Abstract 16187: Validation of Novel Algorithm to Automate Detection of Fractionated Electrograms During Ventricular Tachycardia (VT) Ablation
Bibliographic record
Abstract
Introduction: Ablation of ventricular tachycardia (VT) substrate in patient at risk for VT in the setting of ischemic heart disease is a technically challenging procedure. We thought to evaluate a novel algorithm used to automatically identify target electrograms. Methods: 16 consecutive patients (70±10 years of age, 90% male, 34±18% LV EF) had 20 ablations for ischemic VT using CARTO 3 mapping system over 2 years. Left ventricular (LV) substrate was mapped during right ventricular (RV) apical stimulation. Navistar Thermocool 3.5 mm irrigated tip catheters were used in all patients. A novel algorithm counting the number of electrogram deflections (NOD) crossing the 0.05mV noise threshold and duration of time from first to last such deflection during the window of interest (total fractionation time, TFT) was applied to all acquired maps after ablation was complete. Snapshots of 200 electrograms representing the high and low end of TFT and NOD values were presented to a group of 8 electrophysiologists experienced in VT ablation who were asked to select electrograms they would target for substrate ablation. The diagnostic accuracy of TFT and NOD values was then analysed. Results: Across the range of TFT values (0.0-281.0 ms), a cut-off value of 49.0 ms (81.6% sensitivity, 57% specificity) was established as an optimal indicator of an ablation target. Area under the curve for TFT was 0.675 (95% CI: 0.59-0.75, p=0.001). For NOD values (0.0-70.0 deflections), a cut off of 4.5 deflections (88.0% Sensitivity, 57 % specificity) was established as an optimal indicator of an ablation target. The area under the curve for NOD yielded an area of 0.75 (95% CI: 0.68-0.82, P=0.001). For TFT-NOD product as a variable, a cut-off value of 64 (91.0% Sensitivity, 52.4 % specificity) an optimal indicator of an ablation target. The Area under the curve for NOD and TFT multiple was 0.72 (95% CI: 0.65-0.80, P=0.001). Conclusion: A novel algorithm may be able to automatically classify LV substrate during mapping and ablation of ischemic VT with high sensitivity and acceptable specificity.
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 | 0.004 |
| Meta-epidemiology (narrow) | 0.001 | 0.000 |
| Meta-epidemiology (broad) | 0.001 | 0.000 |
| Bibliometrics | 0.001 | 0.000 |
| Science and technology studies | 0.000 | 0.000 |
| Scholarly communication | 0.001 | 0.000 |
| Open science | 0.001 | 0.000 |
| Research integrity | 0.001 | 0.000 |
| Insufficient payload (model declined to judge) | 0.001 | 0.001 |
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".