{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,10,7]],"date-time":"2026-10-07T16:08:34Z","timestamp":1791389314619,"version":"4.3.3"},"reference-count":35,"publisher":"BMJ","issue":"2","license":[{"start":{"date-parts":[[2022,2,16]],"date-time":"2022-02-16T00:00:00Z","timestamp":1644969600000},"content-version":"unspecified","delay-in-days":15,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0\/"}],"funder":[{"DOI":"10.13039\/501100023699","name":"Health Data Research UK","doi-asserted-by":"crossref","award":["Not applicable"],"award-info":[{"award-number":["Not applicable"]}],"id":[{"id":"10.13039\/501100023699","id-type":"DOI","asserted-by":"crossref"}]},{"name":"National Institute for Health Research (NIHR) Biomedical Research Centre at South London and Maudsley NHS Foundation Trust and King's College London","award":["Not applicable"],"award-info":[{"award-number":["Not applicable"]}]},{"DOI":"10.13039\/501100000764","name":"King's College London","doi-asserted-by":"publisher","award":["Not applicable"],"award-info":[{"award-number":["Not applicable"]}],"id":[{"id":"10.13039\/501100000764","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/100012176","name":"Maudsley Charity","doi-asserted-by":"crossref","award":["BRC-2011-10035"],"award-info":[{"award-number":["BRC-2011-10035"]}],"id":[{"id":"10.13039\/100012176","id-type":"DOI","asserted-by":"crossref"}]},{"name":"Early Career Research Award, NIHR BRC Maudsley","award":["Not applicable"],"award-info":[{"award-number":["Not applicable"]}]},{"DOI":"10.13039\/501100000380","name":"Guy\u2019s and St Thomas\u2019 Charity","doi-asserted-by":"crossref","award":["BRC-2011-10035"],"award-info":[{"award-number":["BRC-2011-10035"]}],"id":[{"id":"10.13039\/501100000380","id-type":"DOI","asserted-by":"crossref"}]}],"content-domain":{"domain":["bmj.com"],"crossmark-restriction":true},"short-container-title":["BMJ Open"],"accepted":{"date-parts":[[2022,1,26]]},"published-print":{"date-parts":[[2022,2]]},"abstract":"<jats:sec>\n                    <jats:title>Objective<\/jats:title>\n                    <jats:p>This paper evaluates the application of a natural language processing (NLP) model for extracting clinical text referring to interpersonal violence using electronic health records (EHRs) from a large mental healthcare provider.<\/jats:p>\n                  <\/jats:sec>\n                  <jats:sec>\n                    <jats:title>Design<\/jats:title>\n                    <jats:p>A multidisciplinary team iteratively developed guidelines for annotating clinical text referring to violence. Keywords were used to generate a dataset which was annotated (ie, classified as affirmed, negated or irrelevant) for: presence of violence, patient status (ie, as perpetrator, witness and\/or victim of violence) and violence type (domestic, physical and\/or sexual). An NLP approach using a pretrained transformer model, BioBERT (Bidirectional Encoder Representations from Transformers for Biomedical Text Mining) was fine-tuned on the annotated dataset and evaluated using 10-fold cross-validation.<\/jats:p>\n                  <\/jats:sec>\n                  <jats:sec>\n                    <jats:title>Setting<\/jats:title>\n                    <jats:p>We used the Clinical Records Interactive Search (CRIS) database, comprising over 500 000 de-identified EHRs of patients within the South London and Maudsley NHS Foundation Trust, a specialist mental healthcare provider serving an urban catchment area.<\/jats:p>\n                  <\/jats:sec>\n                  <jats:sec>\n                    <jats:title>Participants<\/jats:title>\n                    <jats:p>Searches of CRIS were carried out based on 17 predefined keywords. Randomly selected text fragments were taken from the results for each keyword, amounting to 3771 text fragments from the records of 2832 patients.<\/jats:p>\n                  <\/jats:sec>\n                  <jats:sec>\n                    <jats:title>Outcome measures<\/jats:title>\n                    <jats:p>We estimated precision, recall and F1 score for each NLP model. We examined sociodemographic and clinical variables in patients giving rise to the text data, and frequencies for each annotated violence characteristic.