{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,4,30]],"date-time":"2026-04-30T12:00:32Z","timestamp":1777550432296,"version":"3.51.4"},"reference-count":62,"publisher":"SAGE Publications","license":[{"start":{"date-parts":[[2025,1,1]],"date-time":"2025-01-01T00:00:00Z","timestamp":1735689600000},"content-version":"unspecified","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0\/"}],"funder":[{"name":"Framework Collaboration Agreement between the University of Strathclyde and Lanarkshire Health Board","award":["UoS.NHSL.270619"],"award-info":[{"award-number":["UoS.NHSL.270619"]}]}],"content-domain":{"domain":["journals.sagepub.com"],"crossmark-restriction":true},"short-container-title":["DIGITAL HEALTH"],"published-print":{"date-parts":[[2025,1]]},"abstract":"<jats:sec>\n                    <jats:title>Background<\/jats:title>\n                    <jats:p>Frequent attenders to accident and emergency (A&amp;E) services pose complex challenges for healthcare providers, often driven by critical clinical needs. Machine learning (ML) offers potential for predictive approaches to managing frequent attendance, yet its application in this area is limited. Existing studies often focus on specific populations or models, raising concerns about generalisability. Identifying risk factors for frequent attendance and high resource use is crucial for effective prevention strategies.<\/jats:p>\n                  <\/jats:sec>\n                  <jats:sec>\n                    <jats:title>Objectives<\/jats:title>\n                    <jats:p>This research aims to evaluate the strengths and weaknesses of ML approaches in predicting frequent A&amp;E attendance in NHS Lanarkshire, Scotland, identify associated risk factors and compare findings with existing research to uncover commonalities and differences.<\/jats:p>\n                  <\/jats:sec>\n                  <jats:sec>\n                    <jats:title>Method<\/jats:title>\n                    <jats:p>Health and social care data were collected from 17,437 A&amp;E patients in NHS Lanarkshire (2021\u20132022), including clinical, social and demographic information. Five classification models were tested: multinomial logistic regression (LR), random forests (RF), support vector machine (SVM) classifier, k-nearest neighbours (k-NN) and multi-layer perceptron (MLP) classifier. Models were evaluated using a confusion matrix and metrics such as precision, recall, F1 and area under the curve. Shapley values were used to identify risk factors.<\/jats:p>\n                  <\/jats:sec>\n                  <jats:sec>\n                    <jats:title>Results<\/jats:title>\n                    <jats:p>MLP achieved the highest F1 score (0.75), followed by k-NN, RF and SVM (0.72 each), and LR (0.70). Key health conditions and risk factors consistently predicted frequent attendance across models, with some variation highlighting dataset-specific characteristics.<\/jats:p>\n                  <\/jats:sec>\n                  <jats:sec>\n                    <jats:title>Conclusions<\/jats:title>\n                    <jats:p>This study underscores the utility of combining ML models to enhance prediction accuracy and identify risk factors. Findings align with existing research but reveal unique insights specific to the dataset and methodology.