Academic Journal
Stroke detection in medical emergency calls: a retrospective analysis and exploratory evaluation of an AI decision support model.
| Τίτλος: | Stroke detection in medical emergency calls: a retrospective analysis and exploratory evaluation of an AI decision support model. |
|---|---|
| Συγγραφείς: | Iversen E; Norwegian National Advisory Unit on Emergency Medical Communication, Haukeland University Hospital, Bergen, Norway. emil.iversen@helse-bergen.no.; Oslo Emergency Medical Communication Centre, Pre-hospital Clinic, Oslo University Hospital, Oslo, Norway. emil.iversen@helse-bergen.no.; Department of Clinical Medicine, University of Bergen, Bergen, Norway. emil.iversen@helse-bergen.no.; Department of Nursing and Health Promotion, Faculty of Health Sciences, Oslo Metropolitan University, Oslo, Norway. emil.iversen@helse-bergen.no., Ihle-Hansen H; Department of Medicine, Vestre Viken Hospital Trust, Drammen, Norway., Halle KK; Department of Medical Quality Registries, St Olavs Hospital, Trondheim University Hospital, Trondheim, Norway., Lundervold AS; Department of Strategy and Management, NHH Norwegian School of Economics, Bergen, Norway.; Department of Radiology, Haukeland University Hospital, Bergen, Norway., Myrmel L; Department of Anaesthesia & Intensive Care, Haukeland University Hospital, Bergen, Norway., Vestbø AS; Department of Research and Development, Haukeland University Hospital, Bergen, Norway., Fromm A; Department of Neurology, Haukeland University Hospital, Bergen, Norway., Persia CD; Team Artificial Intelligence, Helse Vest ICT, Bergen, Norway., Autenried C; Team Artificial Intelligence, Helse Vest ICT, Bergen, Norway., Brattebø G; Norwegian National Advisory Unit on Emergency Medical Communication, Haukeland University Hospital, Bergen, Norway.; Department of Anaesthesia & Intensive Care, Haukeland University Hospital, Bergen, Norway.; Department of Clinical Medicine, University of Bergen, Bergen, Norway. |
| Πηγή: | Scandinavian journal of trauma, resuscitation and emergency medicine [Scand J Trauma Resusc Emerg Med] 2026 Jun 09; Vol. 34 (1). Date of Electronic Publication: 2026 Jun 09. |
| Τύπος έκδοσης: | Journal Article |
| Γλώσσα: | English |
| Στοιχεία περιοδικού: | Publisher: BioMed Central Country of Publication: England NLM ID: 101477511 Publication Model: Electronic Cited Medium: Internet ISSN: 1757-7241 (Electronic) Linking ISSN: 17577241 NLM ISO Abbreviation: Scand J Trauma Resusc Emerg Med Subsets: MEDLINE |
| Imprint Name(s): | Original Publication: London : BioMed Central |
| Ιατρικοί όροι (MeSH): | Stroke*/diagnosis , Emergency Medical Services*/methods , Artificial Intelligence* , Emergency Medical Service Communication Systems* , Decision Support Techniques*, Humans ; Retrospective Studies ; Female ; Male ; Aged |
| Περίληψη: | Background: Timely identification of acute stroke during medical emergency calls is critical for optimizing patient outcomes. We aimed to (i) characterize the prehospital trajectories of patients with stroke and (ii) explore the ability of an artificial intelligence (AI) model developed within the Artificial Intelligence Support in Medical Emergency Calls project to support decision-making at Emergency Medical Communication Centres (EMCCs). Methods: We conducted a retrospective analysis using data from 1,164 patients diagnosed with stroke from an EMCC (2018-2019), focusing on those primarily assessed by EMCC operators. We categorized patients into optimal and nonoptimal trajectory groups and applied logistic regression to explore the factors associated with an optimal