<\/jats:p>\n                  <\/jats:sec>\n                  <jats:sec>\n                    <jats:title>Results<\/jats:title>\n                    <jats:p>Binary classification models were developed for six labels (violence presence, perpetrator, victim, domestic, physical and sexual). Among annotations affirmed for the presence of any violence, 78% (1724) referred to physical violence, 61% (1350) referred to patients as perpetrator and 33% (731) to domestic violence. NLP models\u2019 precision ranged from 89% (perpetrator) to 98% (sexual); recall ranged from 89% (victim, perpetrator) to 97% (sexual).<\/jats:p>\n                  <\/jats:sec>\n                  <jats:sec>\n                    <jats:title>Conclusions<\/jats:title>\n                    <jats:p>State of the art NLP models can extract and classify clinical text on violence from EHRs at acceptable levels of scale, efficiency and accuracy.<\/jats:p>\n                  <\/jats:sec>","DOI":"10.1136\/bmjopen-2021-052911","type":"journal-article","created":{"date-parts":[[2022,2,16]],"date-time":"2022-02-16T11:21:36Z","timestamp":1645010496000},"page":"e052911","update-policy":"https:\/\/doi.org\/10.1136\/crossmarkpolicy","source":"Crossref","is-referenced-by-count":41,"title":["Can natural language processing models extract and classify instances of interpersonal violence in mental healthcare electronic records: an applied evaluative study"],"prefix":"10.1136","volume":"12","author":[{"ORCID":"https:\/\/orcid.org\/0000-0002-3052-5698","authenticated-orcid":false,"given":"Riley","family":"Botelle","sequence":"first","affiliation":[{"name":"School of Medical Education, Guy's, King's and St Thomas' School of Medicine, London, UK"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Vishal","family":"Bhavsar","sequence":"additional","affiliation":[{"name":"Section of Women\u2019s Mental Health, Department of Health Services and Population Research, King's College London, London, UK"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-3182-905X","authenticated-orcid":false,"given":"Giouliana","family":"Kadra-Scalzo","sequence":"additional","affiliation":[{"name":"Psychological Medicine, Institute of Psychiatry, Psychology and Neuroscience, King's College London, London, UK"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Aurelie","family":"Mascio","sequence":"additional","affiliation":[{"name":"Psychological Medicine, Institute of Psychiatry, Psychology and Neuroscience, King's College London, London, UK"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Marcus V","family":"Williams","sequence":"additional","affiliation":[{"name":"School of Medical Education, Guy's, King's and St Thomas' School of Medicine, London, UK"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Angus","family":"Roberts","sequence":"additional","affiliation":[{"name":"Biostatistics and Health Informatics, King's College London, London, UK"},{"name":"Health Data Research UK, London, UK"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Sumithra","family":"Velupillai","sequence":"additional","affiliation":[{"name":"Psychological Medicine, Institute of Psychiatry, Psychology and Neuroscience, King's College London, London, UK"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Robert","family":"Stewart","sequence":"additional","affiliation":[{"name":"Psychological Medicine, Institute of Psychiatry, Psychology and Neuroscience, King's College London, London, UK"},{"name":"South London and Maudsley Mental Health NHS Trust, London, UK"}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"239","published-online":{"date-parts":[[2022,2,16]]},"reference":[{"key":"2025121408103482000_12.2.e052911.1","doi-asserted-by":"publisher","DOI":"10.1016\/s0140-6736(02)11133-0"},{"key":"2025121408103482000_12.2.e052911.2","doi-asserted-by":"publisher","DOI":"10.1136\/ip.7.2.104"},{"key":"2025121408103482000_12.2.e052911.3","doi-asserted-by":"publisher","DOI":"10.1186\/1471-2458-12-411"},{"key":"2025121408103482000_12.2.e052911.4","doi-asserted-by":"crossref","first-page":"305","DOI":"10.1177\/1524838016659488","article-title":"Physical