<\/jats:p>\n                  <\/jats:sec>","DOI":"10.1177\/20552076251315293","type":"journal-article","created":{"date-parts":[[2025,3,4]],"date-time":"2025-03-04T13:34:24Z","timestamp":1741095264000},"update-policy":"https:\/\/doi.org\/10.1177\/sage-journals-update-policy","source":"Crossref","is-referenced-by-count":0,"title":["Using machine learning to identify frequent attendance at accident and emergency  services in Lanarkshire"],"prefix":"10.1177","volume":"11","author":[{"ORCID":"https:\/\/orcid.org\/0009-0009-1894-6316","authenticated-orcid":false,"given":"Fergus","family":"Reid","sequence":"first","affiliation":[{"name":"Computer and Information Sciences, University of Strathclyde, Glasgow, UK"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-4140-1209","authenticated-orcid":false,"given":"S. Josephine","family":"Pravinkumar","sequence":"additional","affiliation":[{"name":"NHS Lanarkshire, Bothwell, South Lanarkshire, UK"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-7935-3447","authenticated-orcid":false,"given":"Roma","family":"Maguire","sequence":"additional","affiliation":[{"name":"Computer and Information Sciences, University of Strathclyde, Glasgow, UK"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0009-0000-4639-7486","authenticated-orcid":false,"given":"Ashleigh","family":"Main","sequence":"additional","affiliation":[{"name":"Computer and Information Sciences, University of Strathclyde, Glasgow, UK"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0009-0006-1740-3078","authenticated-orcid":false,"given":"Haruno","family":"McCartney","sequence":"additional","affiliation":[{"name":"Computer and Information Sciences, University of Strathclyde, Glasgow, UK"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0009-0003-6032-1412","authenticated-orcid":false,"given":"Lewis","family":"Winters","sequence":"additional","affiliation":[{"name":"Computer and Information Sciences, University of Strathclyde, Glasgow, UK"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-4122-8012","authenticated-orcid":false,"given":"Feng","family":"Dong","sequence":"additional","affiliation":[{"name":"Computer and Information Sciences, University of Strathclyde, Glasgow, UK"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"179","published-online":{"date-parts":[[2025,3,2]]},"reference":[{"key":"bibr1-20552076251315293","unstructured":"The Royal College of Emergency Medicine. Best Practice Guidelines: Frequent Attenders in the Emergency Department. 2017."},{"key":"bibr2-20552076251315293","doi-asserted-by":"publisher","DOI":"10.1067\/mem.2001.111762"},{"key":"bibr3-20552076251315293","doi-asserted-by":"publisher","DOI":"10.1161\/CIRCULATIONAHA.115.001593"},{"key":"bibr4-20552076251315293","doi-asserted-by":"crossref","first-page":"1033","DOI":"10.1001\/jama.2020.14136","volume":"324","author":"Krittanawong C","year":"2020","journal-title":"J Am Med Assoc"},{"key":"bibr5-20552076251315293","first-page":"116","volume":"572","author":"Rajkomar A","year":"2018","journal-title":"Nature"},{"key":"bibr6-20552076251315293","doi-asserted-by":"publisher","DOI":"10.1136\/emj.2009.079160"},{"key":"bibr7-20552076251315293","doi-asserted-by":"publisher","DOI":"10.3109\/02813432.2014.982368"},{"key":"bibr8-20552076251315293","doi-asserted-by":"publisher","DOI":"10.1136\/emermed-2020-210412"},{"key":"bibr9-20552076251315293","doi-asserted-by":"publisher","DOI":"10.1371\/journal.pone.0229022"},{"key":"bibr10-20552076251315293","doi-asserted-by":"publisher","DOI":"10.1212\/WNL.0000000000001944"},{"key":"bibr11-20552076251315293","doi-asserted-by":"publisher","DOI":"10.1007\/s00521-023-08957-4"},{"key":"bibr12-20552076251315293","doi-asserted-by":"publisher","DOI":"10.1515\/9781400881970-018"},{"key":"bibr13-20552076251315293","doi-asserted-by":"crossref","unstructured":"Pereira M, Singh V, Hon CP, et al. Predicting future frequent users of emergency departments in California state. In: Proceedings of the 7th ACM international