{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,9,28]],"date-time":"2026-09-28T17:56:14Z","timestamp":1790618174026,"version":"4.1.0"},"reference-count":28,"publisher":"BMJ","issue":"9","license":[{"start":{"date-parts":[[2026,9,27]],"date-time":"2026-09-27T00:00:00Z","timestamp":1790467200000},"content-version":"unspecified","delay-in-days":26,"URL":"https:\/\/creativecommons.org\/licenses\/by-nc\/4.0\/"}],"funder":[{"name":"Andalusian Regional Ministry of Health and Consumer Affairs","award":["PI-0179-2024"],"award-info":[{"award-number":["PI-0179-2024"]}]}],"content-domain":{"domain":["bmj.com"],"crossmark-restriction":true},"short-container-title":["BMJ Open"],"accepted":{"date-parts":[[2026,8,4]]},"published-print":{"date-parts":[[2026,9]]},"abstract":"<jats:sec>\n                    <jats:title>Introduction<\/jats:title>\n                    <jats:p>Emergency telephone triage must rapidly recognise cardiac arrest, severe respiratory distress, chest pain and stroke, yet current systems struggle to balance under- and over-triage. trIAje will evaluate present performance and develop an artificial intelligence (AI) model to improve triage in an emergency medical system (EMS).<\/jats:p>\n                  <\/jats:sec>\n                  <jats:sec>\n                    <jats:title>Methods and analysis<\/jats:title>\n                    <jats:p>A retrospective cohort will include all 2020\u20132024 calls initially coded as unconsciousness, cardiac arrest, respiratory difficulty, non-traumatic chest pain or suspected stroke. Dispatch records, mobile electronic health records and the population health registry will be linked and anonymised. Structured variables and dispatcher free text will be pre-processed; natural language processing (NLP) methods will convert text into numeric representations for modelling. Supervised machine-learning algorithms (logistic regression, tree-based ensembles, gradient boosting, support-vector machines and neural networks) will be trained with k-fold cross-validation and evaluated on a held-out test set. The reference standard is final clinical severity (field or hospital diagnosis and\/or intensive care unit (ICU) admission). Performance metrics include sensitivity, specificity, predictive values, under- and over-triage rates and area under the receiver operating characteristic (ROC) curve. Feature-importance and SHAP (Shapley Additive Explanations) analyses will identify the most informative questions and caller expressions. Sex-stratified evaluation will detect disparities; sex-specific adjustments will be applied if needed.<\/jats:p>\n                  <\/jats:sec>\n                  <jats:sec>\n                    <jats:title>Ethics and dissemination<\/jats:title>\n                    <jats:p>The Andalusian Biomedical Research Ethics Committee has approved the study (SICEIA-2025-001391); data are anonymised under Spanish Law 14\/2007 and the General Data Protection Regulation (GDPR), so consent is waived. Findings will be published in peer-reviewed journals, presented at emergency-medicine and informatics conferences and shared with emergency services. A prototype decision-support tool and training package will be developed. A blind pilot in shadow mode\u2014planned as the next independent phase of this research programme, contingent on model performance thresholds and subject to dedicated ethics committee approval and prospective registration\u2014will subsequently evaluate the prototype on real-time calls without displaying recommendations to dispatchers or affecting clinical decision-making, allowing diagnostic accuracy to be measured objectively and operational fit to be assessed before any real-world implementation. The protocol is reported according to the STROBE statement and its RECORD extension.<\/jats:p>\n                  <\/jats:sec>\n                  <jats:sec>\n                    <jats:title>Trial registration number<\/jats:title>\n                    <jats:p>\n                      <jats:ext-link xmlns:xlink=\"http:\/\/www.w3.org\/1999\/xlink\" ext-link-type=\"clintrialgov\" xlink:href=\"NCT07247669\">NCT07247669<\/jats:ext-link>\n                      .