Machine learning method for predicting pacemaker implantation following transcatheter aortic valve replacement

Abstract

Background An accurate assessment of permanent pacemaker implantation (PPI) risk following transcatheter aortic valve replacement (TAVR) is important for clinical decision making. The aims of this study were to investigate the significance and utility of pre‐ and post‐TAVR ECG data and compare machine learning approaches with traditional logistic regression in predicting pacemaker risk following TAVR. Methods Five hundred fifity seven patients in sinus rhythm undergoing TAVR for severe aortic stenosis (AS) were included in the analysis. Baseline demographics, clinical, pre‐TAVR ECG, post‐TAVR data, post‐TAVR ECGs (24 h following TAVR and before PPI), and echocardiographic data were recorded. A Random Forest (RF) algorithm and logistic regression were used to train models for assessing the likelihood of PPI following TAVR. Results Average age was 80 ± 9 years, with 52% male. PPI after TAVR occurred in 95 patients (17.1%). The optimal cutoff of delta PR (difference between post and pre TAVR PR intervals) to predict PPI was 20 ms with a sensitivity of 0.82, a specificity of 0.66. With regard to delta QRS, the optimal cutoff was 13 ms with a sensitivity of 0.68 and a specificity of 0.59. The RF model that incorporated post‐TAVR ECG data (AUC 0.81) more accurately predicted PPI risk compared to the RF model without post‐TAVR ECG data (AUC 0.72). Moreover, the RF model performed better than logistic regression model in predicting PPI risk (AUC: 0.81 vs. 0.69). Conclusions Machine learning using RF methodology is significantly more powerful than traditional logistic regression in predicting PPI risk following TAVR.

Artificial Intelligence in Cardiac Surgery: A Systematic Review

“…Clinicians could potentially be guided by AI applications in making better medical decisions. Eighteen studies reported that AI applications can support clinician decision making (4,7,10,13,16,17,19,21,23,24,26,28,(30)(31)(32)(33)35,38). Machine learning models improve clinician's medical decisions by providing better preoperative risk assessment, stratification and prognostication (10,17,21,24,(30)(31)(32)35,38).…”

“…Eighteen studies reported that AI applications can support clinician decision making (4,7,10,13,16,17,19,21,23,24,26,28,(30)(31)(32)(33)35,38). Machine learning models improve clinician's medical decisions by providing better preoperative risk assessment, stratification and prognostication (10,17,21,24,(30)(31)(32)35,38). AI applications could also guide clinicians on how aggressive prophylactic measures are given such as increased patient monitoring or giving additional therapies (4,13,33).…”

Integrated machine learning a predictor of pacemaker implantation after transcatheter aortic valve replacement

“…There has been enormous interest in applying machine learning and artificial intelligence to healthcare and, in particular, to data-rich environments like the interventional cardiology. 1 In this context, we present and propose a graphical representation of a color-coded representation typical of machine learning in relation to the percentage of predicting pacemaker implantation predictive risk related to the integrated variables of 130 patient underwent TAVR in our institution (Figure 1). We ask the authors if a critical analysis and integrated data collection in relation to ECG and other variables through artificial intelligence and machine learning could be a sustainable approach aimed at implementing the quality of clinical research in TAVR.…”

“…In this context, we read with great interest the article: "Machine learning method for predicting pacemaker implantation following transcatheter aortic valve replacement" by Truong et al; the authors investigated about the significance and utility of pre-and post-TAVR electrocardiogram (ECG) data and compared machine learning approaches with traditional logistic regression in predicting pacemaker risk following TAVR. 1 The existing literature to examine the incidence and predictors of predicting pacemaker implantation after TAVR according to generation of valve, valve type, and surgical risk and concluded that the principal independent predictors for predicting pacemaker implantation following TAVR are age, right bundle branch block (RBBB), left bundle branch block (LBBB), self-expanding valve type, and valve implantation depth. These characteristics should be taken in pre-procedural assessment to reduce permanent pacemaker implantation rates.…”

Random forest vs. logistic regression: Predicting angiographic in-stent restenosis after second-generation drug-eluting stent implantation

“…In a large-scale benchmark experiment, RF outperformed LR in prediction in 69% of datasets from open ML databases [ 6 ]. Vien et al found that the RF model was superior to the traditional LR model in predicting pacemaker implantation following transcatheter aortic valve replacement [ 7 ]. A previous study reported that the ML-based algorithms had higher accuracy than the existing risk score model in predicting ISR [ 8 ].…”