Interpreting Wide-Complex Tachycardia With the Use of Artificial Intelligence
Why this work is in the frame
A frame that forgets how it found something cannot be audited. These are the routes that admitted this work.
Bibliographic record
Abstract
BACKGROUND: Adopting artificial intelligence (AI) in medicine may improve speed and accuracy in patient diagnosis. We sought to develop an AI algorithm to interpret wide-complex tachycardia (WCT) electrocardiograms (ECGs) and compare its diagnostic accuracy with that of cardiologists. METHODS: Using 3330 WCT ECGs (2906 supraventricular tachycardia [SVT] and 424 ventricular tachycardia [VT]), we created a training/validation (3131) and a test set (199 ECGs). A convolutional neural network structure using a modification of differentiable architecture search was developed to differentiate between SVT and VT. RESULTS: The mean accuracy of electrophysiology (EP) cardiologists was 92.5% with sensitivity 91.7%, specificity 93.4%, positive predictive value 93.7%, and negative predictive value 91.7%. Non-EP cardiologists had an accuracy of 73.2 ± 14.4% with sensitivity, specificity, and positive and negative predictive values of 59.8 ± 18.2%, 93.8 ± 3.7%, 93.6 ± 2.3%, and 73.2 ± 14.4%, respectively. AI had superior sensitivity and accuracy (91.9% and 93.0%, respectively) than non-EP cardiologists and similar performance compared with EP cardiologists. Mean time to interpret each ECG varied from 10.1 to 13.8 seconds for EP cardiologists and from 3.1 to 16.6 seconds for non-EP cardiologists. AI required a mean of 0.0092 ± 0.0035 seconds for each ECG interpretation. CONCLUSIONS: AI appears to diagnose WCT with accuracy superior to non-EP cardiologists and similar to EP cardiologists. Using AI to assist with ECG interpretations may improve patient care.
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.
Full frame distilled prediction
Teacher imitationNot calibrated prevalence, not ground truth. Human validation pending. Learned from the 10,348 direct Codex labels and 10,348 direct Gemma labels. Candidate is the union of thresholded teacher heads; consensus is their intersection. These outputs are machine_predicted_unvalidated and are not human labels or direct frontier model labels.
Codex and Gemma teacher scores by category
| Category | Codex | Gemma |
|---|---|---|
| Metaresearch | 0.000 | 0.000 |
| Meta-epidemiology (narrow) | 0.000 | 0.000 |
| Meta-epidemiology (broad) | 0.000 | 0.000 |
| Bibliometrics | 0.000 | 0.000 |
| 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) | 0.000 | 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 it