\n                    <\/jats:p>\n                  <\/jats:sec>","DOI":"10.1136\/bmjopen-2025-113242","type":"journal-article","created":{"date-parts":[[2026,9,28]],"date-time":"2026-09-28T17:00:32Z","timestamp":1790614832000},"page":"e113242","update-policy":"https:\/\/doi.org\/10.1136\/crossmarkpolicy","source":"Crossref","is-referenced-by-count":0,"title":["trIAje project: protocol for a retrospective cohort study to optimise AI-assisted telephone triage of time-sensitive conditions in emergency medical services"],"prefix":"10.1136","volume":"16","clinical-trial-number":[{"clinical-trial-number":"nct07247669","registry":"10.18810\/clinical-trials-gov"},{"clinical-trial-number":"nct07247669","registry":"10.18810\/clinical-trials-gov"},{"clinical-trial-number":"nct07247669","registry":"10.18810\/clinical-trials-gov"}],"author":[{"ORCID":"https:\/\/orcid.org\/0000-0003-0612-308X","authenticated-orcid":false,"given":"Mar\u00eda Jos\u00e9","family":"Luque-Hern\u00e1ndez","sequence":"first","affiliation":[{"name":"Centro de Emergencias Sanitarias 061, M\u00e1laga, Spain"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-7551-8416","authenticated-orcid":false,"given":"Carlos","family":"Romero-Ol\u00f3riz","sequence":"additional","affiliation":[{"name":"Centro de Emergencias Sanitarias 061, M\u00e1laga, Spain"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-7292-9842","authenticated-orcid":false,"given":"\u00c1lvaro","family":"Ritor\u00e9-Hidalgo","sequence":"additional","affiliation":[{"name":"Centro de Emergencias Sanitarias 061, M\u00e1laga, Spain"},{"name":"Data Science Lab, Progress and Health Public Foundation (FPS), Regional Ministry of Health and Consumer Affairs, Seville, Spain"},{"name":"Instituto de Investigaci\u00f3n Biom\u00e9dica de M\u00e1laga y Plataforma en Nanomedicina (IBIMA Plataforma BIONAND), M\u00e1laga, Spain"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-0841-4382","authenticated-orcid":false,"given":"\u00c1ngel","family":"Serrano Alarc\u00f3n","sequence":"additional","affiliation":[{"name":"Centro de Emergencias Sanitarias 061, M\u00e1laga, Spain"},{"name":"Data Science Lab, Progress and Health Public Foundation (FPS), Regional Ministry of Health and Consumer Affairs, Seville, Spain"},{"name":"Instituto de Investigaci\u00f3n Biom\u00e9dica de M\u00e1laga y Plataforma en Nanomedicina (IBIMA Plataforma BIONAND), M\u00e1laga, Spain"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-8541-2965","authenticated-orcid":false,"given":"Cristina","family":"L\u00f3pez L\u00f3pez","sequence":"additional","affiliation":[{"name":"Centro de Emergencias Sanitarias 061, M\u00e1laga, Spain"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Auxiliadora","family":"Caballero-Garc\u00eda","sequence":"additional","affiliation":[{"name":"Centro de Emergencias Sanitarias 061, M\u00e1laga, Spain"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-7012-2973","authenticated-orcid":false,"given":"Miguel \u00c1ngel","family":"Armengol de La Hoz","sequence":"additional","affiliation":[{"name":"Data Science Lab, Progress and Health Public Foundation (FPS), Regional Ministry of Health and Consumer Affairs, Seville, Spain"}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"239","published-online":{"date-parts":[[2026,9,28]]},"reference":[{"key":"2026092810001504000_16.9.e113242.1","doi-asserted-by":"crossref","DOI":"10.1186\/s13049-020-0706-3","article-title":"Towards definitions of time-sensitive conditions in prehospital care","volume":"28","author":"Wibring","year":"2020","journal-title":"Scand J Trauma Resusc Emerg Med"},{"key":"2026092810001504000_16.9.e113242.2","doi-asserted-by":"crossref","DOI":"10.1186\/s13049-018-0528-8","article-title":"The accuracy of medical dispatch - a systematic review","volume":"26","author":"Bohm","year":"2018","journal-title":"Scand J Trauma Resusc Emerg Med"},{"key":"2026092810001504000_16.9.e113242.3","doi-asserted-by":"crossref","first-page":"73","DOI":"10.1007\/s00068-010-0022-0","article-title":"Prehospital triage, discrepancy in priority-setting between emergency medical dispatch centre and ambulance crews","volume":"37","author":"Khorram-Manesh","year":"2011","journal-title":"Eur J Trauma Emerg Surg"},{"key":"2026092810001504000_16.9.e113242.4","doi-asserted-by":"crossref","DOI":"10.1186\/s13049-017-0464-z","article-title":"A