Academic Journal
Προβολή σε EDS

Stroke detection in medical emergency calls: a retrospective analysis and exploratory evaluation of an AI decision support model.

Λεπτομέρειες βιβλιογραφικής εγγραφής
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
FullText Text:
  Availability: 0
CustomLinks:
  – Url: https://resolver.ebsco.com/c/fiv2js/result?sid=EBSCO:cmedm&genre=article&issn=17577241&ISBN=&volume=34&issue=1&date=20260609&spage=&pages=&title=Scandinavian journal of trauma, resuscitation and emergency medicine&atitle=Stroke%20detection%20in%20medical%20emergency%20calls%3A%20a%20retrospective%20analysis%20and%20exploratory%20evaluation%20of%20an%20AI%20decision%20support%20model.&aulast=Iversen%20E&id=DOI:10.1186/s13049-026-01645-x
    Name: Full Text Finder (for New FTF UI) (ns324271)
    Category: fullText
    Text: Full Text Finder
    MouseOverText: Full Text Finder
Header DbId: cmedm
DbLabel: MEDLINE
An: 42260600
AccessLevel: 3
PubType: Academic Journal
PubTypeId: academicJournal
PreciseRelevancyScore: 0
IllustrationInfo
Items – Name: Title
  Label: Title
  Group: Ti
  Data: Stroke detection in medical emergency calls: a retrospective analysis and exploratory evaluation of an AI decision support model.
– Name: Author
  Label: Authors
  Group: Au
  Data: <searchLink fieldCode="AU" term="%22Iversen+E%22">Iversen E</searchLink>; 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.<br /><searchLink fieldCode="AU" term="%22Ihle-Hansen+H%22">Ihle-Hansen H</searchLink>; Department of Medicine, Vestre Viken Hospital Trust, Drammen, Norway.<br /><searchLink fieldCode="AU" term="%22Halle+KK%22">Halle KK</searchLink>; Department of Medical Quality Registries, St Olavs Hospital, Trondheim University Hospital, Trondheim, Norway.<br /><searchLink fieldCode="AU" term="%22Lundervold+AS%22">Lundervold AS</searchLink>; Department of Strategy and Management, NHH Norwegian School of Economics, Bergen, Norway.; Department of Radiology, Haukeland University Hospital, Bergen, Norway.<br /><searchLink fieldCode="AU" term="%22Myrmel+L%22">Myrmel L</searchLink>; Department of Anaesthesia & Intensive Care, Haukeland University Hospital, Bergen, Norway.<br /><searchLink fieldCode="AU" term="%22Vestbø+AS%22">Vestbø AS</searchLink>; Department of Research and Development, Haukeland University Hospital, Bergen, Norway.<br /><searchLink fieldCode="AU" term="%22Fromm+A%22">Fromm A</searchLink>; Department of Neurology, Haukeland University Hospital, Bergen, Norway.<br /><searchLink fieldCode="AU" term="%22Persia+CD%22">Persia CD</searchLink>; Team Artificial Intelligence, Helse Vest ICT, Bergen, Norway.<br /><searchLink fieldCode="AU" term="%22Autenried+C%22">Autenried C</searchLink>; Team Artificial Intelligence, Helse Vest ICT, Bergen, Norway.<br /><searchLink fieldCode="AU" term="%22Brattebø+G%22">Brattebø G</searchLink>; 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.
– Name: TitleSource
  Label: Source
  Group: Src
  Data: <searchLink fieldCode="JN" term="%22101477511%22">Scandinavian journal of trauma, resuscitation and emergency medicine</searchLink> [Scand J Trauma Resusc Emerg Med] 2026 Jun 09; Vol. 34 (1). <i>Date of Electronic Publication: </i>2026 Jun 09.
