{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,6,30]],"date-time":"2026-06-30T03:31:33Z","timestamp":1782790293054,"version":"3.54.5"},"reference-count":48,"publisher":"SAGE Publications","issue":"4","license":[{"start":{"date-parts":[[2019,3,7]],"date-time":"2019-03-07T00:00:00Z","timestamp":1551916800000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/journals.sagepub.com\/page\/policies\/text-and-data-mining-license"}],"content-domain":{"domain":["journals.sagepub.com"],"crossmark-restriction":true},"short-container-title":["Health Informatics J"],"published-print":{"date-parts":[[2020,12]]},"abstract":"<jats:p>Learning from patient safety incident reports is a vital part of improving healthcare. However, the volume of reports and their largely free-text nature poses a major analytic challenge. The objective of this study was to test the capability of autonomous classifying of free text within patient safety incident reports to determine incident type and the severity of harm outcome. Primary care patient safety incident reports (n=31333) previously expert-categorised by clinicians (training data) were processed using J48, SVM and Na\u00efve Bayes.<\/jats:p>\n                  <jats:p>The SVM classifier was the highest scoring classifier for incident type (AUROC, 0.891) and severity of harm (AUROC, 0.708). Incident reports containing deaths were most easily classified, correctly identifying 72.82% of reports. In conclusion, supervised ML can be used to classify patient safety incident report categories. The severity classifier, whilst not accurate enough to replace manual processing, could provide a valuable screening tool for this critical aspect of patient safety.<\/jats:p>","DOI":"10.1177\/1460458219833102","type":"journal-article","created":{"date-parts":[[2019,3,7]],"date-time":"2019-03-07T07:51:04Z","timestamp":1551945064000},"page":"3123-3139","update-policy":"https:\/\/doi.org\/10.1177\/sage-journals-update-policy","source":"Crossref","is-referenced-by-count":42,"title":["Automated classification of primary care patient safety incident report content and severity using supervised machine learning (ML) approaches"],"prefix":"10.1177","volume":"26","author":[{"ORCID":"https:\/\/orcid.org\/0000-0001-5277-2342","authenticated-orcid":false,"given":"Huw Prosser","family":"Evans","sequence":"first","affiliation":[{"name":"Cardiff University, UK"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Athanasios","family":"Anastasiou","sequence":"additional","affiliation":[{"name":"Swansea University, UK"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Adrian","family":"Edwards","sequence":"additional","affiliation":[{"name":"Cardiff University, UK"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Peter","family":"Hibbert","sequence":"additional","affiliation":[{"name":"Macquarie University, Australia; University of South Australia, Australia"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Meredith","family":"Makeham","sequence":"additional","affiliation":[{"name":"Macquarie University, Australia"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Saturnino","family":"Luz","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Aziz","family":"Sheikh","sequence":"additional","affiliation":[{"name":"The University of Edinburgh, UK"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Liam","family":"Donaldson","sequence":"additional","affiliation":[{"name":"London School of Hygiene & Tropical Medicine, UK"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Andrew","family":"Carson-Stevens","sequence":"additional","affiliation":[{"name":"Cardiff University, UK; Macquarie University, Australia"}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"179","published-online":{"date-parts":[[2019,3,7]]},"reference":[{"key":"bibr1-1460458219833102","doi-asserted-by":"publisher","DOI":"10.1136\/bmj.i2139"},{"key":"bibr2-1460458219833102","doi-asserted-by":"publisher","DOI":"10.1136\/bmj.322.7285.517"},{"key":"bibr3-1460458219833102","doi-asserted-by":"publisher","DOI":"10.1093\/qjmed\/hcu145"},{"key":"bibr4-1460458219833102","doi-asserted-by":"publisher","DOI":"10.1136\/bmjqs-2015-004178"},{"key":"bibr5-1460458219833102","unstructured":"World Health Organization. Conceptual framework for the international classification for patient safety. Geneva: World Health Organization, 2010, pp. 1\u2013153."