Abstract 16753: Baseline Prediction of Atrial Fibrillation Recurrence After Catheter Ablation: Comparative Analysis of Prognostic Models Using Data Recorded by Implanted Cardiac Monitors
Bibliographic record
Abstract
Intro: Tools for baseline prediction of catheter ablation outcome are instrumental to treatment management that best balances positive outcomes against risk of treatment complications. To date, many such predictive models exist in the literature; yet, it is unclear which should be adopted as no study has compared all using a single dataset. Goals: examine 8 published models using a single dataset with expert-annotated data recorded by implanted monitors. Methods: We collected data from a cohort of ~350, acquired from a randomized clinical trial blinded to ablation outcome. Based on a 2020 review, we shortlisted 12 models for baseline prediction of recurrences recorded between days 91-365 post ablation per standard. Models that use postoperative data, thus unsuited for baseline prediction, were excluded. Four models were further dropped from this work as their required variables (e.g. normalized atrial area) are unavailable in our cohort. Results: There was no missing variable; 34% were female and 53% of patients experienced recurrence. Figure reports each model’s performance with metrics as sensitivity (SEN), specificity (SPEC), positive predictive value (PPV), negative predictive value (NPV), area under receiver operating characteristic curve (AUC), positive and negative clinical utility indices (SENxPPV; SPECxNPV, resp.). The digit after each model name indicates the cut-off used (some studies used different cut-offs). Models are presented in rank-order by utility indices. All evaluated scores achieved AUC<65 and deemed to have poor utility. A model that examines age, stroke, hypertension, heart failure, chronic obstructive pulmonary disease, and obstructive sleep apnea, performed best in this cohort (SEN=54, SPEC=70,PPV=65,NPV=60,AUC=62). Conclusions: Our results reinforce statements of previous reviews that many published models are lacking and that there remains a need to develop and validate models for prediction of AFR post ablation.
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 | 0.013 | 0.043 |
| Meta-epidemiology (narrow) | 0.001 | 0.000 |
| Meta-epidemiology (broad) | 0.002 | 0.006 |
| Bibliometrics | 0.003 | 0.002 |
| Science and technology studies | 0.000 | 0.000 |
| Scholarly communication | 0.002 | 0.001 |
| Open science | 0.001 | 0.001 |
| Research integrity | 0.001 | 0.001 |
| Insufficient payload (model declined to judge) | 0.006 | 0.002 |
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".