– Name: TypePub
  Label: Publication Type
  Group: TypPub
  Data: Journal Article
– Name: Language
  Label: Language
  Group: Lang
  Data: English
– Name: TitleSource
  Label: Journal Info
  Group: Src
  Data: <i>Publisher: </i><searchLink fieldCode="PB" term="%22BioMed+Central%22">BioMed Central </searchLink><i>Country of Publication: </i>England <i>NLM ID: </i>101477511 <i>Publication Model: </i>Electronic <i>Cited Medium: </i>Internet <i>ISSN: </i>1757-7241 (Electronic) <i>Linking ISSN: </i><searchLink fieldCode="IS" term="%2217577241%22">17577241 </searchLink><i>NLM ISO Abbreviation: </i>Scand J Trauma Resusc Emerg Med <i>Subsets: </i>MEDLINE
– Name: PublisherInfo
  Label: Imprint Name(s)
  Group: PubInfo
  Data: <i>Original Publication</i>: London : BioMed Central
– Name: SubjectMESH
  Label: MeSH Terms
  Group: Su
  Data: <searchLink fieldCode="MM" term="%22Stroke%22">Stroke*</searchLink>/<searchLink fieldCode="MM" term="%22Stroke+diagnosis%22">diagnosis</searchLink> <br /><searchLink fieldCode="MM" term="%22Emergency+Medical+Services%22">Emergency Medical Services*</searchLink>/<searchLink fieldCode="MM" term="%22Emergency+Medical+Services+methods%22">methods</searchLink> <br /><searchLink fieldCode="MM" term="%22Artificial+Intelligence%22">Artificial Intelligence*</searchLink> <br /><searchLink fieldCode="MM" term="%22Emergency+Medical+Service+Communication+Systems%22">Emergency Medical Service Communication Systems*</searchLink> <br /><searchLink fieldCode="MM" term="%22Decision+Support+Techniques%22">Decision Support Techniques*</searchLink><br /><searchLink fieldCode="MH" term="%22Humans%22">Humans</searchLink> ; <searchLink fieldCode="MH" term="%22Retrospective+Studies%22">Retrospective Studies</searchLink> ; <searchLink fieldCode="MH" term="%22Female%22">Female</searchLink> ; <searchLink fieldCode="MH" term="%22Male%22">Male</searchLink> ; <searchLink fieldCode="MH" term="%22Aged%22">Aged</searchLink>
– Name: Abstract
  Label: Abstract
  Group: Ab
  Data: 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).<br />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.<br />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.<br />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.<br /> (© 2026. The Author(s).)
– Name: Abstract
  Label: Competing Interests
  Group: Ab
  Data: 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.
– Name: Ref
  Label: References
  Group: RefInfo
  Data: Scand J Trauma Resusc Emerg Med. 2022 May 12;30(1):36. (PMID: <searchLink fieldCode="PM" term="%2235549978%22">35549978)</searchLink><br />Int J Stroke. 2019 Jun;14(4):409-416. (PMID: <searchLink fieldCode="PM" term="%2230758276%22">30758276)</searchLink><br />JAMA Netw Open. 2021 Jan 4;4(1):e2032320. (PMID: <searchLink fieldCode="PM" term="%2233404620%22">33404620)</searchLink><br />J Stroke Cerebrovasc Dis. 2013 Nov;22(8):e610-4. (PMID: <searchLink fieldCode="PM" term="%2224075587%22">24075587)</searchLink><br />NPJ Digit Med. 2023 Dec 19;6(1):235. (PMID: <searchLink fieldCode="PM" term="%2238114611%22">38114611)</searchLink><br />Circ Cardiovasc Qual Outcomes. 2013 May 1;6(3):262-9. (PMID: <searchLink fieldCode="PM" term="%2223633218%22">23633218)</searchLink><br />BMJ. 2007 Oct 20;335(7624):806-8. (PMID: <searchLink fieldCode="PM" term="%2217947786%22">17947786)</searchLink><br />BMC Emerg Med. 2024 Nov 15;24(1):214. (PMID: <searchLink fieldCode="PM" term="%2239548378%22">39548378)</searchLink><br />BMC Emerg Med. 2024 Mar 14;24(1):43. (PMID: <searchLink fieldCode="PM" term="%2238486156%22">38486156)</searchLink><br />Neurology. 2017 May 30;88(22):2123-2127. (PMID: <searchLink fieldCode="PM" term="%2228455382%22">28455382)</searchLink><br />Acta Anaesthesiol Scand. 2018 Jan;62(1):105-115. (PMID: <searchLink fieldCode="PM" term="%2229105736%22">29105736)</searchLink><br />BMJ. 2025 Feb 5;388:e081554. (PMID: <searchLink fieldCode="PM" term="%2239909534%22">39909534)</searchLink><br />Eur Stroke J. 2024 Jun;9(2):283-294. (PMID: <searchLink fieldCode="PM" term="%2238174575%22">38174575)</searchLink><br />Stroke. 1989 Jul;20(7):864-70. (PMID: <searchLink fieldCode="PM" term="%222749846%22">2749846)</searchLink><br />Arch Neurol. 2004 Jul;61(7):1066-70. (PMID: <searchLink fieldCode="PM" term="%2215262737%22">15262737)</searchLink><br />Int J Stroke. 2020 Jul;15(5):555-564. (PMID: <searchLink fieldCode="PM" term="%2232223543%22">32223543)</searchLink><br />Emerg Med J. 2013 Aug;30(8):669-74. (PMID: <searchLink fieldCode="PM" term="%2222886891%22">22886891)</searchLink><br />Clin Neurol Neurosurg. 2022 Jul;218:107297. (PMID: <searchLink fieldCode="PM" term="%2235636379%22">35636379)</searchLink><br />Ann Emerg Med. 2025 Nov;86(5):533-540. (PMID: <searchLink fieldCode="PM" term="%2240448981%22">40448981)</searchLink><br />BMC Emerg Med. 2016 Jan 09;16:3. (PMID: <searchLink fieldCode="PM" term="%2226748628%22">26748628)</searchLink><br />Lancet. 2016 Apr 23;387(10029):1723-31. (PMID: <searchLink fieldCode="PM" term="%2226898852%22">26898852)</searchLink><br />Scand J Trauma Resusc Emerg Med. 2025 May 21;33(1):94. (PMID: <searchLink fieldCode="PM" term="%2240399996%22">40399996)</searchLink><br />J Am Coll Emerg Physicians Open. 2022 Jul 01;3(4):e12750. (PMID: <searchLink fieldCode="PM" term="%2235795711%22">35795711)</searchLink><br />Stroke. 2012 Oct;43(10):2666-70. (PMID: <searchLink fieldCode="PM" term="%2222879096%22">22879096)</searchLink><br />Stroke. 2019 Dec;50(12):e344-e418. (PMID: <searchLink fieldCode="PM" term="%2231662037%22">31662037)</searchLink><br />BMJ Qual Saf. 2025 Jun 19;34(7):421-424. (PMID: <searchLink fieldCode="PM" term="%2240246317%22">40246317)</searchLink><br />Tidsskr Nor Laegeforen. 2017 Jun 06;137(11):798-802. (PMID: <searchLink fieldCode="PM" term="%2228597634%22">28597634)</searchLink>
– Name: SubjectMinor
  Label: Contributed Indexing
  Group:
  Data: <i>Keywords: </i>Artificial intelligence; Decision support; Emergency medical communication centre; Emergency medical dispatch; Emergency medical services; Medical emergency calls; Stroke
– Name: DateEntry
  Label: Entry Date(s)
  Group: Date
  Data: <i>Date Created: </i>20260609 <i>Date Completed: </i>20260819 <i>Latest Revision: </i>20260821
– Name: DateUpdate
  Label: Update Code
  Group: Date
  Data: 20260821
– Name: PubmedCentralID
  Label: PubMed Central ID
  Group: ID
  Data: PMC13487976
– Name: DOI
  Label: DOI
  Group: ID
  Data: 10.1186/s13049-026-01645-x
– Name: AN
  Label: PMID
  Group: ID
  Data: 42260600
PLink https://search.ebscohost.com/login.aspx?direct=true&site=eds-live&db=cmedm&AN=42260600
RecordInfo BibRecord:
  BibEntity:
    Identifiers:
      – Type: doi
        Value: 10.1186/s13049-026-01645-x
    Languages:
      – Code: eng
        Text: English
    Subjects:
      – SubjectFull: Humans
        Type: general
      – SubjectFull: Retrospective Studies
        Type: general
      – SubjectFull: Female
        Type: general
      – SubjectFull: Male
        Type: general
      – SubjectFull: Aged
        Type: general
      – SubjectFull: Stroke diagnosis
        Type: general
      – SubjectFull: Emergency Medical Services methods
        Type: general
      – SubjectFull: Artificial Intelligence
        Type: general
      – SubjectFull: Emergency Medical Service Communication Systems
        Type: general
      – SubjectFull: Decision Support Techniques
        Type: general
    Titles:
      – TitleFull: Stroke detection in medical emergency calls: a retrospective analysis and exploratory evaluation of an AI decision support model.
        Type: main
  BibRelationships:
    HasContributorRelationships:
      – PersonEntity:
          Name:
            NameFull: Iversen E
      – PersonEntity:
          Name:
            NameFull: Ihle-Hansen H
      – PersonEntity:
          Name:
            NameFull: Halle KK
      – PersonEntity:
          Name:
            NameFull: Lundervold AS
      – PersonEntity:
          Name:
            NameFull: Myrmel L
      – PersonEntity:
          Name:
            NameFull: Vestbø AS
      – PersonEntity:
          Name:
            NameFull: Fromm A
      – PersonEntity:
          Name:
            NameFull: Persia CD
      – PersonEntity:
          Name:
            NameFull: Autenried C
      – PersonEntity:
          Name:
            NameFull: Brattebø G
    IsPartOfRelationships:
      – BibEntity:
          Dates:
            – D: 09
              M: 06
              Text: 2026 Jun 09
              Type: published
              Y: 2026
          Identifiers:
            – Type: issn-electronic
              Value: 1757-7241
          Numbering:
            – Type: volume
              Value: 34
            – Type: issue
              Value: 1
          Titles:
            – TitleFull: Scandinavian journal of trauma, resuscitation and emergency medicine
              Type: main
ResultId 1