comparison of two emergency medical dispatch protocols with respect to accuracy","volume":"25","author":"Torl\u00e9n","year":"2017","journal-title":"Scand J Trauma Resusc Emerg Med"},{"key":"2026092810001504000_16.9.e113242.5","doi-asserted-by":"crossref","DOI":"10.1186\/s13049-016-0336-y","article-title":"Medical priority dispatch codes-comparison with National Early Warning Score","volume":"24","author":"Hoikka","year":"2016","journal-title":"Scand J Trauma Resusc Emerg Med"},{"key":"2026092810001504000_16.9.e113242.6","article-title":"PP13\u2005The NHS pathways (NHSP) medical call triage system and new \u2018nature of call\u2019 telephone screening tool, employed prior to NHSP, can accurately identify high acuity patients: analysis of sensitivity and specificity using routine ambulance service data","volume":"36","author":"Green","year":"2019","journal-title":"Emerg Med J"},{"key":"2026092810001504000_16.9.e113242.7","doi-asserted-by":"crossref","first-page":"716","DOI":"10.1111\/1742-6723.12656","article-title":"Association between ambulance dispatch priority and patient condition","volume":"28","author":"Ball","year":"2016","journal-title":"Emerg Med Australas"},{"key":"2026092810001504000_16.9.e113242.8","doi-asserted-by":"crossref","DOI":"10.3390\/ijerph17218254","article-title":"Symptom-Based Dispatching in an Emergency Medical Communication Centre: Sensitivity, Specificity, and the Area under the ROC Curve","volume":"17","author":"Larribau","year":"2020","journal-title":"Int J Environ Res Public Health"},{"key":"2026092810001504000_16.9.e113242.9","doi-asserted-by":"crossref","DOI":"10.1186\/s13049-017-0350-8","article-title":"Recognition of out-of-hospital cardiac arrest during emergency calls - a systematic review of observational studies","volume":"25","author":"Viereck","year":"2017","journal-title":"Scand J Trauma Resusc Emerg Med"},{"key":"2026092810001504000_16.9.e113242.10","doi-asserted-by":"crossref","DOI":"10.1016\/j.resplu.2021.100096","article-title":"Assessment of a quality improvement programme to improve telephone dispatchers\u2019 accuracy in identifying out-of-hospital cardiac arrest","volume":"6","author":"Gram","year":"2021","journal-title":"Resusc Plus"},{"key":"2026092810001504000_16.9.e113242.11","doi-asserted-by":"crossref","first-page":"476","DOI":"10.1016\/j.jen.2014.02.009","article-title":"Analysis of emergency medical services triage and dispatch errors by registered nurses in Italy","volume":"40","author":"Palma","year":"2014","journal-title":"J Emerg Nurs"},{"key":"2026092810001504000_16.9.e113242.12","doi-asserted-by":"crossref","DOI":"10.1161\/JAHA.113.000586","article-title":"Sensitivity, specificity, and sex differences in symptoms reported on the 13-item acute coronary syndrome checklist","volume":"3","author":"Devon","year":"2014","journal-title":"J Am Heart Assoc"},{"key":"2026092810001504000_16.9.e113242.13","doi-asserted-by":"crossref","DOI":"10.1186\/s13049-019-0670-y","article-title":"Predicting acute coronary syndrome in males and females with chest pain who call an emergency medical communication centre","volume":"27","author":"Reuter","year":"2019","journal-title":"Scand J Trauma Resusc Emerg Med"},{"key":"2026092810001504000_16.9.e113242.14","doi-asserted-by":"crossref","DOI":"10.2196\/56729","article-title":"Improving Triage Accuracy in Prehospital Emergency Telemedicine: Scoping Review of Machine Learning-Enhanced Approaches","volume":"13","author":"Raff","year":"2024","journal-title":"Interact J Med Res"},{"key":"2026092810001504000_16.9.e113242.15","doi-asserted-by":"crossref","DOI":"10.3389\/fpubh.2025.1604231","article-title":"Utilising artificial intelligence in prehospital emergency care systems in low- and middle-income countries: a scoping review","volume":"13","author":"Mallon","year":"2025","journal-title":"Front Public Health"},{"key":"2026092810001504000_16.9.e113242.16","doi-asserted-by":"crossref","DOI":"10.1016\/j.resplu.2023.100491","article-title":"Artificial intelligence to support out-of-hospital cardiac arrest care: A scoping review","volume":"16","author":"Toy","year":"2023","journal-title":"Resusc Plus"},{"key":"2026092810001504000_16.9.e113242.17","doi-asserted-by":"crossref","DOI":"10.34133\/hds.0008","article-title":"Building