A prediction model for ventricular tachycardia events using 24h ambulatory ECG
Bibliographic record
Abstract
Abstract Background Ventricular tachycardia (VT) is a potentially lethal condition that occurs intermittently. The aim of this study was to derive a risk prediction model for VT episodes detected on ≤30 day mobile cardiac telemetry using a 24 hour ambulatory ECG recording. Methods We included patients who were monitored for 2–30 full days in the USA using a full-disclosure mobile cardiac telemetry device in 2017. Patients with a VT episode ≥10 beats duration (VT≥10 beats) on the first full recording day were excluded. Arrhythmias were algorithmically detected and manually verified. A LASSO model was derived for the outcome of a VT≥10 beats detected on days 2–30. Potential predictors included age, sex, and ECG data from the first 24h: heart rate (max, min and mean), premature atrial and ventricular complexes occurring as singles, couplets, triplets, and runs ≥4 beats as well as the fastest rate for each event. The population was split into equal random training and testing samples. Results In a population of 19,789 patients (mean age 65.3, 43.4% men), and during a median recording time of 18 days there were 1,511 patients with at least one VT≥10 beats. The LASSO model had good discrimination in the testing sample, ROC-statistic 0.7586, 95% CI 0.7398–0.7774 (Figure 1a). A model excluding age and gender had similar discrimination (ROC 0.7528, 95% CI 0.7339–0.7717). In the testing sample the model was well calibrated (Figure 1b). In the top quintile more than one in five patients had a VT≥10 beats, enough to warrant extended monitoring. Conclusion A risk score based on variables easily derived from a standard 24h ECG can be used to predict high risk of VT episodes ≥10 beats within 30 days. In the top quintile VT events ≥10 beats were ten times more common than in the bottom quintile. Funding Acknowledgement Type of funding sources: Foundation. Main funding source(s): Hjärt-LungfondenSwedish Society for Medical Research
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 | 0.003 | 0.004 |
| Meta-epidemiology (narrow) | 0.001 | 0.000 |
| Meta-epidemiology (broad) | 0.001 | 0.001 |
| Bibliometrics | 0.001 | 0.000 |
| Science and technology studies | 0.000 | 0.000 |
| Scholarly communication | 0.001 | 0.000 |
| Open science | 0.001 | 0.001 |
| Research integrity | 0.001 | 0.001 |
| Insufficient payload (model declined to judge) | 0.002 | 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".