conference on bioinformatics, computational biology, and health informatics, 2016, pp. 603\u2013610.","DOI":"10.1145\/2975167.2985845"},{"key":"bibr14-20552076251315293","doi-asserted-by":"publisher","DOI":"10.1038\/s41598-021-00937-9"},{"key":"bibr15-20552076251315293","doi-asserted-by":"publisher","DOI":"10.1016\/j.health.2022.100050"},{"key":"bibr16-20552076251315293","doi-asserted-by":"publisher","DOI":"10.1016\/j.ienj.2021.100984"},{"key":"bibr17-20552076251315293","doi-asserted-by":"publisher","DOI":"10.3109\/13814780309160402"},{"key":"bibr18-20552076251315293","doi-asserted-by":"publisher","DOI":"10.1093\/abm\/kax054"},{"key":"bibr19-20552076251315293","doi-asserted-by":"publisher","DOI":"10.1136\/bmjspcare-2021-003448"},{"key":"bibr20-20552076251315293","doi-asserted-by":"publisher","DOI":"10.7861\/clinmedicine.16-4-325"},{"key":"bibr21-20552076251315293","unstructured":"Public Health Scotland. Scottish Patients at Risk of Readmission and Admission (SPARRA). 2012."},{"key":"bibr22-20552076251315293","unstructured":"Scottish Government. Scottish Index of Multiple Deprivation 2020. 2020."},{"key":"bibr23-20552076251315293","unstructured":"East London NHS Foundation Trust. Newham High Intensity User (HIU) Service Operational Policy. 2022, https:\/\/www.elft.nhs.uk\/sites\/default\/files\/2023-08\/foi_da4849_-_appendix_2.pdf."},{"key":"bibr24-20552076251315293","first-page":"2579","volume":"9","author":"Van der Maaten L","year":"2008","journal-title":"J Mach Learn Res"},{"key":"bibr25-20552076251315293","doi-asserted-by":"publisher","DOI":"10.1002\/9781118548387"},{"key":"bibr26-20552076251315293","first-page":"2825","volume":"12","author":"Pedregosa F","year":"2011","journal-title":"the Journal of Machine Learning Research"},{"key":"bibr27-20552076251315293","doi-asserted-by":"publisher","DOI":"10.1007\/BF01589116"},{"key":"bibr28-20552076251315293","doi-asserted-by":"publisher","DOI":"10.1007\/978-0-387-84858-7"},{"key":"bibr29-20552076251315293","volume-title":"Deep learning","author":"Goodfellow I","year":"2016"},{"key":"bibr30-20552076251315293","doi-asserted-by":"crossref","unstructured":"Lin T-Y, Goyal P, Girshick R, et al. Focal loss for dense object detection. In: Proceedings of the IEEE international conference on computer vision, 2017, pp. 2980\u20132988.","DOI":"10.1109\/ICCV.2017.324"},{"key":"bibr31-20552076251315293","unstructured":"National Health Service Health and Research Authority. Wales REC 4. Available at: https:\/\/www.hra.nhs.uk\/about-us\/committees-and-services\/res-and-recs\/search-research-ethics-committees\/wales-rec-4\/."},{"key":"bibr32-20552076251315293","first-page":"25","volume":"54","author":"Cunningham P","year":"2021","journal-title":"ACM Comput. Surv"},{"key":"bibr33-20552076251315293","unstructured":"Kittipong C, Chujai P, Teerarassammee P, et al. An empirical study of distance metrics for k-nearest neighbor algorithm. In:\n                      Proceedings of the 3rd international conference on industrial application engineering\n                      , 28 March 2015 (Vol. 2, p. 4)."},{"key":"bibr34-20552076251315293","doi-asserted-by":"publisher","DOI":"10.3390\/fi13080193"},{"key":"bibr35-20552076251315293","doi-asserted-by":"publisher","DOI":"10.24963\/ijcai.2022\/778"},{"key":"bibr36-20552076251315293","unstructured":"NHS England A&E attendances for mental health concerns and A&E attendances where length of stay is greater than 12 hours, 2021. https:\/\/digital.nhs.uk\/supplementary-information\/2021\/ae-attendances-for-mental-health-concerns."