health consequences of interpersonal trauma: a systematic review of the role of psychological variables","volume":"19","author":"L\u00f3pez-Mart\u00ednez","year":"2018","journal-title":"Trauma Violence Abuse"},{"key":"2025121408103482000_12.2.e052911.5","doi-asserted-by":"publisher","DOI":"10.1111\/j.1600-0447.2008.01300.x"},{"key":"2025121408103482000_12.2.e052911.6","doi-asserted-by":"publisher","DOI":"10.1017\/S0033291714001962"},{"key":"2025121408103482000_12.2.e052911.7","doi-asserted-by":"publisher","DOI":"10.1192\/bjp.bp.114.147843"},{"key":"2025121408103482000_12.2.e052911.8","doi-asserted-by":"publisher","DOI":"10.1371\/journal.pmed.1000120"},{"key":"2025121408103482000_12.2.e052911.9","doi-asserted-by":"crossref","DOI":"10.1371\/journal.pone.0093660","article-title":"Investigating exposure to violence and mental health in a diverse urban community sample: data from the South East London community health (SELCoH) survey","volume":"9","author":"Kadra","year":"2014","journal-title":"PLoS One"},{"key":"2025121408103482000_12.2.e052911.10","doi-asserted-by":"crossref","first-page":"168","DOI":"10.1017\/S2045796018000537","article-title":"Psychiatric symptoms and risk of victimisation: a population-based study from Southeast London","volume":"28","author":"Bhavsar","year":"2019","journal-title":"Epidemiol Psychiatr Sci"},{"key":"2025121408103482000_12.2.e052911.11","doi-asserted-by":"publisher","DOI":"10.1080\/08964289709596730"},{"key":"2025121408103482000_12.2.e052911.12","doi-asserted-by":"publisher","DOI":"10.1017\/S003329170500615X"},{"key":"2025121408103482000_12.2.e052911.13","article-title":"Estimating the costs of conflict and containment on adult acute inpatient psychiatric wards","volume":"26","author":"Flood","year":"2008","journal-title":"Nurs Econ"},{"key":"2025121408103482000_12.2.e052911.14","first-page":"193","article-title":"Improving the statistics on violence against women","volume":"22","author":"Walby","year":"2005","journal-title":"Stat J UN ECE"},{"key":"2025121408103482000_12.2.e052911.15","doi-asserted-by":"crossref","first-page":"540","DOI":"10.1016\/S2215-0366(17)30209-2","article-title":"Effect of implementation of a smoke-free policy on physical violence in a psychiatric inpatient setting: an interrupted time series analysis","volume":"4","author":"Robson","year":"2017","journal-title":"Lancet Psychiatry"},{"key":"2025121408103482000_12.2.e052911.16","doi-asserted-by":"crossref","first-page":"51","DOI":"10.1017\/S2045796016000731","article-title":"Factors associated with use of psychiatric intensive care and seclusion in adult inpatient mental health services","volume":"27","author":"Cullen","year":"2018","journal-title":"Epidemiol Psychiatr Sci"},{"key":"2025121408103482000_12.2.e052911.17","doi-asserted-by":"publisher","DOI":"10.1093\/jamia\/ocv180"},{"key":"2025121408103482000_12.2.e052911.18","doi-asserted-by":"crossref","first-page":"14","DOI":"10.1016\/j.jbi.2017.07.012","article-title":"Natural language processing systems for capturing and standardizing unstructured clinical information: a systematic review","volume":"73","author":"Kreimeyer","year":"2017","journal-title":"J Biomed Inform"},{"key":"2025121408103482000_12.2.e052911.19","doi-asserted-by":"crossref","first-page":"34","DOI":"10.1016\/j.jbi.2017.11.011","article-title":"Clinical information extraction applications: a literature review","volume":"77","author":"Wang","year":"2018","journal-title":"J Biomed Inform"},{"key":"2025121408103482000_12.2.e052911.20","doi-asserted-by":"publisher","DOI":"10.1136\/jamia.1994.95236146"},{"key":"2025121408103482000_12.2.e052911.21","doi-asserted-by":"publisher","DOI":"10.1136\/jamia.2009.001560"},{"key":"2025121408103482000_12.2.e052911.22","doi-asserted-by":"publisher","DOI":"10.1093\/jamia\/ocx132"},{"key":"2025121408103482000_12.2.e052911.23","doi-asserted-by":"crossref","DOI":"10.2196\/14782","article-title":"Efficient