Abstract 4358321: ECG-SMART: A Clinician-Guided AI Dashboard for Occlusion Myocardial Infarction Detection in the Emergency Department
Bibliographic record
Abstract
Artificial Intelligence (AI)-driven ECG methods are transforming clinical workflows, signaling a shift in ECG analysis research and clinical practice. Adoption in routine care remains limited—largely due to challenges with explainability and poor integration into existing workflows. Combining human expertise with AI has potential to enhance research translation to improve clinical decision-making and patient outcomes. We applied human-computer interaction principles to develop ECG-SMART, a clinician-facing AI dashboard designed to estimate the likelihood of occlusion myocardial infarction (OMI) while intuitively communicating the model’s reasoning. We aimed to refine an ECG-SMART dashboard based on feedback from practicing clinicians through a series of qualitative focus groups (FG) and clinical usability sessions. Guided by user-centered design principles, we conducted 2 rounds of virtual FGs moderated by a FG methodologist. We asked open-ended questions to elicit feedback from clinical end-users on the scope and presentation of information provided by the dashboard prototype. Round 1 consisted of 3 separate FG sessions (paramedics, ED physicians, and cardiologists) who reviewed the prototype. Feedback was used to derive a modified version of the dashboard. Round 2 combined FGs with all available clinicians who participated in Round 1 to further refine the dashboard. All FGs were recorded and transcribed. Transcripts were coded by 3 research team members to identify recurrent patterns until thematic saturation was reached. After resolution of coding discrepancies, codes coalesced into emerging themes resulting in clinician-recommended dashboard changes. Twelve clinicians participated (mean age = 40 years, 25% female, mean clinical experience = 14 years). Five themes emerged: interpretation and clinical context, trust and explainability, AI recommendations and labels, risk stratification and AI scoring, and workflow and dashboard design. Dashboard design changes included, simplified color coding, improved OMI risk score display, enhanced AI prediction explainability and functionality, access to historical 12-lead ECGs, and revision of clinical action recommendation language. Figure 1 details the dashboard evolution. Engaging multidisciplinary clinicians in the design and refinement of an intelligent AI-ECG dashboard bridges the gap between AI developers and target end-users, improving clinical utility and acceptability for widespread clinical implementation.
Fetched live from OpenAlex and de-inverted. Abstracts are not stored in this database: the inverted indexes are 8.6 GB of the frame’s 9.3 GB of text, and the host has 13 GB free.
How this classification was reachedexpand
Full frame machine prediction
Teacher imitationNot calibrated prevalence, not ground truth. Human validation pending. The Gemma side is a direct model label for every work in the frame, read from the title-only record. The Codex side is a classifier learned from the 10,348 direct Codex labels and calibrated to design-weighted sample rates; fields without enough sample support carry no Codex call. Candidate is the union of the two sides; consensus is their intersection. These outputs are machine_predicted_unvalidated and are not human labels.
Distilled classifier scores by category (both heads)
| Category | Codex | Gemma |
|---|---|---|
| Metaresearch | 0.007 | 0.025 |
| Meta-epidemiology (narrow) | 0.001 | 0.000 |
| Meta-epidemiology (broad) | 0.001 | 0.001 |
| Bibliometrics | 0.001 | 0.001 |
| Science and technology studies | 0.001 | 0.001 |
| Scholarly communication | 0.002 | 0.002 |
| Open science | 0.001 | 0.002 |
| Research integrity | 0.002 | 0.001 |
| Insufficient payload (model declined to judge) | 0.036 | 0.010 |
Machine scores (provisional)
The two teacher heads of the student model, read on this work. A score orders the frame for review; it never asserts a category, and the validation status ships verbatim with every row.
Baseline scores from an immature model (maturity gate not passed, 7 training rounds). Scores rank; they never assert a category.
score_only:v0-immature-baseline · verbatim from the scoring run: score_only means the number may rank works, and no category label ships from itClassification
machine, unvalidatedMachine predicted; a candidate call from one source (direct Gemma or distilled Codex), not a consensus.
How this classification was reached, model by model and score by score, is at the end of the page under "How this classification was reached".