-08-01T00:45:25Z","timestamp":1785545125773,"version":"3.56.0"},"reference-count":28,"publisher":"JMIR Publications Inc.","content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["JMIR Med Inform"],"abstract":"Abstract<\/jats:title>\n \n Background<\/jats:title>\n Clinical natural language processing (cNLP) techniques are commonly developed and used to extract information from clinical notes to facilitate clinical decision-making and research. However, they are less established for rare diseases such as lymphoid malignancies due to the lack of annotated data as well as the heterogeneity and complexity of how clinical information is documented. In addition, there is increasing evidence that cNLP techniques may be prone to biases embedded in clinical documentation or model development. These biases can result in disparities in performance when extracting clinical information or predicting patient outcomes.<\/jats:p>\n <\/jats:sec>\n \n Objective<\/jats:title>\n This study aims to report the development and validation of a cNLP pipeline that extracts clinical information such as performance status, staging, and diagnosis, as well as less common information such as substance use and military environmental exposures, from the clinical notes of veterans with lymphoid malignancies.<\/jats:p>\n <\/jats:sec>\n \n Methods<\/jats:title>\n We developed a rule-based cNLP pipeline that integrates domain expertise. We tested and compared the performance of the cNLP pipeline on notes from 2 veteran patient cohorts: one from non-Hispanic White veterans and the other from non-Hispanic Black veterans.<\/jats:p>\n <\/jats:sec>\n \n Results<\/jats:title>\n \n Overall, our pipeline achieved promising performance on our study data, especially for extracting entities that have standard clinical documentation, such as performance status. We also found that while the pipeline has robust performance across the two patient groups, the false-positive and false-negative rates were significantly associated with race for detecting the primary diagnosis (\n P<\/jats:italic>\n =.001 for both); the false-negative rate was significantly associated with race for identifying substance use (\n P<\/jats:italic>\n =.02).\n <\/jats:p>\n <\/jats:sec>\n \n Conclusions<\/jats:title>\n The system exhibits satisfying and comparable performance for most clinical entities of interest except for (1) the primary diagnosis and (2) substance use. Future work will address the challenges encountered in developing and deploying the cNLP pipeline on the Department of Veterans Affairs data for rare cancers and enhance the performance of cNLP systems to avoid biases.<\/jats:p>\n <\/jats:sec>","DOI":"10.2196\/63908","type":"journal-article","created":{"date-parts":[[2025,9,15]],"date-time":"2025-09-15T17:20:06Z","timestamp":1757956806000},"page":"e63908-e63908","source":"Crossref","is-referenced-by-count":0,"title":["Clinical Information Extraction From Notes of Veterans With Lymphoid Malignancies: Natural Language Processing Study"],"prefix":"10.2196","volume":"13","author":[{"ORCID":"https:\/\/orcid.org\/0000-0003-0181-018X","authenticated-orcid":false,"given":"Lu","family":"He","sequence":"first","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-6596-6231","authenticated-orcid":false,"given":"Matthew R","family":"Moldenhauer","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-4121-4948","authenticated-orcid":false,"given":"Kai","family":"Zheng","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-0416-5115","authenticated-orcid":false,"given":"Helen","family":"Ma","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"1010","published-online":{"date-parts":[[2025,10,16]]},"reference":[{"key":"R1","doi-asserted-by":"publisher","DOI":"10.1016\/j.jbi.2017.11.011","article-title":"Clinical information extraction applications: a literature review","volume":"77","author":"Wang","journal-title":"J Biomed Inform"},{"issue":"6","key":"R2","doi-asserted-by":"publisher","DOI":"10.1200\/CCI.22.00006","article-title":"Assessment of electronic health record for cancer research and patient care through a scoping review of cancer natural language processing","volume":"6","author":"Wang","journal-title":"JCO Clin Cancer Inform"},{"key":"R3","unstructured":"Key statistics for non-Hodgkin lymphoma. American Cancer Society. URL: https:\/\/www.cancer.org\/cancer\/non-hodgkin-lymphoma\/about\/key-statistics.html [Accessed 23-08-2022]"},{"key":"R4","unstructured":"Key statistics for chronic lymphocytic leukemia (CLL). American Cancer Society. URL: https:\/\/www.cancer.org\/cancer\/types\/chronic-lymphocytic-leukemia\/about\/key-statistics.html [Accessed 08-06-2023]"},{"key":"R5","unstructured":"Key statistics for Hodgkin lymphoma. American Cancer Society. URL: https:\/\/www.cancer.org\/cancer\/types\/hodgkin-lymphoma\/about\/key-statistics.html [Accessed 08-06-2023]"},{"key":"R6","unstructured":"Key statistics for multiple myeloma. American Cancer Society. URL: https:\/\/www.cancer.org\/cancer\/types\/multiple-myeloma\/about\/key-statistics.html [Accessed 08-06-2023]"},{"key":"R7","unstructured":"Key statistics about Waldenstr\u00f6m macroglobulinemia. American Cancer Society. URL: https:\/\/www.cancer.org\/cancer\/types\/waldenstrom-macroglobulinemia\/about\/key-statistics.html [Accessed 08-06-2023]"},{"key":"R8","unstructured":"National Academies of Sciences, Engineering, and Medicine. Veterans and Agent Orange. National Academies Press; 2018. ISBN: 9780309477161"},{"key":"R9","unstructured":"The PACT Act. US Department of Veterans Affairs. URL: https:\/\/tinyurl.com\/yc26bfk7 [Accessed 