reuse of natural language processing models for phenotype-mention identification in free-text electronic medical records: a phenotype embedding approach","volume":"7","author":"Wu","year":"2019","journal-title":"JMIR Med Inform"},{"key":"2025121408103482000_12.2.e052911.24","unstructured":"Devlin J , Chang M-W , Lee K . BERT: Pre-training of Deep Bidirectional Transformers for Language Understanding. In: Proceedings of the 2019 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies, Volume 1 (Long and Short Papers). Minneapolis, Minnesota: Association for Computational Linguistics, 2019: 4171\u201386."},{"key":"2025121408103482000_12.2.e052911.25","doi-asserted-by":"publisher","DOI":"10.1093\/bioinformatics\/btz682"},{"key":"2025121408103482000_12.2.e052911.26","unstructured":"Mascio A , Kraljevic Z , Bean D . Comparative Analysis of Text Classification Approaches in Electronic Health Records. arXiv:200506624 [cs] Published Online First: 8 May 2020. Available: http:\/\/arxiv.org\/abs\/2005.06624 [Accessed 18 Jan 2021]."},{"key":"2025121408103482000_12.2.e052911.27","doi-asserted-by":"crossref","first-page":"1297","DOI":"10.1093\/jamia\/ocz096","article-title":"Enhancing clinical concept extraction with contextual embeddings","volume":"26","author":"Si","year":"2019","journal-title":"J Am Med Inform Assoc"},{"key":"2025121408103482000_12.2.e052911.28","doi-asserted-by":"crossref","DOI":"10.1192\/bjo.2020.52","article-title":"The association between neighbourhood characteristics and physical victimisation in men and women with mental disorders","volume":"6","author":"Bhavsar","year":"2020","journal-title":"BJPsych Open"},{"key":"2025121408103482000_12.2.e052911.29","doi-asserted-by":"publisher","DOI":"10.1136\/bmjopen-2016-012012"},{"key":"2025121408103482000_12.2.e052911.30","doi-asserted-by":"crossref","DOI":"10.1038\/s41598-020-80457-0","article-title":"A natural language processing approach for identifying temporal disease onset information from mental healthcare text","volume":"11","author":"Viani","year":"2021","journal-title":"Sci Rep"},{"key":"2025121408103482000_12.2.e052911.31","doi-asserted-by":"publisher","DOI":"10.1136\/bmjopen-2015-008721"},{"key":"2025121408103482000_12.2.e052911.32","unstructured":"Clinical Record Interactive Search (CRIS). Available: https:\/\/www.slam.nhs.uk\/quality-and-research\/clinical-record-interactive-search-cris\/ [Accessed 2 Feb 2021]."},{"key":"2025121408103482000_12.2.e052911.33","unstructured":"World Health Organization . International statistical classification of diseases and related health problems. 10th revision. 2nd edition. Geneva: World Health Organization, 2004."},{"key":"2025121408103482000_12.2.e052911.34","doi-asserted-by":"crossref","unstructured":"Effectiveness of anonymised information sharing and use in health service, police, and local government partnership for preventing violence related injury: experimental study and time series analysis | The BMJ. Available: https:\/\/www.bmj.com\/content\/342\/bmj.d3313 [Accessed 28 Jan 2021].","DOI":"10.1136\/bmj.d3313"},{"key":"2025121408103482000_12.2.e052911.35","doi-asserted-by":"publisher","DOI":"10.1007\/s11524-007-9229-8"}],"container-title":["BMJ Open"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/syndication.highwire.org\/content\/doi\/10.1136\/bmjopen-2021-052911","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,12,14]],"date-time":"2025-12-14T16:10:45Z","timestamp":1765728645000},"score":1,"resource":{"primary":{"URL":"https:\/\/bmjopen.bmj.com\/lookup\/doi\/10.1136\/bmjopen-2021-052911"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2022,2]]},"references-count":35,"journal-issue":{"issue":"2","published-online":{"date-parts":[[2022,2,16]]},"published-print":{"date-parts":[[2022,2]]}},"alternative-id":["10.1136\/bmjopen-2021-052911"],"URL":"https:\/\/doi.org\/10.1136\/bmjopen-2021-052911","relation":{},"ISSN":["2044-6055","2044-6055"],"issn-type":[{"value":"2044-6055","type":"print"},{"value":"2044-6055","type":"electronic"}],"subject":[],"published":{"date-parts":[[2022,2]]}}}