},{"key":"bibr6-1460458219833102","doi-asserted-by":"publisher","DOI":"10.1111\/1468-0009.12166"},{"key":"bibr7-1460458219833102","doi-asserted-by":"publisher","DOI":"10.1136\/bmjopen-2015-009079"},{"key":"bibr8-1460458219833102","unstructured":"National Patient Safety Agency (NPSA). Seven steps to patient safety: full reference guide, http:\/\/www.nrls.npsa.nhs.uk\/resources\/?entryid45=59787&q=0%c2%acseven+steps+to+patient+safety%c2%ac (2004, accessed 15 June 2016)."},{"key":"bibr9-1460458219833102","unstructured":"National Patient Safety Agency (NPSA). Being open: communicating patient safety incidents with patients, their families and care, http:\/\/www.nrls.npsa.nhs.uk\/resources\/collections\/being-open\/?entryid45=83726 (2009, accessed 1 August 2016)."},{"key":"bibr10-1460458219833102","doi-asserted-by":"publisher","DOI":"10.1093\/intqhc\/mzv091"},{"key":"bibr11-1460458219833102","doi-asserted-by":"publisher","DOI":"10.1016\/j.drudis.2006.02.011"},{"key":"bibr12-1460458219833102","doi-asserted-by":"publisher","DOI":"10.1126\/science.aaa8685"},{"key":"bibr13-1460458219833102","doi-asserted-by":"publisher","DOI":"10.1097\/PEC.0000000000000484"},{"key":"bibr14-1460458219833102","doi-asserted-by":"publisher","DOI":"10.1197\/jamia.M1794"},{"key":"bibr15-1460458219833102","volume-title":"Data mining: practical machine learning tools and techniques","author":"Witten IH","year":"2011","edition":"3"},{"key":"bibr16-1460458219833102","doi-asserted-by":"publisher","DOI":"10.3310\/hsdr04270"},{"key":"bibr17-1460458219833102","doi-asserted-by":"publisher","DOI":"10.1197\/jamia.M2437"},{"key":"bibr18-1460458219833102","doi-asserted-by":"crossref","first-page":"e55","DOI":"10.1136\/qshc.2008.027961","volume":"19","author":"Ong MS","year":"2010","journal-title":"Qual Saf Health Care"},{"key":"bibr19-1460458219833102","first-page":"52","volume":"188","author":"Gupta J","year":"2013","journal-title":"Stud Health Technol Inform"},{"key":"bibr20-1460458219833102","unstructured":"Ng AY, Jordan MI. On discriminative vs. generative classifiers: a comparison of logistic regression and naive Bayes. In: Advances in neural information processing systems, 2002; pp. 841\u2013848, https:\/\/ai.stanford.edu\/~ang\/papers\/nips01-discriminativegenerative.pdf"},{"key":"bibr21-1460458219833102","doi-asserted-by":"publisher","DOI":"10.1111\/acem.12174"},{"key":"bibr22-1460458219833102","doi-asserted-by":"publisher","DOI":"10.3233\/IDA-2002-6504"},{"key":"bibr23-1460458219833102","first-page":"137","volume":"192","author":"Fujita K","year":"2013","journal-title":"Stud Health Technol Inform"},{"key":"bibr24-1460458219833102","doi-asserted-by":"publisher","DOI":"10.1007\/s10916-012-9859-6"},{"key":"bibr25-1460458219833102","volume-title":"The WEKA Workbench. Online Appendix for \"Data Mining: Practical Machine Learning Tools and Techniques\"","author":"Frank E","year":"2016","edition":"4"},{"key":"bibr26-1460458219833102","first-page":"370","volume":"207","author":"Alicante A","year":"2014","journal-title":"Stud Health Technol Inform"},{"key":"bibr27-1460458219833102","unstructured":"Kachites M. Bow: a toolkit for statistical language modeling, text retrieval, classification and clustering. 