Reducing Delay to Treatment of ST-Elevation Myocardial Infarction With Software Electrocardiographic Interpretation and Transmission (SCINET)
Bibliographic record
Abstract
BACKGROUND: Prehospital diagnosis of ST-elevation myocardial infarction (STEMI) has resulted in improved outcomes. However, many patients still walk in to the emergency department (ED) with STEMI, experiencing delays and worse outcomes. Software electrocardiogram (ECG) diagnosis of STEMI and electronic transmission to a cardiologist may result in improved door-to-device (D2D) times. METHODS: We retrospectively identified all patients presenting with STEMI from January 2015 to September 2016. Components of delay in D2D, ED variables, and the patients' ECGs were extracted from our regional database. All ECGs performed for suspected myocardial infarction in the region were extracted over the study period. We assessed the accuracy of the software 12SL in diagnosing STEMI, ED contributors to delays in D2D, and the potential reduction in D2D if software diagnosis of STEMI resulted in activation of the cardiac catheterization laboratory. RESULTS: A total of 379 patients presented to an ED in our region and received primary percutaneous coronary intervention over the study period. In the 143,574 ECGs performed over the study period for suspected STEMI, the overall sensitivity and specificity of 12SL were 90.5% and 99.98%, respectively. We estimated a potential 17-minute reduction in D2D in the 90.5% of patients correctly identified as having STEMI, with a false activation rate of 4%. Female patients and older patients experienced an even larger potential benefit, with 24- and 25-minute reductions in D2D, respectively. CONCLUSIONS: Patients who walk in to an ED with STEMI experience significant system-related delays in recognition and treatment. Automated software diagnosis of STEMI is accurate and could result in significant improvements in D2D times.
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 | 0.001 | 0.011 |
| Meta-epidemiology (narrow) | 0.000 | 0.000 |
| Meta-epidemiology (broad) | 0.000 | 0.000 |
| Bibliometrics | 0.001 | 0.001 |
| Science and technology studies | 0.000 | 0.000 |
| Scholarly communication | 0.000 | 0.000 |
| Open science | 0.000 | 0.000 |
| Research integrity | 0.000 | 0.000 |
| Insufficient payload (model declined to judge) | 0.001 | 0.000 |
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".