a Machine Learning-based Ambulance Dispatch Triage Model for Emergency Medical Services","volume":"3","author":"Wang","year":"2023","journal-title":"Health Data Sci"},{"key":"2026092810001504000_16.9.e113242.18","doi-asserted-by":"crossref","DOI":"10.1007\/s10916-021-01762-3","article-title":"Machine Learning in Medical Emergencies: a Systematic Review and Analysis","volume":"45","author":"Mendo","year":"2021","journal-title":"J Med Syst"},{"key":"2026092810001504000_16.9.e113242.19","doi-asserted-by":"crossref","first-page":"108548","DOI":"10.1016\/j.compbiomed.2024.108548","article-title":"Deep continual learning for medical call incidents text classification under the presence of dataset shifts","volume":"175","author":"Ferri","year":"2024","journal-title":"Comput Biol Med"},{"key":"2026092810001504000_16.9.e113242.20","doi-asserted-by":"publisher","DOI":"10.2471\/BLT.22.289310"},{"key":"2026092810001504000_16.9.e113242.21","doi-asserted-by":"crossref","unstructured":"Clark M , Severn M . Artificial Intelligence in Prehospital Emergency Health Care. Can J Health Technol 2023;3. doi:10.51731\/cjht.2023.712","DOI":"10.51731\/cjht.2023.712"},{"key":"2026092810001504000_16.9.e113242.22","doi-asserted-by":"crossref","DOI":"10.1371\/journal.pmed.0040297","article-title":"Strengthening the Reporting of Observational Studies in Epidemiology (STROBE): explanation and elaboration","volume":"4","author":"Vandenbroucke","year":"2007","journal-title":"PLoS Med"},{"key":"2026092810001504000_16.9.e113242.23","doi-asserted-by":"crossref","DOI":"10.1371\/journal.pmed.1001885","article-title":"The REporting of studies Conducted using Observational Routinely-collected health Data (RECORD) statement","volume":"12","author":"Benchimol","year":"2015","journal-title":"PLoS Med"},{"key":"2026092810001504000_16.9.e113242.24","doi-asserted-by":"crossref","DOI":"10.1136\/bmj-2023-078378","article-title":"TRIPOD+AI statement: updated guidance for reporting clinical prediction models that use regression or machine learning methods","volume":"385","author":"Collins","year":"2024","journal-title":"BMJ"},{"key":"2026092810001504000_16.9.e113242.25","doi-asserted-by":"crossref","DOI":"10.1136\/bmj.m441","article-title":"Calculating the sample size required for developing a clinical prediction model","volume":"368","author":"Riley","year":"2020","journal-title":"BMJ"},{"key":"2026092810001504000_16.9.e113242.26","doi-asserted-by":"crossref","DOI":"10.1186\/s12873-024-01152-1","article-title":"Using machine learning and natural language processing in triage for prediction of clinical disposition in the emergency department","volume":"24","author":"Chang","year":"2024","journal-title":"BMC Emerg Med"},{"key":"2026092810001504000_16.9.e113242.27","doi-asserted-by":"crossref","first-page":"1639","DOI":"10.1111\/jan.16528","article-title":"The Role of Language in Remote Healthcare Triage: A Meta-Aggregative Review","volume":"81","author":"Spek","year":"2025","journal-title":"J Adv Nurs"},{"key":"2026092810001504000_16.9.e113242.28","doi-asserted-by":"crossref","first-page":"31","DOI":"10.29045\/14784726.2022.09.7.2.31","article-title":"Using natural language processing in facilitating pre-hospital telephone triage of emergency calls","volume":"7","author":"Gormley","year":"2022","journal-title":"Br Paramed J"}],"container-title":["BMJ Open"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/syndication.highwire.org\/content\/doi\/10.1136\/bmjopen-2025-113242","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,9,28]],"date-time":"2026-09-28T17:00:37Z","timestamp":1790614837000},"score":1,"resource":{"primary":{"URL":"https:\/\/bmjopen.bmj.com\/lookup\/doi\/10.1136\/bmjopen-2025-113242"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026,9]]},"references-count":28,"journal-issue":{"issue":"9","published-online":{"date-parts":[[2026,9,28]]},"published-print":{"date-parts":[[2026,9]]}},"alternative-id":["10.1136\/bmjopen-2025-113242"],"URL":"https:\/\/doi.org\/10.1136\/bmjopen-2025-113242","relation":{},"ISSN":["2044-6055","2044-6055"],"issn-type":[{"value":"2044-6055","type":"print"},{"value":"2044-6055","type":"electronic"}],"subject":[],"published":{"date-parts":[[2026,9]]}}}