Smartphone AI Assistance for Prehospital ECG Interpretation

NCT07810686 | Recruiting

• 2 other identifiers: ECG-IA-20262026-01430
• Study Type: interventional
• Target: 144
• Locations: 1 country
• Sites: 1

Brief Summary

Prehospital providers interpret 12-lead electrocardiograms (ECGs) under time pressure and without immediate expert support. Missed acute coronary occlusion - occlusion myocardial infarction (OMI) - delays reperfusion, while false positive interpretations trigger unnecessary catheterization laboratory activations. Multimodal large language models (LLMs) available on any smartphone can now analyze a photographed ECG, and prehospital providers have begun using them spontaneously. No randomized trial has evaluated whether this practice improves diagnostic performance. This randomized controlled trial compares the diagnostic performance of prehospital providers interpreting ECG clinical vignettes with and without mandatory assistance from a single, version-locked smartphone large language model. Participants - paramedics, emergency medical technicians, nurses and physicians practicing in prehospital care in French-speaking Switzerland - are randomized 1:1 on a dedicated digital platform and answer 14 clinical vignettes presented in individually randomized order. Each vignette is built around a real, anonymized 12-lead ECG obtained during routine clinical care. The primary outcome is the proportion of vignettes for which the participant correctly identifies the presence or absence of an OMI. Secondary outcomes are sensitivity, specificity, and the accuracy of the prehospital priority decision level.

Conditions

Acute Coronary Syndromes; ST Elevation Myocardial Infarction; Non-ST Elevated Myocardial Infarction; Myocardial Infarction (MI); Diagnostic Errors

Keywords

artificial intelligence; large language model; GPT-4o; electrocardiography; occlusion myocardial infarction; OMI; prehospital care; paramedics; emergency medical services; clinical decision support; diagnostic accuracy; clinical vignettes; Switzerland; French-speaking Switzerland; prehospital providers

Outcome Measures

Primary Outcomes (1)

• Proportion of vignettes with correct identification of occlusion myocardial infarction (OMI) status

  For each of the 14 vignettes, the participant answers a binary question: "At this stage of care, is an OMI (acute coronary occlusion) likely? Yes / No". Responses are scored against a reference standard defined a priori, vignette by vignette, by the study cardiologist and locked before data collection. This reference standard is the answer expected of a prehospital provider at the point of care, anchored on coronary angiography wherever angiography is discriminant. For non-ischaemic mimics the expected answer depends on whether the acute presentation allows the condition to be distinguished from a coronary occlusion: it does not for the Takotsubo case (expected answer "yes"), whereas acute pericarditis is usually recognisable (expected answer "no"). This pre-specified departure from a purely angiographic standard is reported as such, and the analysis is repeated in a sensitivity analysis classifying all mimics as non-OMI. The outcome is the proportion of correctly classified vignettes

  Single study session, approximately 90 minutes; 14 vignettes per participant

Secondary Outcomes (3)

• Sensitivity of OMI detection

  Single study session, approximately 90 minutes

• Specificity of OMI detection

  Single study session, approximately 90 minutes

• Accuracy of the prehospital priority decision level

  Single study session, approximately 90 minutes

Other Outcomes (5)

• Diagnostic accuracy on the closed-list diagnosis question

  Single study session, approximately 90 minutes

• Self-reported confidence and calibration

  Single study session, approximately 90 minutes

• Self-reported influence of the AI on the final answer

  Single study session, approximately 90 minutes

Study Arms (2)

Control: unaided ECG interpretation

NO INTERVENTION

Participants interpret each of the 14 ECG vignettes without any assistance. Smartphones are turned face down and out of reach for the duration of the session. No intervention is administered.

AI-assisted ECG interpretation

EXPERIMENTAL

Participants must consult the study-imposed large language model for every vignette before submitting their answer. The platform locks the submit button until use of the tool is confirmed. Participants remain free not to follow the interpretation produced by the model and may base their final answer on their own clinical reasoning.

Diagnostic Test: Smartphone large language model assistance (GPT-4o, version-locked)

Interventions

Smartphone large language model assistance (GPT-4o, version-locked) DIAGNOSTIC_TEST

The platform transmits the ECG image to a single large language model (OpenAI GPT-4o, API snapshot gpt-4o-2024-08-06), locked for the entire study, together with a standardised prompt identical for all participants and all vignettes: "I am on an urgent prehospital call with a patient who presents this ECG. Analyse it and tell me what you think." Participants cannot modify the prompt, ask follow-up questions or provide additional clinical context. The model version and system fingerprint returned by the API are recorded for every call. The model's interpretation is displayed within the vignette. Use of the tool is mandatory; adherence to its interpretation is not.

Also known as: ChatGPT, gpt-4o-2024-08-06

AI-assisted ECG interpretation

Eligibility Criteria

• Age: 18 Years+
• Sex: all
• Healthy Volunteers: Yes
• Age Groups: Adult (18-64), Older Adult (65+)

You may qualify if:

• Prehospital care provider practising in French-speaking Switzerland
• Any level of training: emergency medical technician, paramedic (ES), nurse (ES/HES) in prehospital emergency care, or prehospital emergency physician
• Electronic informed consent signed before randomization

You may not qualify if:

• Cardiologist
• Any person not practising in prehospital care
• Insufficient command of written French to answer the vignettes reliably
• Refusal to participate or withdrawal of consent

Sponsors & Collaborators

• École Supérieure de Soins Ambulanciers - College of Higher Education in Prehospital Care: lead
• University Hospital, Geneva: collaborator
• Swissrescue.ch, Website for Prehospital Healthcare Providers, Les Pontins, Switzerland: collaborator

Study Sites (1)

Caserne des pompiers de Morat (Swiss French-speaking prehospital clinical research conference)

Murten/Morat, Canton of Fribourg, 3280, Switzerland

RECRUITING

MeSH Terms

Conditions

Acute Coronary Syndrome; ST Elevation Myocardial Infarction; Non-ST Elevated Myocardial Infarction; Myocardial Infarction

Condition Hierarchy (Ancestors)

Myocardial Ischemia; Heart Diseases; Cardiovascular Diseases; Vascular Diseases; Infarction; Ischemia; Pathologic Processes; Pathological Conditions, Signs and Symptoms; Necrosis

Central Study Contacts

Laurent Bourgeois

CONTACT

+41 22 388 34 04; laurent.bourgeois@edu.ge.ch

Study Design

• Study Type: interventional
• Phase: not applicable
• Allocation: RANDOMIZED
• Masking: SINGLE
• Who Masked: OUTCOMES ASSESSOR
• Masking Details: Participants and investigators cannot be masked to allocation, since participants in the intervention arm knowingly use the AI tool. The statistician conducting the primary analysis is masked: groups are coded "Group 1" and "Group 2", and the allocation key is held solely by the principal investigator and released only after database lock and approval of the statistical analysis plan.
• Purpose: DIAGNOSTIC
• Intervention Model: PARALLEL
• Sponsor Type: OTHER
• Responsible Party: PRINCIPAL INVESTIGATOR
• PI Title: Maître-adjoint (Lecturer and Deputy Head of School), Principal Investigator

Model Details: Two parallel groups of prehospital providers, randomized 1:1 at the individual level. Each participant completes a single session comprising 14 ECG clinical vignettes presented in an individually randomized order. The control group interprets the ECGs unaided; the intervention group must consult a study-imposed smartphone large language model for every vignette before submitting an answer.

Study Record Dates

• First Submitted: August 27, 2026
• First Posted: September 9, 2026
• Study Start: September 2, 2026
• Primary Completion (Estimated): November 30, 2026
• Study Completion (Estimated): November 30, 2026
• Last Updated: September 9, 2026

Record last verified: 2026-09

Data Sharing

• IPD Sharing: Will share
• Shared Documents: STUDY PROTOCOL, SAP, ICF, ANALYTIC CODE
• Time Frame: From the date of publication, with no end date.
• Access Criteria: Open access, no restriction, no request procedure.

Locations

CH (1)