Acute Cardiopulmonary Disease, Chest Pain, Dyspnea, Emergency Department Patients
Conditions
Keywords
Artificial intelligence, Large language model, Emergency department, Electrocardiography, Chest radiography, Multimodal AI, Clinical decision support, Randomized controlled trial
Brief summary
Prospective, multicenter, randomized, open-label, blinded-endpoint (PROBE-like) clinical trial evaluating whether physician-supervised Generative Pre-trained Transformer (GPT)-assisted multimodal diagnostic support improves diagnostic concordance in emergency department patients presenting with acute cardiopulmonary symptoms.
Interventions
DIAGNOSTIC_TESTGenerative Pre-trained Transformer (GPT)-assisted multimodal visual language model (VLM) diagnostic support
A Generative Pre-trained Transformer (GPT)-based multimodal visual language model integrates electrocardiograms, chest radiographs, structured clinical information, laboratory findings, vital signs, and relevant clinical history to generate diagnostic suggestions and differential diagnoses for physician-supervised clinical decision support.
DIAGNOSTIC_TESTConventional emergency department diagnostic evaluation
Routine emergency department diagnostic evaluation performed according to standard clinical practice without AI-assisted diagnostic support.
Sponsors
Ewha Womans University Mokdong Hospital
Ewha Womans University Seoul Hospital
Study design
Allocation
RANDOMIZED
Intervention model
PARALLEL
Primary purpose
DIAGNOSTIC
Masking
NONE
Masking description
Outcome assessor blinded
Intervention model description
Eligible participants presenting to the emergency department with acute cardiopulmonary symptoms are randomly assigned in a 1:1 ratio to either conventional physician-guided diagnostic evaluation or physician-supervised GPT-assisted multimodal diagnostic support. Randomization is performed immediately after completion of the initial clinical assessment and documentation of the physician's preliminary diagnosis.
Eligibility
Sex/Gender
ALL
Age
18 Years to No maximum
Healthy volunteers
No
Inclusion criteria
* Age ≥18 years * Presentation to a participating emergency department with acute cardiopulmonary symptoms, including chest pain, dyspnea, palpitations, syncope, dizziness, or fever accompanied by cardiopulmonary symptoms * Performance of both a standard 12-lead electrocardiogram and chest radiography during the initial emergency department evaluation * Availability of initial clinical assessment, vital signs, laboratory findings, and all mandatory clinical information required for the multimodal AI workflow * Expected emergency department observation or hospital admission for at least 24 hours * Ability and willingness to provide written informed consent
Exclusion criteria
* Inability or refusal to provide written informed consent * Requirement for immediate life-saving intervention that precludes completion of the study workflow * Death before completion of the initial emergency department diagnostic assessment * Electrocardiographic quality insufficient for reliable physician or Artificial intelligence (AI) interpretation * Chest radiographic quality insufficient for reliable physician or Artificial intelligence (AI) interpretation * Cardiac pacing rhythm * Missing mandatory clinical information required for the multimodal Artificial intelligence (AI) workflow * Previous enrollment in the ER-VISION-AI trial * Inability to establish a blinded adjudicated reference diagnosis
Design outcomes
Primary
| Measure | Time frame | Description |
|---|---|---|
| Diagnostic concordance between the final emergency department diagnosis and the blinded adjudicated reference diagnosis established at hospital discharge. | During the index hospitalization, up to hospital discharge (average 3 days) | Diagnostic concordance between the treating physician's final emergency department diagnosis and the blinded adjudicated reference diagnosis based on the prespecified principal diagnostic category. |
Secondary
| Measure | Time frame | Description |
|---|---|---|
| Diagnostic concordance after Generative Pre-trained Transformer (GPT)-assisted diagnostic support | During the index emergency department visit (average 6 hours) | Diagnostic concordance between the physician's final emergency department diagnosis after Generative Pre-trained Transformer (GPT)-assisted multimodal diagnostic support and the blinded adjudicated reference diagnosis in participants assigned to the intervention group. |
| Time from emergency department presentation to final diagnosis | During the index emergency department visit (average 6 hours) | Time required from emergency department presentation until establishment of the physician's final emergency department diagnosis. |
| Diagnostic reclassification after Generative Pre-trained Transformer (GPT)-assisted evaluation | During the index emergency department visit (average 6 hours) | Frequency of changes between the physician's initial working diagnosis and the final emergency department diagnosis after review of Generative Pre-trained Transformer (GPT)-generated diagnostic recommendations. |
| Physician diagnostic confidence | During the index emergency department visit (average 6 hours) | Physician-reported diagnostic confidence recorded before and after Generative Pre-trained Transformer (GPT)-assisted diagnostic support using the prespecified study assessment scale. |
| Physician acceptance of Generative Pre-trained Transformer (GPT)-generated diagnostic recommendations | During the index emergency department visit (average 6 hours) | Frequency of physician acceptance, modification, or rejection of Generative Pre-trained Transformer (GPT)-generated diagnostic recommendations in the intervention group. |
| Emergency department disposition accuracy | Up to hospital discharge (average 3 days) | Accuracy of emergency department disposition decisions, including discharge, hospital admission, or intensive care unit admission, compared with the adjudicated reference diagnosis. |
| Emergency department length of stay | Up to hospital discharge (average 3 days) | Length of stay in the emergency department measured from patient presentation until emergency department discharge or hospital admission. |
| Hospital length of stay | Up to hospital discharge (average 3 days) | Total duration of hospitalization from admission until hospital discharge. |
| In-hospital mortality | Up to hospital discharge (average 3 days) | All-cause mortality occurring during the index hospitalization. |
| 30-day all-cause mortality | 30 days | All-cause mortality occurring within 30 days after the index emergency department visit. |
| 30-day emergency department revisit | 30 days | Revisit to any emergency department for any cause within 30 days after the index emergency department visit. |
| 30-day hospital readmission | 30 days | Hospital readmission for any cause within 30 days after discharge from the index hospitalization. |
Countries
South Korea
Contacts
CONTACTYeji Kim, PhD
Outcome results
None listed