Funding Acknowledgements Type of funding sources: None. Background Relative benefits of transvenous lead extraction (TLE) should be weighed against the risks on an individual basis. Observational studies have identified disparate risk factors for major adverse events (MAEs), however there are few available tools to aid the clinician risk-stratifying patients. Purpose The purpose of this study was to develop a machine learning (ML)-based risk stratification system to predict risk of MAEs following transvenous lead extraction (TLE). Methods Multiple ML models were derived from a training cohort of 3555 patients undergoing TLE to pre-procedurally identify patients at high and low risk of major adverse events (procedure-related major complication, including procedure-related death). The ML models were then tested on an independent, reference centre cohort of 1171 patients undergoing TLE. Clinical features were selected based on whether they were available in both datasets without large gaps. For model selection we compared the ML algorithms logistic regression, ridge regression, support vector machines (SVM), gradient boosting classifier and random forest. The best performing of these was then compared to a self-normalising network (SNN). Results In total 3122 cases with the required features were included from the training cohort with 53 MAEs (1.7%), and 998 cases in the test cohort with 24 MAEs (2.4%). SVM identified lead dwell time, left ventricular ejection fraction (LVEF), estimated glomerular filtration rate (eGFR), chronic respiratory disease, local infection, heart failure, sepsis and male gender as predictors of MAEs in order of decreasing importance (see figure). For the training data, the SVM provided a more sensitive result compared with SNN (0.83 vs 0.71) at the cost of specificity (0.63 vs 0.79). For the test data, the SVM identified MAEs in 12 out of 123 (9.8%) "high risk" patients, 10 out of 552 (1.8%) "medium risk" patients, and 2 out of 323 (0.006%) "low risk" patients. Conclusion Machine learning provided good discriminative capabilities for identifying patients in a "high risk" and "low risk" category for MAEs. Abstract Figure. 8 most important predictors of MAEs
Funding Acknowledgements Type of funding sources: None. Background Among patients undergoing transvenous lead extraction (TLE), differences in complication rate and 1-year mortality has been explored in patients with cardiac resynchronisation therapy (CRT) devices. Longer term outcomes and the influence of timing of reimplantation of device, with respect to rehospitalisation and longer-term mortality is poorly understood. Purpose The purpose of this study was to evaluate whether early reimplantation following TLE in patients with CRT devices influenced survival and rehospitalisation. Methods Clinical data from consecutive patients undergoing TLE in the reference centre between the years 2000 to 2019 were prospectively collected. Patients surviving to discharge who were re-implanted with the same device were included. The cohort was split depending on whether or not they had a CRT device at time of explant. The association between TLE in CRT patients and all-cause mortality and re-hospitalisation was assessed by Kaplan Meier estimates in a 1:1 propensity-score matched cohort, with a calliper of 0.10. Early reimplantation was defined as reimplantation within 7 days of TLE, and late reimplantation as reimplantation after greater than 7 days of TLE. Results Of 1005 patients included in the analysis, 285 (25%) had a CRT device. After matching, 192 CRT patients were compared with 192 non-CRT patients. Propensity scores were calculated using 39 baseline characteristics, including age, gender, co-morbidities, TLE indication, left ventricular ejection fraction, baseline creatinine and technical extraction data. Mean follow up was 53.5 ± 38.3 months, mean age at explant was 67.7 ± 12.1 years, 83.3% were male and 54.4% had an infective indication for TLE. In the matched cohort, there was no significant difference between the CRT and non-CRT group with respect to long-term mortality (hazard ratio [HR] = 1.01, 95% confidence interval [CI] [0.74-1.39], p = 0.093) or rehospitalisation (HR = 1.2 [0.87-1.66], p = 0.265). A similar proportion of patients were reimplanted within 7 days in the CRT and non-CRT groups (59.4% vs 61.5%, p = 0.754). In the matched non-CRT group, late reimplantation was associated with similar mortality to early reimplantation (HR = 1.33 [0.86-2.05], p = 0.208) and rehospitalisation (HR = 0.88 [0.53-1.45], p = 0.603). In the matched CRT group, late reimplantation was associated with higher mortality (HR = 1.64 [1.04-2.57], p = 0.032) and rehospitalisation (HR = 1.57 [1.00-2.46], p = 0.049] (see figure). Conclusion In this closely matched population, TLE in CRT patients resulted in similar long-term outcomes compared with non-CRT patients. Early reimplantation post CRT explant was associated with reduced long-term mortality and rehospitalisation. This suggests a longer duration without biventricular pacing post TLE may induce negative reverse-remodelling and should be avoided in a CRT population. Abstract Figure. Kaplan-Meier survival curves
scite is a Brooklyn-based organization that helps researchers better discover and understand research articles through Smart Citations–citations that display the context of the citation and describe whether the article provides supporting or contrasting evidence. scite is used by students and researchers from around the world and is funded in part by the National Science Foundation and the National Institute on Drug Abuse of the National Institutes of Health.
customersupport@researchsolutions.com
10624 S. Eastern Ave., Ste. A-614
Henderson, NV 89052, USA
Copyright © 2024 scite LLC. All rights reserved.
Made with 💙 for researchers
Part of the Research Solutions Family.