Key result
Five-minute intraoperative HRV modestly predicts near-term arrhythmia with ~0.68 AUROC.
Why the study?
Rhythm disturbance is the most frequent cardiovascular abnormality of the operative period, and whether the autonomic profile of a short intraoperative observation window predicts significant arrhythmia in the following minutes was untested.
Does the autonomic and ectopic profile of a 300-second intraoperative ECG observation window predict incident significant arrhythmia in the following 300 seconds among surgical patients?
Cohort (n=299)
No
Does the autonomic and ectopic profile of a 300-second intraoperative ECG observation window predict incident significant arrhythmia in the following 300 seconds among surgical patients?
A 5-minute intraoperative heart rate variability profile derived solely from bedside monitor R-peak timing and beat labels modestly predicts incident significant arrhythmias—especially bradyarrhythmias—over the subsequent 5 minutes, performing equally well with simple logistic regression as with machine learning.
Answers are grounded in this paper and cite their sources.
Brief intraoperative HRV monitoring should not yet alter arrhythmia surveillance; leaves open its value for prospective risk stratification in surgical cohorts.
Rhythm disturbance is the most frequent cardiovascular abnormality of the operative period, and new onset atrial fibrillation carries lasting stroke and mortality risk. We tested whether the autonomic profile of a short intraoperative observation window predicts significant arrhythmia in the minutes that follow. Secondary analysis of the VitalDB Arrhythmia Database, with anesthesiologist adjudicated annotations from 482 surgical cases. A 300 s index window was taken at the start of each annotated segment, with the following 300 s as the outcome window. Cases free of significant arrhythmia during the index window were eligible. The endpoint was incident significant arrhythmia, a composite of atrial and ventricular tachyarrhythmias, atrioventricular block and sinus node dysfunction. Logistic regression, random forest and gradient boosting were compared by repeated stratified cross validation. Of 482 cases, 299 were eligible and 109 (36.5%) reached the endpoint. Logistic regression and the random forest discriminated similarly, with areas under the curve of 0.670 (95% CI 0.604 to 0.732) and 0.682 (0.620 to 0.742) (DeLong p = 0.55). The random forest had a favorable calibration slope (0.94), with overprediction of absolute risk, and a negative predictive value of 80.9%. Discrimination was highest for bradyarrhythmic events (0.749). Lower pNN50 and RMSSD, and unexpectedly lower ventricular ectopy, were associated with the endpoint. Ventricular tachyarrhythmia episodes were short, with a median of 4 beats. A five minute heart rate variability profile, derived only from R peak timing and beat labels, predicts significant arrhythmia in the following five minutes of surgery. The signal is physiologically coherent, strongest for bradyarrhythmias, and captured as well by logistic regression as by machine learning. This first prediction benchmark on the VitalDB Arrhythmia Database provides a reproducible foundation for externally validated, clinically enriched intraoperative rhythm prediction.
No takes yet. Share an insight, caveat, or question.
Eini et al. (2026) conducted a cohort in Surgical patients undergoing intraoperative electrocardiographic monitoring (n=299). 5-minute (300-second) intraoperative heart rate variability and ectopy profile evaluated via logistic regression, random forest, and gradient boosting models vs. Comparison between classifiers (logistic regression, random forest, gradient boosting) and between cases with vs. without incident significant arrhythmia was evaluated on Incident significant arrhythmia (composite of atrial fibrillation or flutter, supraventricular tachyarrhythmia, ventricular tachyarrhythmia, atrioventricular block, sinus node dysfunction, and multifocal atrial tachycardia) (AUROC 0.682 (random forest); AUROC 0.670 (logistic regression), 95% CI 0.620 to 0.742, p=0.55). Five-minute intraoperative heart rate variability predicted incident significant arrhythmia in the next 5 minutes with AUROCs of 0.682 for random forest and 0.670 for logistic regression (p=0.55).
Synapse has enriched 10 related papers. Consider them for comparative context: