{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,9,30]],"date-time":"2025-09-30T00:04:13Z","timestamp":1759190653115,"version":"3.44.0"},"reference-count":25,"publisher":"BMJ","issue":"9","license":[{"start":{"date-parts":[[2025,9,28]],"date-time":"2025-09-28T00:00:00Z","timestamp":1759017600000},"content-version":"unspecified","delay-in-days":27,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0\/"}],"funder":[{"name":"King\u2019s College London"},{"DOI":"10.13039\/501100000272","name":"National Institute for Health Research","doi-asserted-by":"crossref","id":[{"id":"10.13039\/501100000272","id-type":"DOI","asserted-by":"crossref"}]},{"name":"Applied Research Collaboration South London"},{"DOI":"10.13039\/501100000272","name":"NIHR","doi-asserted-by":"crossref","id":[{"id":"10.13039\/501100000272","id-type":"DOI","asserted-by":"crossref"}]},{"DOI":"10.13039\/100010872","name":"King\u2019s College Hospital NHS Foundation Trust","doi-asserted-by":"crossref","id":[{"id":"10.13039\/100010872","id-type":"DOI","asserted-by":"crossref"}]},{"DOI":"10.13039\/501100000265","name":"Medical Research Council","doi-asserted-by":"publisher","award":["MR\/W014386","MR\/Z504816\/1"],"award-info":[{"award-number":["MR\/W014386","MR\/Z504816\/1"]}],"id":[{"id":"10.13039\/501100000265","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/100031401","name":"UK Prevention Research Partnership","doi-asserted-by":"publisher","award":["MR-VO49879\/1"],"award-info":[{"award-number":["MR-VO49879\/1"]}],"id":[{"id":"10.13039\/100031401","id-type":"DOI","asserted-by":"publisher"}]},{"name":"Brain"},{"name":"NIHR Maudsley Biomedical Research Centre at the South London and Maudsley NHS Foundation Trust"},{"DOI":"10.13039\/100009362","name":"South London and Maudsley NHS Foundation Trust","doi-asserted-by":"publisher","id":[{"id":"10.13039\/100009362","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/100019418","name":"NIHR Maudsley Biomedical Research Centre","doi-asserted-by":"publisher","id":[{"id":"10.13039\/100019418","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":["bmj.com"],"crossmark-restriction":true},"short-container-title":["BMJ Open"],"accepted":{"date-parts":[[2025,9,4]]},"published-print":{"date-parts":[[2025,9]]},"abstract":"<jats:sec>\n                  <jats:title>Objectives<\/jats:title>\n                  <jats:p>Structural MRI of the brain is routinely performed on patients referred to memory clinics; however, resulting radiology reports, including volumetric assessments, are conventionally stored as unstructured free text. We sought to use natural language processing (NLP) to extract text relating to intracranial volumetric assessment from brain MRI text reports to enhance routine data availability for research purposes.<\/jats:p>\n               <\/jats:sec>\n               <jats:sec>\n                  <jats:title>Setting<\/jats:title>\n                  <jats:p>Electronic records from a large mental healthcare provider serving a geographic catchment of 1.3\u2009million residents in four boroughs of south London, UK.<\/jats:p>\n               <\/jats:sec>\n               <jats:sec>\n                  <jats:title>Design<\/jats:title>\n                  <jats:p>A corpus of 4007 de-identified brain MRI reports from patients referred to memory assessment services. An NLP algorithm was developed, using a span categorisation approach, to extract six binary (presence\/absence) categories from the text reports: (i) global volume loss, (ii) hippocampal\/medial temporal lobe volume loss and (iii) other lobar\/regional volume loss. Distributions of these categories were evaluated.<\/jats:p>\n               <\/jats:sec>\n               <jats:sec>\n                  <jats:title>Results<\/jats:title>\n                  <jats:p>The overall F1 score for the six categories was 0.89 (precision 0.92, recall 0.86), with the following precision\/recall for each category: presence of global volume loss 0.95\/0.95, absence of global volume loss 0.94\/0.77, presence of regional volume loss 0.80\/0.58, absence of regional volume loss 0.91\/0.93, presence of hippocampal volume loss 0.90\/0.88, and absence of hippocampal volume loss 0.94\/0.92.<\/jats:p>\n               <\/jats:sec>\n               <jats:sec>\n                  <jats:title>Conclusions<\/jats:title>\n                  <jats:p>These results support the feasibility and accuracy of using NLP techniques to extract volumetric assessments from radiology reports, and the potential for automated generation of novel meta-data from dementia assessments in electronic health records.<\/jats:p>\n               <\/jats:sec>","DOI":"10.1136\/bmjopen-2024-092459","type":"journal-article","created":{"date-parts":[[2025,9,29]],"date-time":"2025-09-29T07:20:13Z","timestamp":1759130413000},"page":"e092459","update-policy":"https:\/\/doi.org\/10.1136\/crossmarkpolicy","source":"Crossref","is-referenced-by-count":0,"title":["Dementia-related volumetric assessments in neuroradiology reports: a natural language processing-based study"],"prefix":"10.1136","volume":"15","author":[{"ORCID":"https:\/\/orcid.org\/0009-0008-1948-657X","authenticated-orcid":false,"given":"Adam John","family":"Mayers","sequence":"first","affiliation":[{"name":"King\u2019s College London, Institute of Psychiatry Psychology & Neuroscience, London, UK"},{"name":"Guy's and St Thomas\u2019 NHS Foundation Trust, London, UK"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Angus","family":"Roberts","sequence":"additional","affiliation":[{"name":"King\u2019s College London, Institute of Psychiatry Psychology & Neuroscience, London, UK"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-7977-1948","authenticated-orcid":false,"given":"Ashwin V","family":"Venkataraman","sequence":"additional","affiliation":[{"name":"King\u2019s College London, Institute of Psychiatry Psychology & Neuroscience, London, UK"},{"name":"South London and Maudsley NHS Foundation Trust, London, UK"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Christopher","family":"Booth","sequence":"additional","affiliation":[{"name":"Guy's and St Thomas\u2019 NHS Foundation Trust, London, UK"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Robert","family":"Stewart","sequence":"additional","affiliation":[{"name":"King\u2019s College London, Institute of Psychiatry Psychology & Neuroscience, London, UK"},{"name":"South London and Maudsley NHS Foundation Trust, London, UK"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"239","published-online":{"date-parts":[[2025,9,28]]},"reference":[{"key":"2025092900200747000_15.9.e092459.1","doi-asserted-by":"publisher","DOI":"10.1016\/S1474-4422(02)00002-9"},{"key":"2025092900200747000_15.9.e092459.2","doi-asserted-by":"crossref","first-page":"1","DOI":"10.1186\/s13195-020-00612-7","article-title":"Imaging biomarkers in neurodegeneration: current and future practices","volume":"12","author":"Young","year":"2020","journal-title":"Alz Res Therapy"},{"key":"2025092900200747000_15.9.e092459.3","doi-asserted-by":"crossref","DOI":"10.2196\/16816","article-title":"Systematic Evaluation of Research Progress on Natural Language Processing in Medicine Over the Past 20 Years: Bibliometric Study on PubMed","volume":"22","author":"Wang","year":"2020","journal-title":"J Med Internet Res"},{"key":"2025092900200747000_15.9.e092459.4","doi-asserted-by":"crossref","DOI":"10.1186\/s12911-021-01533-7","article-title":"A systematic review of natural language processing applied to radiology reports","volume":"21","author":"Casey","year":"2021","journal-title":"BMC Med Inform Decis Mak"},{"key":"2025092900200747000_15.9.e092459.5","doi-asserted-by":"crossref","first-page":"447","DOI":"10.1016\/j.nic.2020.08.001","article-title":"Review of Natural Language Processing in Radiology","volume":"30","author":"Luo","year":"2020","journal-title":"Neuroimaging Clin N Am"},{"key":"2025092900200747000_15.9.e092459.6","doi-asserted-by":"publisher","DOI":"10.1148\/radiol.16142770"},{"key":"2025092900200747000_15.9.e092459.7","doi-asserted-by":"crossref","first-page":"104779","DOI":"10.1016\/j.ijmedinf.2022.104779","article-title":"Applications of natural language processing in radiology: A systematic review","volume":"163","author":"Linna","year":"2022","journal-title":"Int J Med Inform"},{"key":"2025092900200747000_15.9.e092459.8","doi-asserted-by":"publisher","DOI":"10.1186\/s12911-021-01574-y"},{"key":"2025092900200747000_15.9.e092459.9","doi-asserted-by":"crossref","DOI":"10.1371\/journal.pone.0234908","article-title":"Machine learning and natural language processing methods to identify ischemic stroke, acuity and location from radiology reports","volume":"15","author":"Ong","year":"2020","journal-title":"PLoS ONE"},{"key":"2025092900200747000_15.9.e092459.10","doi-asserted-by":"crossref","first-page":"189","DOI":"10.1186\/s12883-021-02221-9","article-title":"Agreement between neuroimages and reports for natural language processing-based detection of silent brain infarcts and white matter disease","volume":"21","author":"Leung","year":"2021","journal-title":"BMC Neurol"},{"key":"2025092900200747000_15.9.e092459.11","doi-asserted-by":"crossref","first-page":"23","DOI":"10.1186\/s13326-019-0211-7","article-title":"Text mining brain imaging reports","volume":"10","author":"Alex","year":"2019","journal-title":"J Biomed