What does this research mean for the field?

Preoperative heart rate variability parameters predict temporary electrical pacing needs with a model achieving an AUC of 0.731 in patients undergoing aortic valve replacement. Novelty: ClaimNovelty.NOVEL_FINDING. Consensus alignment: ConsensusAlignment.NEUTRAL.

What question did this study set out to answer?

Assess the predictive value of preoperative heart rate variability on postoperative pacemaker needs following aortic valve replacement.

February 8, 2026

Prediction of electrical pacing after surgical aortic valve replacement using machine learning algorithm and heart rate variability: a retrospective analysis

Key Result

RandomForest model using preoperative HRV and clinical data predicted post-AVR temporary pacing with AUROC 0.731 and AUPRC 0.687 in 194 patients.

Key Points

Assess the predictive value of preoperative heart rate variability on postoperative pacemaker needs following aortic valve replacement.
Reviewed electrical records of 194 adults after isolated AVR.
Obtained HRV parameters before anesthesia and cardiopulmonary bypass.
Developed machine learning models to predict pacing requirements using HRV and clinical variables.
35.1% of patients required temporary pacing postoperatively.
RandomForest model achieved an AUC of 0.731, indicating good predictive ability.
Eight HRV parameters identified as key predictors for pacing needs.

Structured PICO

Can machine learning models using preoperative heart rate variability predict postoperative electrical pacing requirements in adult patients undergoing isolated surgical aortic valve replacement?

Population

194 adult patients who underwent isolated surgical aortic valve replacement (AVR)

Intervention

Tree-based machine learning (ML) models (RandomForest, LightGBM, and ExtraTrees) using preoperative heart rate variability (HRV) parameters and clinical variables

Outcome

Postoperative temporary electrical pacing requirements assessed at the end of surgery

Machine learning models incorporating preoperative heart rate variability and clinical features show potential for predicting postoperative pacemaker requirements following isolated surgical aortic valve replacement.

Main Result

Absolute Event Rate: 0% vs 0%

Abstract

Abstract Background Pacemaker use due to conduction abnormalities is a common complication following surgical aortic valve replacement (AVR). While heart rate variability (HRV) is associated with sinus node dysfunction and significant dysrhythmias, its predictive value for postoperative electrical pacing requirements after AVR remains unclear. Purpose We aimed to assess the association between preoperative HRV and postoperative pacemaker use in patients undergoing AVR. Methods Pre-registered electrical records from 194 adult patients who underwent isolated AVR were reviewed. HRV parameters in both time and frequency domains were obtained prior to anesthesia induction and before initiating cardiopulmonary bypass. Temporary electrical pacing requirements were assessed at the end of surgery. Tree-based machine learning (ML) models, including RandomForest, LightGBM, and ExtraTrees, were developed using HRV parameters and clinical variables to predict postoperative pacing needs. Results The incidence of temporary electrical pacing postoperatively was 35.1% (34.8% in the training set and 35.9% in the test set), while the rate of permanent pacemaker implantation during the index hospitalization was 3.1%. A feature selection process identified eight HRV parameters, with or without clinical variables, as key predictors for model development. The RandomForest model incorporating both HRV and clinical features achieved an area under the receiver operating characteristic curve of 0.731 (95%CI 0.681–0.781) and an area under the precision-recall curve of 0.687 (95%CI 0.619–0.746). Conclusion ML models leveraging HRV demonstrated potential for predicting postoperative pacemaker requirements following isolated AVR. Accurate prediction of significant conduction disturbances through HRV-based ML algorithms may enable timely interventions and improved management for at-risk patients.graphical abstract

AI से पूछें

Bookmark