1996, http:\/\/www.cs.cmu.edu\/~mccallum\/bow"},{"key":"bibr28-1460458219833102","doi-asserted-by":"publisher","DOI":"10.1016\/j.procs.2011.01.023"},{"key":"bibr29-1460458219833102","doi-asserted-by":"publisher","DOI":"10.1016\/j.compind.2015.12.001"},{"key":"bibr30-1460458219833102","volume-title":"Introduction to information retrieval","author":"Manning CD","year":"2009"},{"key":"bibr31-1460458219833102","doi-asserted-by":"publisher","DOI":"10.1145\/1007730.1007735"},{"key":"bibr32-1460458219833102","volume":"192","author":"Wong Z","year":"2013","journal-title":"Stud Health Technol Inform"},{"key":"bibr33-1460458219833102","doi-asserted-by":"publisher","DOI":"10.1016\/j.ijmedinf.2011.08.001"},{"key":"bibr34-1460458219833102","doi-asserted-by":"publisher","DOI":"10.1016\/j.compind.2015.09.005"},{"key":"bibr35-1460458219833102","doi-asserted-by":"publisher","DOI":"10.1016\/j.jbi.2006.06.003"},{"key":"bibr36-1460458219833102","first-page":"722","volume":"2010","author":"Savova GK","year":"2010","journal-title":"AMIA Annu Symp Proc"},{"key":"bibr37-1460458219833102","unstructured":"Moise I, Pournaras E, Helbing D. Classification and decision trees, https:\/\/www.ethz.ch\/content\/dam\/ethz\/special-interest\/gess\/computational-social-science-dam\/documents\/education\/Spring2016\/Datascience\/Classification%20and%20Decision%20Trees.pdf (2016, accessed 7 December 2016)."},{"key":"bibr38-1460458219833102","doi-asserted-by":"publisher","DOI":"10.1148\/radiol.2241011118"},{"key":"bibr39-1460458219833102","doi-asserted-by":"publisher","DOI":"10.1007\/s10620-012-2433-8"},{"key":"bibr40-1460458219833102","doi-asserted-by":"publisher","DOI":"10.1007\/s10278-011-9411-0"},{"key":"bibr41-1460458219833102","first-page":"32","volume-title":"Proceedings of the 31st international conference on machine learning","author":"Le QV"},{"issue":"6","key":"bibr42-1460458219833102","volume":"10","author":"Danso SO","year":"2013","journal-title":"International Journal of Computer Science Issues"},{"key":"bibr43-1460458219833102","first-page":"250","volume":"180","author":"Fujita K","year":"2012","journal-title":"Stud Health Technol Inform"},{"key":"bibr44-1460458219833102","doi-asserted-by":"publisher","DOI":"10.1186\/s12911-017-0483-8"},{"key":"bibr45-1460458219833102","doi-asserted-by":"crossref","unstructured":"Alghoson AM. Medical document classification based on MeSH. New York: IEEE, 2013, pp. 2571\u20132575.","DOI":"10.1109\/HICSS.2014.324"},{"key":"bibr46-1460458219833102","doi-asserted-by":"publisher","DOI":"10.1136\/jamia.2009.001024"},{"key":"bibr47-1460458219833102","doi-asserted-by":"publisher","DOI":"10.1111\/j.1365-2125.2011.04153.x"},{"key":"bibr48-1460458219833102","doi-asserted-by":"publisher","DOI":"10.1016\/j.retrec.2012.12.001"}],"container-title":["Health Informatics Journal"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/journals.sagepub.com\/doi\/pdf\/10.1177\/1460458219833102","content-type":"application\/pdf","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/journals.sagepub.com\/doi\/full-xml\/10.1177\/1460458219833102","content-type":"application\/xml","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/journals.sagepub.com\/doi\/pdf\/10.1177\/1460458219833102","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,4,29]],"date-time":"2026-04-29T22:31:00Z","timestamp":1777501860000},"score":1,"resource":{"primary":{"URL":"https:\/\/journals.sagepub.com\/doi\/10.1177\/1460458219833102"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2019,3,7]]},"references-count":48,"journal-issue":{"issue":"4","published-print":{"date-parts":[[2020,12]]}},"alternative-id":["10.1177\/1460458219833102"],"URL":"https:\/\/doi.org\/10.1177\/1460458219833102","relation":{},"ISSN":["1460-4582","1741-2811"],"issn-type":[{"value":"1460-4582","type":"print"},{"value":"1741-2811","type":"electronic"}],"subject":[],"published":{"date-parts":[[2019,3,7]]}}}