Semantics"},{"key":"2025092900200747000_15.9.e092459.12","doi-asserted-by":"crossref","DOI":"10.1093\/jamiaopen\/ooab052","article-title":"Machine learning for modeling the progression of Alzheimer disease dementia using clinical data: a systematic literature review","volume":"4","author":"Kumar","year":"2021","journal-title":"JAMIA Open"},{"key":"2025092900200747000_15.9.e092459.13","doi-asserted-by":"crossref","unstructured":"Venkataraman AV , Marshall C , Rittman T . Automated brain image analysis in dementia using artificial intelligence: a roadmap for the development of clinical tools. Open Science Framework [Preprint] 2023. doi:10.31219\/osf.io\/myuq7","DOI":"10.31219\/osf.io\/myuq7"},{"key":"2025092900200747000_15.9.e092459.14","doi-asserted-by":"crossref","unstructured":"Searle T , Ibrahim Z , Dobson R . Comparing natural language processing techniques for Alzheimer\u2019s dementia prediction in spontaneous speech. arXiv 2020. doi:10.48550\/arXiv.2006.07358","DOI":"10.21437\/Interspeech.2020-2729"},{"key":"2025092900200747000_15.9.e092459.15","doi-asserted-by":"crossref","DOI":"10.1177\/2333721420959861","article-title":"Free-Text Documentation of Dementia Symptoms in Home Healthcare: A Natural Language Processing Study","volume":"6","author":"Topaz","year":"2020","journal-title":"Gerontol Geriatr Med"},{"key":"2025092900200747000_15.9.e092459.16","doi-asserted-by":"publisher","DOI":"10.1186\/1471-244X-9-1"},{"key":"2025092900200747000_15.9.e092459.17","doi-asserted-by":"crossref","DOI":"10.1136\/bmjopen-2015-008721","article-title":"Cohort profile of the South London and Maudsley NHS Foundation Trust Biomedical Research Centre (SLaM BRC) Case Register: current status and recent enhancement of an Electronic Mental Health Record-derived data resource","volume":"6","author":"Perera","year":"2016","journal-title":"BMJ Open"},{"key":"2025092900200747000_15.9.e092459.18","unstructured":"Schmuhl E , Miranda L , K\u00e1d\u00e1r \u00c1 , et al . Spancat: a new approach for span labelling. 2022. Available: https:\/\/explosion.ai\/blog\/spancat"},{"key":"2025092900200747000_15.9.e092459.19","unstructured":"Montani I , Honnibal M . Prodigy: a modern and scriptable annotation tool for creating training data for machine learning models. In: Prodigy. Explosion. Available: https:\/\/prodi.gy\/"},{"key":"2025092900200747000_15.9.e092459.20","unstructured":"Deleger L , Li Q , Lingren T , et al . Building gold standard corpora for medical natural language processing tasks. AMIA Annual Symposium Proceedings, Vol. 2012; 2012:144."},{"key":"2025092900200747000_15.9.e092459.21","doi-asserted-by":"crossref","DOI":"10.1038\/s41540-021-00200-x","article-title":"NERO: a biomedical named-entity (recognition) ontology with a large, annotated corpus reveals meaningful associations through text embedding","volume":"7","author":"Wang","year":"2021","journal-title":"NPJ Syst Biol Appl"},{"key":"2025092900200747000_15.9.e092459.22","doi-asserted-by":"crossref","unstructured":"Papay S , Klinger R , Pad\u00f3 S . Dissecting span identification tasks with performance prediction. arXiv 2020. doi:10.48550\/arXiv.2010.02587","DOI":"10.18653\/v1\/2020.emnlp-main.396"},{"key":"2025092900200747000_15.9.e092459.23","unstructured":"Honnibal M , Montani I , Van Landeghem S , et al . spaCy: industrial-strength natural language processing in python. 2020. Available: https:\/\/doi.org\/10.5281\/zenodo.1212303"},{"key":"2025092900200747000_15.9.e092459.24","unstructured":"Mayers A . Brain mri nlp (version 1.0.0) [computer software]. 2025. Available: https:\/\/doi.org\/10.5281\/zenodo.15790492"},{"key":"2025092900200747000_15.9.e092459.25","unstructured":"Spacy \u2013 available trained pipelines for English. 2025. Available: https:\/\/spacy.io\/models\/en#en_core_web_trf [Accessed 02 Jul 2025]."}],"container-title":["BMJ Open"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/syndication.highwire.org\/content\/doi\/10.1136\/bmjopen-2024-092459","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,9,29]],"date-time":"2025-09-29T07:20:22Z","timestamp":1759130422000},"score":1,"resource":{"primary":{"URL":"https:\/\/bmjopen.bmj.com\/lookup\/doi\/10.1136\/bmjopen-2024-092459"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,9]]},"references-count":25,"journal-issue":{"issue":"9","published-online":{"date-parts":[[2025,9,28]]},"published-print":{"date-parts":[[2025,9]]}},"alternative-id":["10.1136\/bmjopen-2024-092459"],"URL":"https:\/\/doi.org\/10.1136\/bmjopen-2024-092459","relation":{},"ISSN":["2044-6055","2044-6055"],"issn-type":[{"value":"2044-6055","type":"print"},{"value":"2044-6055","type":"electronic"}],"subject":[],"published":{"date-parts":[[2025,9]]}}}