},{"key":"bibr37-20552076251315293","doi-asserted-by":"publisher","DOI":"10.1590\/0104-1169.0072.2560"},{"key":"bibr38-20552076251315293","doi-asserted-by":"publisher","DOI":"10.1186\/s12913-020-05774-6"},{"key":"bibr39-20552076251315293","doi-asserted-by":"publisher","DOI":"10.1097\/MEJ.0000000000000349"},{"key":"bibr40-20552076251315293","doi-asserted-by":"publisher","DOI":"10.1111\/1742-6723.14011"},{"key":"bibr41-20552076251315293","doi-asserted-by":"publisher","DOI":"10.1016\/j.ienj.2017.06.001"},{"key":"bibr42-20552076251315293","doi-asserted-by":"publisher","DOI":"10.1186\/s12873-023-00808-8"},{"key":"bibr43-20552076251315293","doi-asserted-by":"publisher","DOI":"10.1177\/2049463717720635"},{"key":"bibr44-20552076251315293","doi-asserted-by":"publisher","DOI":"10.1016\/j.jemermed.2014.03.014"},{"key":"bibr45-20552076251315293","doi-asserted-by":"publisher","DOI":"10.1111\/ggi.13875"},{"key":"bibr46-20552076251315293","doi-asserted-by":"publisher","DOI":"10.1016\/j.annemergmed.2016.01.033"},{"key":"bibr47-20552076251315293","doi-asserted-by":"publisher","DOI":"10.1136\/emermed-2020-210772"},{"key":"bibr48-20552076251315293","doi-asserted-by":"publisher","DOI":"10.17294\/2330-0698.1747"},{"key":"bibr49-20552076251315293","doi-asserted-by":"publisher","DOI":"10.1067\/mem.2003.68"},{"key":"bibr50-20552076251315293","doi-asserted-by":"publisher","DOI":"10.5694\/j.1326-5377.2008.tb02177.x"},{"key":"bibr51-20552076251315293","doi-asserted-by":"publisher","DOI":"10.1016\/j.jemermed.2020.03.012"},{"key":"bibr52-20552076251315293","doi-asserted-by":"publisher","DOI":"10.1016\/j.genhosppsych.2014.09.010"},{"key":"bibr53-20552076251315293","volume":"60","author":"Palmer E","year":"2014","journal-title":"Can Fam Physician"},{"key":"bibr54-20552076251315293","doi-asserted-by":"publisher","DOI":"10.1177\/2010105817715271"},{"key":"bibr55-20552076251315293","doi-asserted-by":"publisher","DOI":"10.1016\/j.annemergmed.2018.12.013"},{"key":"bibr56-20552076251315293","doi-asserted-by":"publisher","DOI":"10.1136\/emj.2008.059428"},{"key":"bibr57-20552076251315293","doi-asserted-by":"publisher","DOI":"10.3399\/bjgpopen20X101076"},{"key":"bibr58-20552076251315293","doi-asserted-by":"publisher","DOI":"10.1136\/archdischild-2016-311952"},{"key":"bibr59-20552076251315293","doi-asserted-by":"publisher","DOI":"10.47102\/annals-acadmedsg.2021483"},{"key":"bibr60-20552076251315293","doi-asserted-by":"publisher","DOI":"10.3390\/ijerph18126351"},{"key":"bibr61-20552076251315293","doi-asserted-by":"publisher","DOI":"10.1192\/bjb.2019.8"},{"key":"bibr62-20552076251315293","doi-asserted-by":"publisher","DOI":"10.1016\/j.ijnurstu.2013.11.002"}],"container-title":["DIGITAL HEALTH"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/journals.sagepub.com\/doi\/pdf\/10.1177\/20552076251315293","content-type":"application\/pdf","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/journals.sagepub.com\/doi\/full-xml\/10.1177\/20552076251315293","content-type":"application\/xml","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/journals.sagepub.com\/doi\/pdf\/10.1177\/20552076251315293","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,4,28]],"date-time":"2026-04-28T17:51:02Z","timestamp":1777398662000},"score":1,"resource":{"primary":{"URL":"https:\/\/journals.sagepub.com\/doi\/10.1177\/20552076251315293"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,1]]},"references-count":62,"alternative-id":["10.1177\/20552076251315293"],"URL":"https:\/\/doi.org\/10.1177\/20552076251315293","relation":{},"ISSN":["2055-2076","2055-2076"],"issn-type":[{"value":"2055-2076","type":"print"},{"value":"2055-2076","type":"electronic"}],"subject":[],"published":{"date-parts":[[2025,1]]},"article-number":"20552076251315293"}}