trajectory. An AI model was trained using a dataset of 2,980 emergency calls (2019 and 2022), integrating transcribed audio logs and structured clinical data. The model was evaluated on the full dataset and subgroups that were incorrectly assessed by the EMCC. Results: Aphasia/dysarthria was the only factor associated with optimal trajectories. The AI model achieved a sensitivity of 81.0%, specificity of 79.6%, and F1-score of 64.7%. The subgroup analysis included 14 false-negative and 41 false-positive cases. The model correctly predicted stroke in 9 of 14 false-negative cases and ruled out stroke in 9 of 41 false-positive cases. Conclusions: This explorative evaluation indicates that a multimodal AI pipeline combining audio and structured clinical data may show potential to support decision making in medical emergency calls. Internal results are promising, but studies on larger and external datasets are needed to validate these findings. (© 2026. The Author(s).) |
| Competing Interests: | Declarations. Ethics approval and consent to participate: The study was approved by the Regional Committee for Medical Research Ethics, Western Norway, on March 22, 2024 (REK West No. 2020–108573). The committee granted a waiver of confidentiality obligations, but an information letter was sent to all identified individuals, providing details about the study and offering the opportunity to withdraw at any time. Consent for publication: Not applicable. Competing interests: The authors declare no competing interests. |
| References: | Scand J Trauma Resusc Emerg Med. 2022 May 12;30(1):36. (PMID: 35549978) Int J Stroke. 2019 Jun;14(4):409-416. (PMID: 30758276) JAMA Netw Open. 2021 Jan 4;4(1):e2032320. (PMID: 33404620) J Stroke Cerebrovasc Dis. 2013 Nov;22(8):e610-4. (PMID: 24075587) NPJ Digit Med. 2023 Dec 19;6(1):235. (PMID: 38114611) Circ Cardiovasc Qual Outcomes. 2013 May 1;6(3):262-9. (PMID: 23633218) BMJ. 2007 Oct 20;335(7624):806-8. (PMID: 17947786) BMC Emerg Med. 2024 Nov 15;24(1):214. (PMID: 39548378) BMC Emerg Med. 2024 Mar 14;24(1):43. (PMID: 38486156) Neurology. 2017 May 30;88(22):2123-2127. (PMID: 28455382) Acta Anaesthesiol Scand. 2018 Jan;62(1):105-115. (PMID: 29105736) BMJ. 2025 Feb 5;388:e081554. (PMID: 39909534) Eur Stroke J. 2024 Jun;9(2):283-294. (PMID: 38174575) Stroke. 1989 Jul;20(7):864-70. (PMID: 2749846) Arch Neurol. 2004 Jul;61(7):1066-70. (PMID: 15262737) Int J Stroke. 2020 Jul;15(5):555-564. (PMID: 32223543) Emerg Med J. 2013 Aug;30(8):669-74. (PMID: 22886891) Clin Neurol Neurosurg. 2022 Jul;218:107297. (PMID: 35636379) Ann Emerg Med. 2025 Nov;86(5):533-540. (PMID: 40448981) BMC Emerg Med. 2016 Jan 09;16:3. (PMID: 26748628) Lancet. 2016 Apr 23;387(10029):1723-31. (PMID: 26898852) Scand J Trauma Resusc Emerg Med. 2025 May 21;33(1):94. (PMID: 40399996) J Am Coll Emerg Physicians Open. 2022 Jul 01;3(4):e12750. (PMID: 35795711) Stroke. 2012 Oct;43(10):2666-70. (PMID: 22879096) Stroke. 2019 Dec;50(12):e344-e418. (PMID: 31662037) BMJ Qual Saf. 2025 Jun 19;34(7):421-424. (PMID: 40246317) Tidsskr Nor Laegeforen. 2017 Jun 06;137(11):798-802. (PMID: 28597634) |
| Contributed Indexing: | Keywords: Artificial intelligence; Decision support; Emergency medical communication centre; Emergency medical dispatch; Emergency medical services; Medical emergency calls; Stroke |
| Entry Date(s): | Date Created: 20260609 Date Completed: 20260819 Latest Revision: 20260821 |
| Update Code: | 20260821 |
| PubMed Central ID: | PMC13487976 |
| DOI: | 10.1186/s13049-026-01645-x |
| PMID: | 42260600 |
| Βάση Δεδομένων: | MEDLINE |
καταχωρήστε σχόλιο πρώτοι!