20-02-2023]"},{"issue":"3","key":"R10","doi-asserted-by":"publisher","first-page":"281","DOI":"10.1001\/journalofethics.2017.19.3.stas1-1703","article-title":"Language, structure, and reuse in the electronic health record","volume":"19","author":"Roberts","journal-title":"AMA J Ethics"},{"key":"R11","unstructured":"VA Informatics and Computing Infrastructure (VINCI). US Department of Veterans Affairs. URL: https:\/\/www.research.va.gov\/programs\/vinci\/ [Accessed 07-10-2025]"},{"key":"R12","unstructured":"Veterans Health Administration. US Department of Veterans Affairs. URL: https:\/\/www.va.gov\/health\/aboutvha.asp [Accessed 27-01-2025]"},{"issue":"11","key":"R13","doi-asserted-by":"publisher","first-page":"2583","DOI":"10.1093\/jamia\/ocae231","article-title":"CACER: clinical concept annotations for cancer events and relations","volume":"31","author":"Fu","journal-title":"J Am Med Inform Assoc"},{"key":"R14","doi-asserted-by":"publisher","DOI":"10.1016\/j.jbi.2020.103631","article-title":"Annotating social determinants of health using active learning, and characterizing determinants using neural event extraction","volume":"113","author":"Lybarger","journal-title":"J Biomed Inform"},{"issue":"8","key":"R15","doi-asserted-by":"publisher","first-page":"1438","DOI":"10.1093\/jamia\/ocad054","article-title":"Automatic extraction of social determinants of health from medical notes of chronic lower back pain patients","volume":"30","author":"Lituiev","journal-title":"J Am Med Inform Assoc"},{"key":"R16","volume":"2012","author":"Deleger","journal-title":"AMIA Annu Symp Proc"},{"issue":"8","key":"R17","doi-asserted-by":"publisher","first-page":"1429","DOI":"10.1093\/jamia\/ocad081","article-title":"Automated identification of eviction status from electronic health record notes","volume":"30","author":"Yao","journal-title":"J Am Med Inform Assoc"},{"key":"R18","unstructured":"Lu Q Li R Wen A Wang J Wang L Liu H . Large language models struggle in token-level clinical named entity recognition. arXiv. Preprint posted online on Jun 30, 2024. [doi: 10.48550\/arXiv.2407.00731]"},{"key":"R19","doi-asserted-by":"publisher","DOI":"10.1016\/j.ijmedinf.2022.104973","article-title":"Assess the documentation of cognitive tests and biomarkers in electronic health records via natural language processing for Alzheimer\u2019s disease and related dementias","volume":"170","author":"Chen","journal-title":"Int J Med Inform"},{"issue":"4","key":"R20","doi-asserted-by":"publisher","first-page":"572","DOI":"10.1016\/j.pan.2024.03.016","article-title":"Identification of pancreatic cancer risk factors from clinical notes using natural language processing","volume":"24","author":"Sarwal","journal-title":"Pancreatology"},{"issue":"10","key":"R21","doi-asserted-by":"publisher","first-page":"1547","DOI":"10.1093\/jamia\/ocaa128","article-title":"Assessing the enrichment of dietary supplement coverage in the Unified Medical Language System","volume":"27","author":"Vasilakes","journal-title":"J Am Med Inform Assoc"},{"issue":"1","key":"R22","doi-asserted-by":"publisher","first-page":"3","DOI":"10.1093\/jamia\/ocz166","article-title":"2018 n2c2 shared task on adverse drug events and medication extraction in electronic health records","volume":"27","author":"Henry","journal-title":"J Am Med Inform Assoc"},{"issue":"10","key":"R23","doi-asserted-by":"publisher","first-page":"6209","DOI":"10.3390\/app13106209","article-title":"A natural language processing algorithm to improve completeness of ECOG performance status in real-world data","volume":"13","author":"Cohen","journal-title":"Appl Sci (Basel)"},{"key":"R24","doi-asserted-by":"publisher","DOI":"10.1177\/10732748241279518","article-title":"A multi-institutional natural language processing pipeline to extract performance status from electronic health records","volume":"31","author":"Maghsoudi","journal-title":"Cancer Control"},{"issue":"1","key":"R25","doi-asserted-by":"publisher","DOI":"10.1186\/s13045-023-01521-6","article-title":"The association of Agent Orange exposure with the progression of monoclonal gammopathy of undetermined significance to multiple myeloma: a population-based study of Vietnam War Era Veterans","volume":"17","author":"Liu","journal-title":"J Hematol Oncol"},{"key":"R26","unstructured":"PACT Act toxic exposure screening. US Department Veterans Affairs. URL: https:\/\/www.va.gov\/walla-walla-health-care\/programs\/pact-act-toxic-exposure-screening\/ [Accessed 27-01-2025]"},{"issue":"7","key":"R27","doi-asserted-by":"publisher","first-page":"1208","DOI":"10.1093\/jamia\/ocac040","article-title":"CancerBERT: a cancer domain-specific language model for extracting breast cancer phenotypes from electronic health records","volume":"29","author":"Zhou","journal-title":"J Am Med Inform Assoc"},{"key":"R28","unstructured":"Yan X Chen A PourNejatian N et al. GatorTron: a large clinical language model to unlock patient information from unstructured electronic health records. arXiv. Preprint posted online on Feb 2, 2022. [doi: 10.48550\/arXiv.2203.03540]"}],"container-title":["JMIR Medical Informatics"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/medinform.jmir.org\/2025\/1\/e63908","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,7,31]],"date-time":"2026-07-31T22:30:44Z","timestamp":1785537044000},"score":1,"resource":{"primary":{"URL":"https:\/\/medinform.jmir.org\/2025\/1\/e63908"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,10,16]]},"references-count":28,"URL":"https:\/\/doi.org\/10.2196\/63908","relation":{},"ISSN":["2291-9694"],"issn-type":[{"value":"2291-9694","type":"electronic"}],"subject":[],"published":{"date-parts":[[2025,10,16]]},"article-number":"v13i6e63908"}}